loop-benchmarking

Controlled experiments across agentic coding configurations. Same task, one variable, what actually works.
git clone https://git.shiptheloop.com/loop-benchmarking.git
Log | Files | Refs | README

commit 46364ff78312c3c0d5d647e2f6d59c0c40345cec
parent 03f7652cb15c203683d9239f08dc22efbb51b1b5
Author: Brian Graham <brian@buildingbetterteams.de>
Date:   Thu, 16 Apr 2026 15:53:40 +0200

Analyze and push 512 runs

Diffstat:
Mresults/analysis/main_effects_build_quality.json | 170+------------------------------------------------------------------------------
Mresults/analysis/main_effects_code_quality.json | 572++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/analysis/main_effects_cost.json | 446++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/analysis/main_effects_gameplay.json | 596++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/analysis/main_effects_score.json | 596++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/analysis/main_effects_sonarqube.json | 650++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/analysis/main_effects_structural.json | 608++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/analysis/main_effects_transcript.json | 508++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/analysis/main_effects_turns.json | 428++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/analysis/main_effects_wall_time.json | 500++++++++++++++++++++++++++++++++++++++++----------------------------------------
Mresults/index.jsonl | 342+++++++++++++++++++++++++++++--------------------------------------------------
11 files changed, 2581 insertions(+), 2835 deletions(-)

diff --git a/results/analysis/main_effects_build_quality.json b/results/analysis/main_effects_build_quality.json @@ -1,167 +1 @@ -{ - "architecture": { - "values": { - "best_practices": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - }, - "none": { - "mean": 0.67, - "effect": 0.0, - "n": 54 - }, - "separation": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - } - }, - "spread": 0.0 - }, - "context_noise": { - "values": { - "clean": { - "mean": 0.67, - "effect": 0.0, - "n": 36 - }, - "lorem_100k": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - }, - "lorem_10k": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - }, - "lorem_1k": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - }, - "lorem_50k": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - }, - "wikipedia_100k": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - }, - "wikipedia_10k": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - }, - "wikipedia_1k": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - }, - "wikipedia_50k": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - } - }, - "spread": 0.0 - }, - "design_guidance": { - "values": { - "none": { - "mean": 0.67, - "effect": 0.0, - "n": 54 - }, - "specific": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - }, - "vague": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - } - }, - "spread": 0.0 - }, - "error_checking": { - "values": { - "none": { - "mean": 0.67, - "effect": 0.0, - "n": 57 - }, - "self_verify": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - } - }, - "spread": 0.0 - }, - "playwright": { - "values": { - "instructed": { - "mean": 0.67, - "effect": 0.0, - "n": 2 - }, - "off": { - "mean": 0.67, - "effect": 0.0, - "n": 58 - } - }, - "spread": 0.0 - }, - "strategy": { - "values": { - "creative_validate": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - }, - "delegate": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - }, - "iterate": { - "mean": 0.67, - "effect": 0.0, - "n": 2 - }, - "none": { - "mean": 0.67, - "effect": 0.0, - "n": 41 - }, - "plan_first": { - "mean": 0.67, - "effect": 0.0, - "n": 2 - }, - "review": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - }, - "split_work": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - }, - "use_subagents": { - "mean": 0.67, - "effect": 0.0, - "n": 3 - } - }, - "spread": 0.0 - } -} -\ No newline at end of file +{} +\ No newline at end of file diff --git a/results/analysis/main_effects_code_quality.json b/results/analysis/main_effects_code_quality.json @@ -1,477 +1,477 @@ { - "context_noise": { - "values": { - "clean": { - "mean": 0.4467, - "effect": -0.0167, - "n": 433 - }, - "lorem_100k": { - "mean": 0.7667, - "effect": 0.3033, - "n": 3 - }, - "lorem_10k": { - "mean": 0.75, - "effect": 0.2866, - "n": 3 - }, - "lorem_1k": { - "mean": 0.7, - "effect": 0.2366, - "n": 3 - }, - "lorem_50k": { - "mean": 0.8167, - "effect": 0.3533, - "n": 3 - }, - "wikipedia_100k": { - "mean": 0.7667, - "effect": 0.3033, - "n": 3 - }, - "wikipedia_10k": { - "mean": 0.7667, - "effect": 0.3033, - "n": 3 - }, - "wikipedia_1k": { - "mean": 0.7833, - "effect": 0.3199, - "n": 3 - }, - "wikipedia_50k": { - "mean": 0.7667, - "effect": 0.3033, - "n": 3 - } - }, - "spread": 0.37 - }, "model": { "values": { "gemma-4-26b": { "mean": 0.4488, - "effect": -0.0146, + "effect": 0.0525, "n": 43 }, "glm-4.5-air": { - "mean": 0.3217, - "effect": -0.1417, + "mean": 0.318, + "effect": -0.0783, "n": 41 }, "glm-4.7": { - "mean": 0.3554, - "effect": -0.1081, - "n": 28 + "mean": 0.3222, + "effect": -0.0741, + "n": 81 }, "glm-5.1": { - "mean": 0.6011, - "effect": 0.1377, + "mean": 0.393, + "effect": -0.0033, "n": 123 }, "haiku-4.5": { - "mean": 0.347, - "effect": -0.1164, + "mean": 0.3464, + "effect": -0.0499, "n": 89 }, "kimi-k2.5": { "mean": 0.3667, - "effect": -0.0967, + "effect": -0.0297, "n": 3 }, "minimax-m2.7": { "mean": 0.4167, - "effect": -0.0467, + "effect": 0.0203, "n": 3 }, "opus-4.6": { "mean": 0.5083, - "effect": 0.0449, + "effect": 0.1119, "n": 52 }, "qwen-3.6-plus": { "mean": 0.3973, - "effect": -0.0661, + "effect": 0.0009, "n": 22 }, "sonnet-4.6": { "mean": 0.5094, - "effect": 0.046, + "effect": 0.1131, "n": 53 } }, - "spread": 0.2794 + "spread": 0.1914 }, "strategy": { "values": { "creative_validate": { - "mean": 0.32, - "effect": -0.1434, + "mean": 0.27, + "effect": -0.1263, "n": 8 }, "delegate": { - "mean": 0.53, - "effect": 0.0666, - "n": 5 + "mean": 0.3029, + "effect": -0.0935, + "n": 7 }, "iterate": { - "mean": 0.3944, - "effect": -0.069, - "n": 9 + "mean": 0.3091, + "effect": -0.0872, + "n": 11 }, "none": { - "mean": 0.466, - "effect": 0.0025, - "n": 257 + "mean": 0.3774, + "effect": -0.0189, + "n": 300 }, "plan_first": { - "mean": 0.49, - "effect": 0.0266, - "n": 7 + "mean": 0.368, + "effect": -0.0283, + "n": 10 }, "review": { - "mean": 0.59, - "effect": 0.1266, + "mean": 0.38, + "effect": -0.0163, "n": 5 }, "split_work": { - "mean": 0.564, - "effect": 0.1006, + "mean": 0.414, + "effect": 0.0177, "n": 5 }, "use_subagents": { - "mean": 0.4601, - "effect": -0.0034, - "n": 161 + "mean": 0.4486, + "effect": 0.0523, + "n": 164 } }, - "spread": 0.27 + "spread": 0.1786 + }, + "language": { + "values": { + "javascript": { + "mean": 0.4838, + "effect": 0.0875, + "n": 21 + }, + "typescript": { + "mean": 0.388, + "effect": -0.0083, + "n": 469 + }, + "unspecified": { + "mean": 0.5, + "effect": 0.1037, + "n": 20 + } + }, + "spread": 0.112 }, "renderer": { "values": { "canvas": { - "mean": 0.5375, - "effect": 0.0741, - "n": 4 + "mean": 0.3, + "effect": -0.0963, + "n": 7 }, "dom": { "mean": 0.4, - "effect": -0.0634, - "n": 4 + "effect": 0.0037, + "n": 5 }, "none": { - "mean": 0.461, - "effect": -0.0025, - "n": 441 + "mean": 0.399, + "effect": 0.0027, + "n": 487 }, "svg": { - "mean": 0.6125, - "effect": 0.1491, - "n": 4 + "mean": 0.3029, + "effect": -0.0935, + "n": 7 }, "webgl": { - "mean": 0.575, - "effect": 0.1116, + "mean": 0.4, + "effect": 0.0037, "n": 4 } }, - "spread": 0.2125 + "spread": 0.1 }, - "architecture": { + "playwright": { "values": { - "best_practices": { - "mean": 0.65, - "effect": 0.1866, - "n": 4 + "available": { + "mean": 0.4485, + "effect": 0.0522, + "n": 165 }, - "none": { - "mean": 0.4602, - "effect": -0.0032, - "n": 448 + "instructed": { + "mean": 0.3582, + "effect": -0.0382, + "n": 11 }, - "separation": { - "mean": 0.6, - "effect": 0.1366, - "n": 5 + "off": { + "mean": 0.3718, + "effect": -0.0245, + "n": 334 } }, - "spread": 0.1898 + "spread": 0.0903 }, - "design_guidance": { + "context_noise": { "values": { - "none": { - "mean": 0.4601, - "effect": -0.0033, - "n": 447 + "clean": { + "mean": 0.3978, + "effect": 0.0015, + "n": 477 }, - "specific": { - "mean": 0.6, - "effect": 0.1366, - "n": 5 + "lorem_100k": { + "mean": 0.3283, + "effect": -0.068, + "n": 6 }, - "vague": { - "mean": 0.62, - "effect": 0.1566, - "n": 5 + "lorem_10k": { + "mean": 0.3833, + "effect": -0.013, + "n": 6 + }, + "lorem_1k": { + "mean": 0.35, + "effect": -0.0463, + "n": 3 + }, + "lorem_50k": { + "mean": 0.3583, + "effect": -0.038, + "n": 6 + }, + "wikipedia_100k": { + "mean": 0.4167, + "effect": 0.0203, + "n": 3 + }, + "wikipedia_10k": { + "mean": 0.4, + "effect": 0.0037, + "n": 3 + }, + "wikipedia_1k": { + "mean": 0.4167, + "effect": 0.0203, + "n": 3 + }, + "wikipedia_50k": { + "mean": 0.4, + "effect": 0.0037, + "n": 3 } }, - "spread": 0.1599 + "spread": 0.0884 }, "error_checking": { "values": { "none": { - "mean": 0.4623, - "effect": -0.0011, - "n": 453 + "mean": 0.397, + "effect": 0.0007, + "n": 506 }, "self_verify": { - "mean": 0.5875, - "effect": 0.1241, + "mean": 0.3125, + "effect": -0.0838, "n": 4 } }, - "spread": 0.1252 - }, - "human_language": { - "values": { - "en": { - "mean": 0.4688, - "effect": 0.0054, - "n": 429 - }, - "es": { - "mean": 0.3807, - "effect": -0.0827, - "n": 28 - } - }, - "spread": 0.0881 + "spread": 0.0845 }, "provider": { "values": { "anthropic": { - "mean": 0.4346, - "effect": -0.0288, + "mean": 0.4343, + "effect": 0.038, "n": 194 }, "openrouter": { "mean": 0.428, - "effect": -0.0354, + "effect": 0.0317, "n": 71 }, "zai": { - "mean": 0.5056, - "effect": 0.0422, - "n": 192 + "mean": 0.3571, + "effect": -0.0393, + "n": 245 } }, - "spread": 0.0776 + "spread": 0.0772 }, - "tool_write": { + "prompt_style": { "values": { - "off": { - "mean": 0.3984, - "effect": -0.065, - "n": 31 + "detailed": { + "mean": 0.445, + "effect": 0.0487, + "n": 30 }, - "on": { - "mean": 0.4681, - "effect": 0.0047, - "n": 426 + "simple": { + "mean": 0.3933, + "effect": -0.003, + "n": 480 } }, - "spread": 0.0697 + "spread": 0.0517 }, - "context_file": { + "tool_grep": { "values": { - "none": { - "mean": 0.4678, - "effect": 0.0044, - "n": 428 + "off": { + "mean": 0.4326, + "effect": 0.0362, + "n": 31 }, - "provided": { - "mean": 0.399, - "effect": -0.0644, - "n": 29 + "on": { + "mean": 0.394, + "effect": -0.0023, + "n": 479 } }, - "spread": 0.0688 + "spread": 0.0386 }, - "max_budget": { + "tool_read": { "values": { - "high": { - "mean": 0.4017, - "effect": -0.0617, - "n": 23 + "off": { + "mean": 0.431, + "effect": 0.0346, + "n": 31 }, - "low": { - "mean": 0.4667, - "effect": 0.0033, - "n": 434 + "on": { + "mean": 0.3941, + "effect": -0.0022, + "n": 479 } }, - "spread": 0.065 + "spread": 0.0369 }, - "web_search": { + "linter": { "values": { "off": { - "mean": 0.4042, - "effect": -0.0592, - "n": 33 + "mean": 0.4231, + "effect": 0.0267, + "n": 39 }, "on": { - "mean": 0.468, - "effect": 0.0046, - "n": 424 + "mean": 0.3941, + "effect": -0.0022, + "n": 471 } }, - "spread": 0.0638 + "spread": 0.029 }, - "language": { + "architecture": { "values": { - "javascript": { - "mean": 0.5055, - "effect": 0.0421, - "n": 20 + "best_practices": { + "mean": 0.375, + "effect": -0.0213, + "n": 4 }, - "typescript": { - "mean": 0.4596, - "effect": -0.0038, - "n": 417 + "none": { + "mean": 0.3968, + "effect": 0.0004, + "n": 501 }, - "unspecified": { - "mean": 0.5, - "effect": 0.0366, - "n": 20 + "separation": { + "mean": 0.37, + "effect": -0.0263, + "n": 5 } }, - "spread": 0.0459 + "spread": 0.0268 }, - "tool_glob": { + "human_language": { "values": { - "off": { - "mean": 0.4204, - "effect": -0.043, - "n": 27 + "en": { + "mean": 0.3978, + "effect": 0.0014, + "n": 481 }, - "on": { - "mean": 0.4661, - "effect": 0.0027, - "n": 430 + "es": { + "mean": 0.3724, + "effect": -0.0239, + "n": 29 } }, - "spread": 0.0457 + "spread": 0.0254 }, - "linter": { + "tool_edit": { "values": { "off": { - "mean": 0.4263, - "effect": -0.0371, - "n": 38 + "mean": 0.4089, + "effect": 0.0125, + "n": 35 }, "on": { - "mean": 0.4668, - "effect": 0.0034, - "n": 419 + "mean": 0.3954, + "effect": -0.0009, + "n": 475 } }, - "spread": 0.0405 + "spread": 0.0135 }, - "tool_edit": { + "tool_glob": { "values": { "off": { - "mean": 0.4294, - "effect": -0.034, - "n": 33 + "mean": 0.4057, + "effect": 0.0093, + "n": 30 }, "on": { - "mean": 0.4661, - "effect": 0.0026, - "n": 424 + "mean": 0.3957, + "effect": -0.0006, + "n": 480 } }, - "spread": 0.0367 + "spread": 0.01 }, - "tool_grep": { + "design_guidance": { "values": { - "off": { - "mean": 0.437, - "effect": -0.0264, - "n": 30 + "none": { + "mean": 0.3965, + "effect": 0.0001, + "n": 500 }, - "on": { - "mean": 0.4653, - "effect": 0.0019, - "n": 427 + "specific": { + "mean": 0.39, + "effect": -0.0063, + "n": 5 + }, + "vague": { + "mean": 0.39, + "effect": -0.0063, + "n": 5 } }, - "spread": 0.0283 + "spread": 0.0065 }, "effort": { "values": { "high": { - "mean": 0.4644, - "effect": 0.001, - "n": 441 + "mean": 0.3964, + "effect": 0.0001, + "n": 491 }, "max": { - "mean": 0.4369, - "effect": -0.0265, - "n": 16 + "mean": 0.3937, + "effect": -0.0026, + "n": 19 } }, - "spread": 0.0275 + "spread": 0.0027 }, - "playwright": { + "tool_write": { "values": { - "available": { - "mean": 0.4518, - "effect": -0.0116, - "n": 163 - }, - "instructed": { - "mean": 0.4778, - "effect": 0.0144, - "n": 9 - }, "off": { - "mean": 0.4696, - "effect": 0.0062, - "n": 285 + "mean": 0.3955, + "effect": -0.0009, + "n": 33 + }, + "on": { + "mean": 0.3964, + "effect": 0.0001, + "n": 477 } }, - "spread": 0.026 + "spread": 0.0009 }, - "tool_read": { + "web_search": { "values": { "off": { - "mean": 0.4396, - "effect": -0.0238, - "n": 28 + "mean": 0.3956, + "effect": -0.0008, + "n": 36 }, "on": { - "mean": 0.465, - "effect": 0.0016, - "n": 429 + "mean": 0.3964, + "effect": 0.0001, + "n": 474 } }, - "spread": 0.0254 + "spread": 0.0008 }, - "prompt_style": { + "context_file": { "values": { - "detailed": { - "mean": 0.4446, - "effect": -0.0188, - "n": 28 + "none": { + "mean": 0.3964, + "effect": 0.0, + "n": 479 }, - "simple": { - "mean": 0.4646, - "effect": 0.0012, - "n": 429 + "provided": { + "mean": 0.3958, + "effect": -0.0005, + "n": 31 + } + }, + "spread": 0.0006 + }, + "max_budget": { + "values": { + "high": { + "mean": 0.3958, + "effect": -0.0005, + "n": 24 + }, + "low": { + "mean": 0.3964, + "effect": 0.0, + "n": 486 } }, - "spread": 0.02 + "spread": 0.0006 } } \ No newline at end of file diff --git a/results/analysis/main_effects_cost.json b/results/analysis/main_effects_cost.json @@ -3,52 +3,52 @@ "values": { "gemma-4-26b": { "mean": 1.7918, - "effect": 1.0701, + "effect": 1.1071, "n": 43 }, "glm-4.5-air": { "mean": 0.6678, - "effect": -0.0538, + "effect": -0.0169, "n": 41 }, "glm-4.7": { - "mean": 0.4845, - "effect": -0.2371, - "n": 28 + "mean": 0.407, + "effect": -0.2776, + "n": 81 }, "glm-5.1": { "mean": 0.3566, - "effect": -0.365, + "effect": -0.3281, "n": 123 }, "haiku-4.5": { "mean": 0.2769, - "effect": -0.4448, + "effect": -0.4078, "n": 89 }, "kimi-k2.5": { "mean": 1.1331, - "effect": 0.4114, + "effect": 0.4484, "n": 3 }, "minimax-m2.7": { "mean": 1.8167, - "effect": 1.0951, + "effect": 1.132, "n": 3 }, "opus-4.6": { "mean": 0.6445, - "effect": -0.0771, + "effect": -0.0402, "n": 52 }, "qwen-3.6-plus": { "mean": 1.3787, - "effect": 0.657, + "effect": 0.694, "n": 22 }, "sonnet-4.6": { "mean": 1.3319, - "effect": 0.6103, + "effect": 0.6472, "n": 53 } }, @@ -58,420 +58,420 @@ "values": { "anthropic": { "mean": 0.6636, - "effect": -0.058, + "effect": -0.021, "n": 194 }, "openrouter": { "mean": 1.637, - "effect": 0.9154, + "effect": 0.9523, "n": 71 }, "zai": { - "mean": 0.4417, - "effect": -0.2799, - "n": 192 + "mean": 0.4254, + "effect": -0.2593, + "n": 245 } }, - "spread": 1.1953 + "spread": 1.2116 }, "strategy": { "values": { "creative_validate": { "mean": 1.2884, - "effect": 0.5668, + "effect": 0.6037, "n": 8 }, "delegate": { - "mean": 0.8818, - "effect": 0.1602, - "n": 5 + "mean": 0.8727, + "effect": 0.188, + "n": 7 }, "iterate": { - "mean": 1.1955, - "effect": 0.4738, - "n": 9 + "mean": 1.1211, + "effect": 0.4364, + "n": 11 }, "none": { - "mean": 0.6547, - "effect": -0.0669, - "n": 257 + "mean": 0.6073, + "effect": -0.0774, + "n": 300 }, "plan_first": { - "mean": 1.1808, - "effect": 0.4591, - "n": 7 + "mean": 0.9415, + "effect": 0.2568, + "n": 10 }, "review": { "mean": 1.0455, - "effect": 0.3238, + "effect": 0.3608, "n": 5 }, "split_work": { "mean": 1.032, - "effect": 0.3103, + "effect": 0.3473, "n": 5 }, "use_subagents": { - "mean": 0.7292, - "effect": 0.0076, - "n": 161 + "mean": 0.7223, + "effect": 0.0376, + "n": 164 } }, - "spread": 0.6337 + "spread": 0.6811 }, "playwright": { "values": { "available": { - "mean": 0.7172, - "effect": -0.0044, - "n": 163 + "mean": 0.7125, + "effect": 0.0278, + "n": 165 }, "instructed": { - "mean": 1.3155, - "effect": 0.5939, - "n": 9 + "mean": 1.1926, + "effect": 0.5079, + "n": 11 }, "off": { - "mean": 0.7054, - "effect": -0.0162, - "n": 285 + "mean": 0.6542, + "effect": -0.0305, + "n": 334 } }, - "spread": 0.6101 + "spread": 0.5384 }, "context_noise": { "values": { "clean": { - "mean": 0.7432, - "effect": 0.0216, - "n": 433 + "mean": 0.7076, + "effect": 0.023, + "n": 477 }, "lorem_100k": { - "mean": 0.4313, - "effect": -0.2903, - "n": 3 + "mean": 0.5024, + "effect": -0.1823, + "n": 6 }, "lorem_10k": { - "mean": 0.2553, - "effect": -0.4663, - "n": 3 + "mean": 0.265, + "effect": -0.4197, + "n": 6 }, "lorem_1k": { "mean": 0.3576, - "effect": -0.364, + "effect": -0.3271, "n": 3 }, "lorem_50k": { - "mean": 0.4246, - "effect": -0.297, - "n": 3 + "mean": 0.3994, + "effect": -0.2852, + "n": 6 }, "wikipedia_100k": { "mean": 0.3776, - "effect": -0.3441, + "effect": -0.3071, "n": 3 }, "wikipedia_10k": { "mean": 0.2867, - "effect": -0.435, + "effect": -0.398, "n": 3 }, "wikipedia_1k": { "mean": 0.1992, - "effect": -0.5224, + "effect": -0.4855, "n": 3 }, "wikipedia_50k": { "mean": 0.3265, - "effect": -0.3951, + "effect": -0.3581, "n": 3 } }, - "spread": 0.544 + "spread": 0.5084 }, "renderer": { "values": { "canvas": { - "mean": 0.4246, - "effect": -0.2971, - "n": 4 + "mean": 0.4155, + "effect": -0.2692, + "n": 7 }, "dom": { - "mean": 0.4262, - "effect": -0.2954, - "n": 4 + "mean": 0.3856, + "effect": -0.2991, + "n": 5 }, "none": { - "mean": 0.7323, - "effect": 0.0107, - "n": 441 + "mean": 0.6981, + "effect": 0.0134, + "n": 487 }, "svg": { - "mean": 0.3167, - "effect": -0.4049, - "n": 4 + "mean": 0.3176, + "effect": -0.367, + "n": 7 }, "webgl": { "mean": 0.5393, - "effect": -0.1824, + "effect": -0.1454, "n": 4 } }, - "spread": 0.4156 + "spread": 0.3805 }, "max_budget": { "values": { "high": { - "mean": 0.4527, - "effect": -0.269, - "n": 23 + "mean": 0.4427, + "effect": -0.242, + "n": 24 }, "low": { - "mean": 0.7359, - "effect": 0.0143, - "n": 434 + "mean": 0.6966, + "effect": 0.012, + "n": 486 } }, - "spread": 0.2832 + "spread": 0.2539 }, - "human_language": { + "architecture": { "values": { - "en": { - "mean": 0.7389, - "effect": 0.0172, - "n": 429 + "best_practices": { + "mean": 0.7915, + "effect": 0.1068, + "n": 4 }, - "es": { - "mean": 0.4575, - "effect": -0.2641, - "n": 28 - } - }, - "spread": 0.2814 - }, - "linter": { - "values": { - "off": { - "mean": 0.4747, - "effect": -0.2469, - "n": 38 + "none": { + "mean": 0.6853, + "effect": 0.0006, + "n": 501 }, - "on": { - "mean": 0.744, - "effect": 0.0224, - "n": 419 + "separation": { + "mean": 0.5392, + "effect": -0.1455, + "n": 5 } }, - "spread": 0.2693 + "spread": 0.2523 }, - "context_file": { + "human_language": { "values": { - "none": { - "mean": 0.7383, - "effect": 0.0166, - "n": 428 + "en": { + "mean": 0.6986, + "effect": 0.0139, + "n": 481 }, - "provided": { - "mean": 0.4759, - "effect": -0.2457, + "es": { + "mean": 0.4541, + "effect": -0.2306, "n": 29 } }, - "spread": 0.2624 + "spread": 0.2445 }, - "architecture": { + "context_file": { "values": { - "best_practices": { - "mean": 0.7915, - "effect": 0.0699, - "n": 4 - }, "none": { - "mean": 0.723, - "effect": 0.0014, - "n": 448 + "mean": 0.699, + "effect": 0.0144, + "n": 479 }, - "separation": { - "mean": 0.5392, - "effect": -0.1824, - "n": 5 + "provided": { + "mean": 0.4627, + "effect": -0.222, + "n": 31 } }, - "spread": 0.2523 + "spread": 0.2363 }, - "language": { + "linter": { "values": { - "javascript": { - "mean": 0.6394, - "effect": -0.0822, - "n": 20 - }, - "typescript": { - "mean": 0.7333, - "effect": 0.0117, - "n": 417 + "off": { + "mean": 0.4721, + "effect": -0.2126, + "n": 39 }, - "unspecified": { - "mean": 0.5603, - "effect": -0.1614, - "n": 20 + "on": { + "mean": 0.7023, + "effect": 0.0176, + "n": 471 } }, - "spread": 0.173 + "spread": 0.2302 }, "design_guidance": { "values": { "none": { - "mean": 0.7205, - "effect": -0.0011, - "n": 447 + "mean": 0.6829, + "effect": -0.0017, + "n": 500 }, "specific": { "mean": 0.689, - "effect": -0.0327, + "effect": 0.0043, "n": 5 }, "vague": { "mean": 0.8542, - "effect": 0.1326, + "effect": 0.1695, "n": 5 } }, - "spread": 0.1652 + "spread": 0.1713 }, "prompt_style": { "values": { "detailed": { - "mean": 0.5698, - "effect": -0.1518, - "n": 28 + "mean": 0.5406, + "effect": -0.144, + "n": 30 }, "simple": { - "mean": 0.7315, - "effect": 0.0099, - "n": 429 + "mean": 0.6937, + "effect": 0.009, + "n": 480 } }, - "spread": 0.1617 + "spread": 0.1531 }, - "tool_edit": { + "web_search": { "values": { "off": { - "mean": 0.5736, - "effect": -0.148, - "n": 33 + "mean": 0.5497, + "effect": -0.135, + "n": 36 }, "on": { - "mean": 0.7331, - "effect": 0.0115, - "n": 424 + "mean": 0.6949, + "effect": 0.0103, + "n": 474 } }, - "spread": 0.1595 + "spread": 0.1452 }, - "web_search": { + "tool_edit": { "values": { "off": { - "mean": 0.5757, - "effect": -0.146, - "n": 33 + "mean": 0.5573, + "effect": -0.1274, + "n": 35 }, "on": { - "mean": 0.733, - "effect": 0.0114, - "n": 424 + "mean": 0.6941, + "effect": 0.0094, + "n": 475 } }, - "spread": 0.1573 + "spread": 0.1368 }, - "tool_grep": { + "language": { "values": { - "off": { - "mean": 0.5789, - "effect": -0.1427, - "n": 30 + "javascript": { + "mean": 0.617, + "effect": -0.0677, + "n": 21 }, - "on": { - "mean": 0.7317, - "effect": 0.01, - "n": 427 + "typescript": { + "mean": 0.693, + "effect": 0.0083, + "n": 469 + }, + "unspecified": { + "mean": 0.5603, + "effect": -0.1244, + "n": 20 } }, - "spread": 0.1528 + "spread": 0.1327 }, - "tool_write": { + "tool_grep": { "values": { "off": { - "mean": 0.5941, - "effect": -0.1275, + "mean": 0.5673, + "effect": -0.1173, "n": 31 }, "on": { - "mean": 0.7309, - "effect": 0.0093, - "n": 426 + "mean": 0.6923, + "effect": 0.0076, + "n": 479 } }, - "spread": 0.1368 + "spread": 0.125 }, - "effort": { + "tool_write": { "values": { - "high": { - "mean": 0.717, - "effect": -0.0047, - "n": 441 + "off": { + "mean": 0.5712, + "effect": -0.1134, + "n": 33 }, - "max": { - "mean": 0.85, - "effect": 0.1284, - "n": 16 + "on": { + "mean": 0.6925, + "effect": 0.0078, + "n": 477 } }, - "spread": 0.133 + "spread": 0.1213 }, "tool_glob": { "values": { "off": { - "mean": 0.6171, - "effect": -0.1045, - "n": 27 + "mean": 0.5848, + "effect": -0.0998, + "n": 30 }, "on": { - "mean": 0.7282, - "effect": 0.0066, - "n": 430 + "mean": 0.6909, + "effect": 0.0062, + "n": 480 } }, - "spread": 0.1111 + "spread": 0.1061 }, "tool_read": { "values": { "off": { - "mean": 0.6241, - "effect": -0.0976, - "n": 28 + "mean": 0.5882, + "effect": -0.0964, + "n": 31 }, "on": { - "mean": 0.728, - "effect": 0.0064, - "n": 429 + "mean": 0.6909, + "effect": 0.0062, + "n": 479 } }, - "spread": 0.1039 + "spread": 0.1027 }, "error_checking": { "values": { "none": { - "mean": 0.7213, - "effect": -0.0003, - "n": 453 + "mean": 0.6841, + "effect": -0.0006, + "n": 506 }, "self_verify": { "mean": 0.7612, - "effect": 0.0396, + "effect": 0.0765, "n": 4 } }, - "spread": 0.0399 + "spread": 0.0771 + }, + "effort": { + "values": { + "high": { + "mean": 0.6818, + "effect": -0.0029, + "n": 491 + }, + "max": { + "mean": 0.7587, + "effect": 0.0741, + "n": 19 + } + }, + "spread": 0.0769 } } \ No newline at end of file diff --git a/results/analysis/main_effects_gameplay.json b/results/analysis/main_effects_gameplay.json @@ -3,475 +3,475 @@ "values": { "gemma-4-26b": { "mean": 0.0926, - "effect": -0.182, + "effect": -0.5699, "n": 43 }, "glm-4.5-air": { - "mean": 0.4634, - "effect": 0.1889, + "mean": 0.5924, + "effect": -0.0701, "n": 41 }, "glm-4.7": { - "mean": 0.4018, - "effect": 0.1273, - "n": 28 + "mean": 0.7019, + "effect": 0.0394, + "n": 81 }, "glm-5.1": { - "mean": 0.2178, - "effect": -0.0567, + "mean": 0.6854, + "effect": 0.023, "n": 123 }, "haiku-4.5": { - "mean": 0.2871, - "effect": 0.0125, + "mean": 0.7642, + "effect": 0.1017, "n": 89 }, "kimi-k2.5": { "mean": 0.67, - "effect": 0.3955, + "effect": 0.0075, "n": 3 }, "minimax-m2.7": { - "mean": 0.4433, - "effect": 0.1688, + "mean": 0.4667, + "effect": -0.1958, "n": 3 }, "opus-4.6": { - "mean": 0.2194, - "effect": -0.0551, + "mean": 0.8331, + "effect": 0.1706, "n": 52 }, "qwen-3.6-plus": { - "mean": 0.2223, - "effect": -0.0523, + "mean": 0.5236, + "effect": -0.1389, "n": 22 }, "sonnet-4.6": { - "mean": 0.3632, - "effect": 0.0887, + "mean": 0.7958, + "effect": 0.1334, "n": 53 } }, - "spread": 0.5774 - }, - "context_noise": { - "values": { - "clean": { - "mean": 0.2791, - "effect": 0.0046, - "n": 433 - }, - "lorem_100k": { - "mean": 0.0, - "effect": -0.2745, - "n": 3 - }, - "lorem_10k": { - "mean": 0.2233, - "effect": -0.0512, - "n": 3 - }, - "lorem_1k": { - "mean": 0.2233, - "effect": -0.0512, - "n": 3 - }, - "lorem_50k": { - "mean": 0.2233, - "effect": -0.0512, - "n": 3 - }, - "wikipedia_100k": { - "mean": 0.3567, - "effect": 0.0821, - "n": 3 - }, - "wikipedia_10k": { - "mean": 0.28, - "effect": 0.0055, - "n": 3 - }, - "wikipedia_1k": { - "mean": 0.2233, - "effect": -0.0512, - "n": 3 - }, - "wikipedia_50k": { - "mean": 0.0, - "effect": -0.2745, - "n": 3 - } - }, - "spread": 0.3567 + "spread": 0.7405 }, "strategy": { "values": { "creative_validate": { "mean": 0.46, - "effect": 0.1855, + "effect": -0.2025, "n": 8 }, "delegate": { - "mean": 0.268, - "effect": -0.0065, - "n": 5 + "mean": 0.6071, + "effect": -0.0553, + "n": 7 }, "iterate": { - "mean": 0.36, - "effect": 0.0855, - "n": 9 + "mean": 0.59, + "effect": -0.0725, + "n": 11 }, "none": { - "mean": 0.2693, - "effect": -0.0052, - "n": 257 + "mean": 0.625, + "effect": -0.0375, + "n": 300 }, "plan_first": { - "mean": 0.3829, - "effect": 0.1083, - "n": 7 + "mean": 0.563, + "effect": -0.0995, + "n": 10 }, "review": { - "mean": 0.268, - "effect": -0.0065, + "mean": 0.536, + "effect": -0.1265, "n": 5 }, "split_work": { - "mean": 0.134, - "effect": -0.1405, + "mean": 0.2, + "effect": -0.4625, "n": 5 }, "use_subagents": { - "mean": 0.2689, - "effect": -0.0056, - "n": 161 + "mean": 0.7723, + "effect": 0.1098, + "n": 164 } }, - "spread": 0.326 + "spread": 0.5723 }, - "design_guidance": { - "values": { - "none": { - "mean": 0.277, - "effect": 0.0024, - "n": 447 - }, - "specific": { - "mean": 0.266, - "effect": -0.0085, - "n": 5 - }, - "vague": { - "mean": 0.066, - "effect": -0.2085, - "n": 5 - } - }, - "spread": 0.211 - }, - "architecture": { + "provider": { "values": { - "best_practices": { - "mean": 0.0825, - "effect": -0.192, - "n": 4 + "anthropic": { + "mean": 0.7913, + "effect": 0.1288, + "n": 194 }, - "none": { - "mean": 0.2764, - "effect": 0.0019, - "n": 448 + "openrouter": { + "mean": 0.2663, + "effect": -0.3962, + "n": 71 }, - "separation": { - "mean": 0.258, - "effect": -0.0165, - "n": 5 + "zai": { + "mean": 0.6753, + "effect": 0.0128, + "n": 245 } }, - "spread": 0.1939 + "spread": 0.525 }, - "language": { + "playwright": { "values": { - "javascript": { - "mean": 0.168, - "effect": -0.1065, - "n": 20 + "available": { + "mean": 0.7867, + "effect": 0.1242, + "n": 165 }, - "typescript": { - "mean": 0.2759, - "effect": 0.0014, - "n": 417 + "instructed": { + "mean": 0.4691, + "effect": -0.1934, + "n": 11 }, - "unspecified": { - "mean": 0.352, - "effect": 0.0775, - "n": 20 + "off": { + "mean": 0.6075, + "effect": -0.055, + "n": 334 } }, - "spread": 0.184 + "spread": 0.3176 }, "renderer": { "values": { "canvas": { - "mean": 0.1675, - "effect": -0.107, - "n": 4 + "mean": 0.6729, + "effect": 0.0104, + "n": 7 }, "dom": { - "mean": 0.335, - "effect": 0.0605, - "n": 4 + "mean": 0.838, + "effect": 0.1755, + "n": 5 }, "none": { - "mean": 0.2746, - "effect": 0.0001, - "n": 441 + "mean": 0.6631, + "effect": 0.0007, + "n": 487 }, "svg": { - "mean": 0.335, - "effect": 0.0605, - "n": 4 + "mean": 0.5257, + "effect": -0.1368, + "n": 7 }, "webgl": { - "mean": 0.25, - "effect": -0.0245, + "mean": 0.585, + "effect": -0.0775, "n": 4 } }, - "spread": 0.1675 + "spread": 0.3123 }, - "provider": { + "architecture": { "values": { - "anthropic": { - "mean": 0.2897, - "effect": 0.0152, - "n": 194 + "best_practices": { + "mean": 0.665, + "effect": 0.0025, + "n": 4 }, - "openrouter": { - "mean": 0.172, - "effect": -0.1026, - "n": 71 + "none": { + "mean": 0.6652, + "effect": 0.0028, + "n": 501 }, - "zai": { - "mean": 0.2971, - "effect": 0.0226, - "n": 192 + "separation": { + "mean": 0.384, + "effect": -0.2785, + "n": 5 } }, - "spread": 0.1251 + "spread": 0.2812 }, - "tool_glob": { + "design_guidance": { "values": { - "off": { - "mean": 0.1637, - "effect": -0.1108, - "n": 27 + "none": { + "mean": 0.6647, + "effect": 0.0022, + "n": 500 }, - "on": { - "mean": 0.2815, - "effect": 0.007, - "n": 430 + "specific": { + "mean": 0.46, + "effect": -0.2025, + "n": 5 + }, + "vague": { + "mean": 0.646, + "effect": -0.0165, + "n": 5 } }, - "spread": 0.1178 + "spread": 0.2047 }, - "error_checking": { + "prompt_style": { "values": { - "none": { - "mean": 0.2755, - "effect": 0.0009, - "n": 453 + "detailed": { + "mean": 0.8383, + "effect": 0.1758, + "n": 30 }, - "self_verify": { - "mean": 0.1675, - "effect": -0.107, - "n": 4 + "simple": { + "mean": 0.6515, + "effect": -0.011, + "n": 480 } }, - "spread": 0.108 + "spread": 0.1868 + }, + "context_noise": { + "values": { + "clean": { + "mean": 0.6618, + "effect": -0.0007, + "n": 477 + }, + "lorem_100k": { + "mean": 0.605, + "effect": -0.0575, + "n": 6 + }, + "lorem_10k": { + "mean": 0.725, + "effect": 0.0625, + "n": 6 + }, + "lorem_1k": { + "mean": 0.67, + "effect": 0.0075, + "n": 3 + }, + "lorem_50k": { + "mean": 0.6133, + "effect": -0.0492, + "n": 6 + }, + "wikipedia_100k": { + "mean": 0.5833, + "effect": -0.0792, + "n": 3 + }, + "wikipedia_10k": { + "mean": 0.7633, + "effect": 0.1008, + "n": 3 + }, + "wikipedia_1k": { + "mean": 0.7333, + "effect": 0.0708, + "n": 3 + }, + "wikipedia_50k": { + "mean": 0.7633, + "effect": 0.1008, + "n": 3 + } + }, + "spread": 0.18 }, "human_language": { "values": { "en": { - "mean": 0.268, - "effect": -0.0066, - "n": 429 + "mean": 0.6555, + "effect": -0.007, + "n": 481 }, "es": { - "mean": 0.375, - "effect": 0.1005, - "n": 28 + "mean": 0.7783, + "effect": 0.1158, + "n": 29 } }, - "spread": 0.107 + "spread": 0.1228 }, - "tool_edit": { + "max_budget": { + "values": { + "high": { + "mean": 0.7746, + "effect": 0.1121, + "n": 24 + }, + "low": { + "mean": 0.657, + "effect": -0.0055, + "n": 486 + } + }, + "spread": 0.1176 + }, + "web_search": { "values": { "off": { - "mean": 0.183, - "effect": -0.0915, - "n": 33 + "mean": 0.7697, + "effect": 0.1072, + "n": 36 }, "on": { - "mean": 0.2817, - "effect": 0.0071, - "n": 424 + "mean": 0.6543, + "effect": -0.0081, + "n": 474 } }, - "spread": 0.0987 + "spread": 0.1154 }, - "playwright": { + "language": { "values": { - "available": { - "mean": 0.2712, - "effect": -0.0033, - "n": 163 + "javascript": { + "mean": 0.7552, + "effect": 0.0927, + "n": 21 }, - "instructed": { - "mean": 0.1856, - "effect": -0.089, - "n": 9 + "typescript": { + "mean": 0.6577, + "effect": -0.0048, + "n": 469 }, - "off": { - "mean": 0.2792, - "effect": 0.0047, - "n": 285 + "unspecified": { + "mean": 0.6775, + "effect": 0.015, + "n": 20 } }, - "spread": 0.0936 + "spread": 0.0975 }, - "tool_write": { + "context_file": { "values": { - "off": { - "mean": 0.19, - "effect": -0.0845, - "n": 31 + "none": { + "mean": 0.6577, + "effect": -0.0048, + "n": 479 }, - "on": { - "mean": 0.2807, - "effect": 0.0062, - "n": 426 + "provided": { + "mean": 0.7365, + "effect": 0.074, + "n": 31 } }, - "spread": 0.0907 + "spread": 0.0788 }, - "effort": { + "tool_edit": { "values": { - "high": { - "mean": 0.2777, - "effect": 0.0031, - "n": 441 + "off": { + "mean": 0.722, + "effect": 0.0595, + "n": 35 }, - "max": { - "mean": 0.1881, - "effect": -0.0864, - "n": 16 + "on": { + "mean": 0.6581, + "effect": -0.0044, + "n": 475 } }, - "spread": 0.0896 + "spread": 0.0639 }, - "tool_grep": { + "tool_read": { "values": { "off": { - "mean": 0.339, - "effect": 0.0645, - "n": 30 + "mean": 0.7087, + "effect": 0.0462, + "n": 31 }, "on": { - "mean": 0.27, - "effect": -0.0045, - "n": 427 + "mean": 0.6595, + "effect": -0.003, + "n": 479 } }, - "spread": 0.069 + "spread": 0.0492 }, - "prompt_style": { + "tool_grep": { "values": { - "detailed": { - "mean": 0.2193, - "effect": -0.0552, - "n": 28 + "off": { + "mean": 0.6971, + "effect": 0.0346, + "n": 31 }, - "simple": { - "mean": 0.2781, - "effect": 0.0036, - "n": 429 + "on": { + "mean": 0.6603, + "effect": -0.0022, + "n": 479 } }, - "spread": 0.0588 + "spread": 0.0368 }, - "web_search": { + "tool_glob": { "values": { "off": { - "mean": 0.3164, - "effect": 0.0418, - "n": 33 + "mean": 0.692, + "effect": 0.0295, + "n": 30 }, "on": { - "mean": 0.2713, - "effect": -0.0033, - "n": 424 + "mean": 0.6606, + "effect": -0.0018, + "n": 480 } }, - "spread": 0.0451 + "spread": 0.0314 }, - "tool_read": { + "tool_write": { "values": { "off": { - "mean": 0.3071, - "effect": 0.0326, - "n": 28 + "mean": 0.6858, + "effect": 0.0233, + "n": 33 }, "on": { - "mean": 0.2724, - "effect": -0.0021, - "n": 429 + "mean": 0.6609, + "effect": -0.0016, + "n": 477 } }, - "spread": 0.0347 + "spread": 0.0249 }, "linter": { "values": { "off": { - "mean": 0.3026, - "effect": 0.0281, - "n": 38 + "mean": 0.6828, + "effect": 0.0203, + "n": 39 }, "on": { - "mean": 0.272, - "effect": -0.0025, - "n": 419 + "mean": 0.6608, + "effect": -0.0017, + "n": 471 } }, - "spread": 0.0306 + "spread": 0.022 }, - "max_budget": { + "error_checking": { "values": { - "high": { - "mean": 0.2474, - "effect": -0.0271, - "n": 23 + "none": { + "mean": 0.6624, + "effect": -0.0001, + "n": 506 }, - "low": { - "mean": 0.276, - "effect": 0.0014, - "n": 434 + "self_verify": { + "mean": 0.67, + "effect": 0.0075, + "n": 4 } }, - "spread": 0.0286 + "spread": 0.0076 }, - "context_file": { + "effort": { "values": { - "none": { - "mean": 0.2754, - "effect": 0.0008, - "n": 428 + "high": { + "mean": 0.6624, + "effect": -0.0001, + "n": 491 }, - "provided": { - "mean": 0.2624, - "effect": -0.0121, - "n": 29 + "max": { + "mean": 0.6653, + "effect": 0.0028, + "n": 19 } }, - "spread": 0.013 + "spread": 0.0029 } } \ No newline at end of file diff --git a/results/analysis/main_effects_score.json b/results/analysis/main_effects_score.json @@ -2,476 +2,476 @@ "model": { "values": { "gemma-4-26b": { - "mean": 0.0463, - "effect": -0.091, + "mean": 0.4963, + "effect": -0.2352, "n": 43 }, "glm-4.5-air": { - "mean": 0.2317, - "effect": 0.0944, + "mean": 0.67, + "effect": -0.0615, "n": 41 }, "glm-4.7": { - "mean": 0.2009, - "effect": 0.0636, - "n": 28 + "mean": 0.7107, + "effect": -0.0207, + "n": 81 }, "glm-5.1": { - "mean": 0.1089, - "effect": -0.0284, + "mean": 0.754, + "effect": 0.0225, "n": 123 }, "haiku-4.5": { - "mean": 0.1435, - "effect": 0.0063, + "mean": 0.7558, + "effect": 0.0243, "n": 89 }, "kimi-k2.5": { - "mean": 0.335, - "effect": 0.1977, + "mean": 0.5667, + "effect": -0.1648, "n": 3 }, "minimax-m2.7": { - "mean": 0.2217, - "effect": 0.0844, + "mean": 0.725, + "effect": -0.0065, "n": 3 }, "opus-4.6": { - "mean": 0.1097, - "effect": -0.0276, + "mean": 0.8256, + "effect": 0.0941, "n": 52 }, "qwen-3.6-plus": { - "mean": 0.1111, - "effect": -0.0261, + "mean": 0.7148, + "effect": -0.0167, "n": 22 }, "sonnet-4.6": { - "mean": 0.1816, - "effect": 0.0443, + "mean": 0.8327, + "effect": 0.1013, "n": 53 } }, - "spread": 0.2887 - }, - "context_noise": { - "values": { - "clean": { - "mean": 0.1396, - "effect": 0.0023, - "n": 433 - }, - "lorem_100k": { - "mean": 0.0, - "effect": -0.1373, - "n": 3 - }, - "lorem_10k": { - "mean": 0.1117, - "effect": -0.0256, - "n": 3 - }, - "lorem_1k": { - "mean": 0.1117, - "effect": -0.0256, - "n": 3 - }, - "lorem_50k": { - "mean": 0.1117, - "effect": -0.0256, - "n": 3 - }, - "wikipedia_100k": { - "mean": 0.1783, - "effect": 0.0411, - "n": 3 - }, - "wikipedia_10k": { - "mean": 0.14, - "effect": 0.0027, - "n": 3 - }, - "wikipedia_1k": { - "mean": 0.1117, - "effect": -0.0256, - "n": 3 - }, - "wikipedia_50k": { - "mean": 0.0, - "effect": -0.1373, - "n": 3 - } - }, - "spread": 0.1783 + "spread": 0.3364 }, "strategy": { "values": { "creative_validate": { - "mean": 0.23, - "effect": 0.0927, + "mean": 0.5981, + "effect": -0.1333, "n": 8 }, "delegate": { - "mean": 0.134, - "effect": -0.0033, - "n": 5 + "mean": 0.7086, + "effect": -0.0229, + "n": 7 }, "iterate": { - "mean": 0.18, - "effect": 0.0427, - "n": 9 + "mean": 0.7318, + "effect": 0.0003, + "n": 11 }, "none": { - "mean": 0.1346, - "effect": -0.0026, - "n": 257 + "mean": 0.7085, + "effect": -0.023, + "n": 300 }, "plan_first": { - "mean": 0.1914, - "effect": 0.0542, - "n": 7 + "mean": 0.7115, + "effect": -0.02, + "n": 10 }, "review": { - "mean": 0.134, - "effect": -0.0033, + "mean": 0.705, + "effect": -0.0265, "n": 5 }, "split_work": { - "mean": 0.067, - "effect": -0.0703, + "mean": 0.536, + "effect": -0.1955, "n": 5 }, "use_subagents": { - "mean": 0.1345, - "effect": -0.0028, - "n": 161 + "mean": 0.7889, + "effect": 0.0574, + "n": 164 } }, - "spread": 0.163 + "spread": 0.2529 }, - "design_guidance": { + "provider": { "values": { - "none": { - "mean": 0.1385, - "effect": 0.0012, - "n": 447 + "anthropic": { + "mean": 0.7955, + "effect": 0.064, + "n": 194 }, - "specific": { - "mean": 0.133, - "effect": -0.0043, - "n": 5 + "openrouter": { + "mean": 0.5766, + "effect": -0.1549, + "n": 71 }, - "vague": { - "mean": 0.033, - "effect": -0.1043, - "n": 5 + "zai": { + "mean": 0.7256, + "effect": -0.0058, + "n": 245 } }, - "spread": 0.1055 + "spread": 0.2189 + }, + "playwright": { + "values": { + "available": { + "mean": 0.7907, + "effect": 0.0592, + "n": 165 + }, + "instructed": { + "mean": 0.5918, + "effect": -0.1397, + "n": 11 + }, + "off": { + "mean": 0.7068, + "effect": -0.0246, + "n": 334 + } + }, + "spread": 0.1989 + }, + "context_noise": { + "values": { + "clean": { + "mean": 0.731, + "effect": -0.0004, + "n": 477 + }, + "lorem_100k": { + "mean": 0.6842, + "effect": -0.0473, + "n": 6 + }, + "lorem_10k": { + "mean": 0.7492, + "effect": 0.0177, + "n": 6 + }, + "lorem_1k": { + "mean": 0.7783, + "effect": 0.0469, + "n": 3 + }, + "lorem_50k": { + "mean": 0.6742, + "effect": -0.0573, + "n": 6 + }, + "wikipedia_100k": { + "mean": 0.69, + "effect": -0.0415, + "n": 3 + }, + "wikipedia_10k": { + "mean": 0.7483, + "effect": 0.0169, + "n": 3 + }, + "wikipedia_1k": { + "mean": 0.85, + "effect": 0.1185, + "n": 3 + }, + "wikipedia_50k": { + "mean": 0.835, + "effect": 0.1035, + "n": 3 + } + }, + "spread": 0.1758 }, "architecture": { "values": { "best_practices": { - "mean": 0.0413, - "effect": -0.096, + "mean": 0.795, + "effect": 0.0635, "n": 4 }, "none": { - "mean": 0.1382, - "effect": 0.0009, - "n": 448 + "mean": 0.7319, + "effect": 0.0004, + "n": 501 }, "separation": { - "mean": 0.129, - "effect": -0.0083, + "mean": 0.638, + "effect": -0.0935, "n": 5 } }, - "spread": 0.0969 + "spread": 0.157 }, - "language": { + "design_guidance": { "values": { - "javascript": { - "mean": 0.084, - "effect": -0.0533, - "n": 20 + "none": { + "mean": 0.7323, + "effect": 0.0008, + "n": 500 }, - "typescript": { - "mean": 0.138, - "effect": 0.0007, - "n": 417 + "specific": { + "mean": 0.62, + "effect": -0.1115, + "n": 5 }, - "unspecified": { - "mean": 0.176, - "effect": 0.0387, - "n": 20 + "vague": { + "mean": 0.762, + "effect": 0.0305, + "n": 5 } }, - "spread": 0.092 + "spread": 0.142 }, "renderer": { "values": { "canvas": { - "mean": 0.0838, - "effect": -0.0535, - "n": 4 + "mean": 0.6971, + "effect": -0.0343, + "n": 7 }, "dom": { - "mean": 0.1675, - "effect": 0.0302, - "n": 4 + "mean": 0.749, + "effect": 0.0175, + "n": 5 }, "none": { - "mean": 0.1373, - "effect": 0.0, - "n": 441 + "mean": 0.7333, + "effect": 0.0018, + "n": 487 }, "svg": { - "mean": 0.1675, - "effect": 0.0302, - "n": 4 + "mean": 0.6364, + "effect": -0.095, + "n": 7 }, "webgl": { - "mean": 0.125, - "effect": -0.0123, + "mean": 0.7137, + "effect": -0.0177, "n": 4 } }, - "spread": 0.0837 + "spread": 0.1126 }, - "provider": { + "prompt_style": { "values": { - "anthropic": { - "mean": 0.1449, - "effect": 0.0076, - "n": 194 - }, - "openrouter": { - "mean": 0.086, - "effect": -0.0513, - "n": 71 + "detailed": { + "mean": 0.8182, + "effect": 0.0867, + "n": 30 }, - "zai": { - "mean": 0.1485, - "effect": 0.0113, - "n": 192 + "simple": { + "mean": 0.7261, + "effect": -0.0054, + "n": 480 } }, - "spread": 0.0625 + "spread": 0.0921 }, - "tool_glob": { + "language": { "values": { - "off": { - "mean": 0.0819, - "effect": -0.0554, - "n": 27 + "javascript": { + "mean": 0.8033, + "effect": 0.0719, + "n": 21 }, - "on": { - "mean": 0.1407, - "effect": 0.0035, - "n": 430 + "typescript": { + "mean": 0.7257, + "effect": -0.0058, + "n": 469 + }, + "unspecified": { + "mean": 0.7923, + "effect": 0.0608, + "n": 20 } }, - "spread": 0.0588 + "spread": 0.0776 }, - "error_checking": { + "human_language": { "values": { - "none": { - "mean": 0.1377, - "effect": 0.0005, - "n": 453 + "en": { + "mean": 0.7282, + "effect": -0.0032, + "n": 481 }, - "self_verify": { - "mean": 0.0838, - "effect": -0.0535, - "n": 4 + "es": { + "mean": 0.7853, + "effect": 0.0539, + "n": 29 } }, - "spread": 0.0539 + "spread": 0.0571 }, - "human_language": { + "context_file": { "values": { - "en": { - "mean": 0.134, - "effect": -0.0033, - "n": 429 + "none": { + "mean": 0.7284, + "effect": -0.0031, + "n": 479 }, - "es": { - "mean": 0.1875, - "effect": 0.0502, - "n": 28 + "provided": { + "mean": 0.7792, + "effect": 0.0477, + "n": 31 } }, - "spread": 0.0535 + "spread": 0.0508 }, - "tool_edit": { + "web_search": { "values": { "off": { - "mean": 0.0915, - "effect": -0.0457, - "n": 33 + "mean": 0.7747, + "effect": 0.0433, + "n": 36 }, "on": { - "mean": 0.1408, - "effect": 0.0036, - "n": 424 + "mean": 0.7282, + "effect": -0.0033, + "n": 474 } }, - "spread": 0.0493 + "spread": 0.0465 }, - "playwright": { + "tool_edit": { "values": { - "available": { - "mean": 0.1356, - "effect": -0.0017, - "n": 163 - }, - "instructed": { - "mean": 0.0928, - "effect": -0.0445, - "n": 9 - }, "off": { - "mean": 0.1396, - "effect": 0.0023, - "n": 285 + "mean": 0.7679, + "effect": 0.0364, + "n": 35 + }, + "on": { + "mean": 0.7288, + "effect": -0.0027, + "n": 475 } }, - "spread": 0.0468 + "spread": 0.0391 }, - "tool_write": { + "tool_grep": { "values": { "off": { - "mean": 0.095, - "effect": -0.0423, + "mean": 0.7668, + "effect": 0.0353, "n": 31 }, "on": { - "mean": 0.1403, - "effect": 0.0031, - "n": 426 + "mean": 0.7292, + "effect": -0.0023, + "n": 479 } }, - "spread": 0.0453 + "spread": 0.0376 }, - "effort": { + "max_budget": { "values": { "high": { - "mean": 0.1388, - "effect": 0.0016, - "n": 441 + "mean": 0.7583, + "effect": 0.0269, + "n": 24 }, - "max": { - "mean": 0.0941, - "effect": -0.0432, - "n": 16 + "low": { + "mean": 0.7301, + "effect": -0.0013, + "n": 486 } }, - "spread": 0.0447 + "spread": 0.0282 }, - "tool_grep": { + "tool_read": { "values": { "off": { - "mean": 0.1695, - "effect": 0.0322, - "n": 30 + "mean": 0.7573, + "effect": 0.0258, + "n": 31 }, "on": { - "mean": 0.135, - "effect": -0.0023, - "n": 427 + "mean": 0.7298, + "effect": -0.0017, + "n": 479 } }, - "spread": 0.0345 + "spread": 0.0275 }, - "prompt_style": { + "error_checking": { "values": { - "detailed": { - "mean": 0.1096, - "effect": -0.0276, - "n": 28 + "none": { + "mean": 0.7316, + "effect": 0.0002, + "n": 506 }, - "simple": { - "mean": 0.1391, - "effect": 0.0018, - "n": 429 + "self_verify": { + "mean": 0.71, + "effect": -0.0215, + "n": 4 } }, - "spread": 0.0295 + "spread": 0.0216 }, - "web_search": { + "effort": { "values": { - "off": { - "mean": 0.1582, - "effect": 0.0209, - "n": 33 + "high": { + "mean": 0.7323, + "effect": 0.0008, + "n": 491 }, - "on": { - "mean": 0.1356, - "effect": -0.0016, - "n": 424 + "max": { + "mean": 0.7111, + "effect": -0.0204, + "n": 19 } }, - "spread": 0.0226 + "spread": 0.0212 }, - "tool_read": { + "linter": { "values": { "off": { - "mean": 0.1536, - "effect": 0.0163, - "n": 28 + "mean": 0.7396, + "effect": 0.0081, + "n": 39 }, "on": { - "mean": 0.1362, - "effect": -0.0011, - "n": 429 + "mean": 0.7308, + "effect": -0.0007, + "n": 471 } }, - "spread": 0.0174 + "spread": 0.0088 }, - "linter": { + "tool_glob": { "values": { "off": { - "mean": 0.1513, - "effect": 0.0141, - "n": 38 + "mean": 0.7267, + "effect": -0.0048, + "n": 30 }, "on": { - "mean": 0.136, - "effect": -0.0013, - "n": 419 + "mean": 0.7318, + "effect": 0.0003, + "n": 480 } }, - "spread": 0.0153 + "spread": 0.0051 }, - "max_budget": { - "values": { - "high": { - "mean": 0.1237, - "effect": -0.0136, - "n": 23 - }, - "low": { - "mean": 0.138, - "effect": 0.0007, - "n": 434 - } - }, - "spread": 0.0143 - }, - "context_file": { + "tool_write": { "values": { - "none": { - "mean": 0.1377, - "effect": 0.0004, - "n": 428 + "off": { + "mean": 0.7341, + "effect": 0.0026, + "n": 33 }, - "provided": { - "mean": 0.1312, - "effect": -0.0061, - "n": 29 + "on": { + "mean": 0.7313, + "effect": -0.0002, + "n": 477 } }, - "spread": 0.0065 + "spread": 0.0028 } } \ No newline at end of file diff --git a/results/analysis/main_effects_sonarqube.json b/results/analysis/main_effects_sonarqube.json @@ -1,477 +1,477 @@ { - "architecture": { + "model": { "values": { - "best_practices": { - "mean": 0.0, - "effect": 0.0, - "n": 4 + "gemma-4-26b": { + "mean": 0.9, + "effect": 0.0995, + "n": 43 }, - "none": { - "mean": 0.0, - "effect": 0.0, - "n": 442 + "glm-4.5-air": { + "mean": 0.7476, + "effect": -0.0529, + "n": 41 }, - "separation": { - "mean": 0.0, - "effect": 0.0, - "n": 5 - } - }, - "spread": 0.0 - }, - "context_file": { - "values": { - "none": { - "mean": 0.0, - "effect": 0.0, - "n": 422 + "glm-4.7": { + "mean": 0.7196, + "effect": -0.0808, + "n": 81 }, - "provided": { - "mean": 0.0, - "effect": 0.0, - "n": 29 + "glm-5.1": { + "mean": 0.8225, + "effect": 0.0221, + "n": 123 + }, + "haiku-4.5": { + "mean": 0.7474, + "effect": -0.053, + "n": 89 + }, + "kimi-k2.5": { + "mean": 0.4633, + "effect": -0.3371, + "n": 3 + }, + "minimax-m2.7": { + "mean": 0.9833, + "effect": 0.1829, + "n": 3 + }, + "opus-4.6": { + "mean": 0.8181, + "effect": 0.0176, + "n": 52 + }, + "qwen-3.6-plus": { + "mean": 0.9059, + "effect": 0.1055, + "n": 22 + }, + "sonnet-4.6": { + "mean": 0.8696, + "effect": 0.0692, + "n": 53 } }, - "spread": 0.0 + "spread": 0.52 }, "context_noise": { "values": { "clean": { - "mean": 0.0, - "effect": 0.0, - "n": 427 + "mean": 0.8003, + "effect": -0.0002, + "n": 477 }, "lorem_100k": { - "mean": 0.0, - "effect": 0.0, - "n": 3 + "mean": 0.7633, + "effect": -0.0371, + "n": 6 }, "lorem_10k": { - "mean": 0.0, - "effect": 0.0, - "n": 3 + "mean": 0.7733, + "effect": -0.0271, + "n": 6 }, "lorem_1k": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.8867, + "effect": 0.0862, "n": 3 }, "lorem_50k": { - "mean": 0.0, - "effect": 0.0, - "n": 3 + "mean": 0.735, + "effect": -0.0655, + "n": 6 }, "wikipedia_100k": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.7967, + "effect": -0.0038, "n": 3 }, "wikipedia_10k": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.7333, + "effect": -0.0671, "n": 3 }, "wikipedia_1k": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.9667, + "effect": 0.1662, "n": 3 }, "wikipedia_50k": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.9067, + "effect": 0.1062, "n": 3 } }, - "spread": 0.0 + "spread": 0.2334 }, - "design_guidance": { + "renderer": { "values": { - "none": { - "mean": 0.0, - "effect": 0.0, - "n": 441 + "canvas": { + "mean": 0.7214, + "effect": -0.079, + "n": 7 }, - "specific": { - "mean": 0.0, - "effect": 0.0, + "dom": { + "mean": 0.66, + "effect": -0.1405, "n": 5 }, - "vague": { - "mean": 0.0, - "effect": 0.0, - "n": 5 - } - }, - "spread": 0.0 - }, - "effort": { - "values": { - "high": { - "mean": 0.0, - "effect": 0.0, - "n": 435 + "none": { + "mean": 0.8034, + "effect": 0.003, + "n": 487 }, - "max": { - "mean": 0.0, - "effect": 0.0, - "n": 16 + "svg": { + "mean": 0.7471, + "effect": -0.0533, + "n": 7 + }, + "webgl": { + "mean": 0.8425, + "effect": 0.042, + "n": 4 } }, - "spread": 0.0 + "spread": 0.1825 }, - "error_checking": { + "strategy": { "values": { + "creative_validate": { + "mean": 0.7363, + "effect": -0.0642, + "n": 8 + }, + "delegate": { + "mean": 0.81, + "effect": 0.0095, + "n": 7 + }, + "iterate": { + "mean": 0.8736, + "effect": 0.0732, + "n": 11 + }, "none": { - "mean": 0.0, - "effect": 0.0, - "n": 447 + "mean": 0.7921, + "effect": -0.0084, + "n": 300 }, - "self_verify": { - "mean": 0.0, - "effect": 0.0, - "n": 4 + "plan_first": { + "mean": 0.86, + "effect": 0.0595, + "n": 10 + }, + "review": { + "mean": 0.874, + "effect": 0.0735, + "n": 5 + }, + "split_work": { + "mean": 0.872, + "effect": 0.0715, + "n": 5 + }, + "use_subagents": { + "mean": 0.8055, + "effect": 0.0051, + "n": 164 } }, - "spread": 0.0 + "spread": 0.1377 }, - "human_language": { + "architecture": { "values": { - "en": { - "mean": 0.0, - "effect": 0.0, - "n": 423 + "best_practices": { + "mean": 0.925, + "effect": 0.1245, + "n": 4 }, - "es": { - "mean": 0.0, - "effect": 0.0, - "n": 28 + "none": { + "mean": 0.7985, + "effect": -0.0019, + "n": 501 + }, + "separation": { + "mean": 0.892, + "effect": 0.0915, + "n": 5 } }, - "spread": 0.0 + "spread": 0.1265 }, "language": { "values": { "javascript": { - "mean": 0.0, - "effect": 0.0, - "n": 20 + "mean": 0.8514, + "effect": 0.051, + "n": 21 }, "typescript": { - "mean": 0.0, - "effect": 0.0, - "n": 411 + "mean": 0.7936, + "effect": -0.0068, + "n": 469 }, "unspecified": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.907, + "effect": 0.1065, "n": 20 } }, - "spread": 0.0 + "spread": 0.1134 }, - "linter": { + "provider": { "values": { - "off": { - "mean": 0.0, - "effect": 0.0, - "n": 38 + "anthropic": { + "mean": 0.7997, + "effect": -0.0007, + "n": 194 }, - "on": { - "mean": 0.0, - "effect": 0.0, - "n": 413 - } - }, - "spread": 0.0 - }, - "max_budget": { - "values": { - "high": { - "mean": 0.0, - "effect": 0.0, - "n": 23 + "openrouter": { + "mean": 0.8869, + "effect": 0.0865, + "n": 71 }, - "low": { - "mean": 0.0, - "effect": 0.0, - "n": 428 + "zai": { + "mean": 0.776, + "effect": -0.0245, + "n": 245 } }, - "spread": 0.0 + "spread": 0.1109 }, - "model": { + "design_guidance": { "values": { - "gemma-4-26b": { - "mean": 0.0, - "effect": 0.0, - "n": 43 - }, - "glm-4.5-air": { - "mean": 0.0, - "effect": 0.0, - "n": 41 - }, - "glm-4.7": { - "mean": 0.0, - "effect": 0.0, - "n": 28 - }, - "glm-5.1": { - "mean": 0.0, - "effect": 0.0, - "n": 117 - }, - "haiku-4.5": { - "mean": 0.0, - "effect": 0.0, - "n": 89 - }, - "kimi-k2.5": { - "mean": 0.0, - "effect": 0.0, - "n": 3 - }, - "minimax-m2.7": { - "mean": 0.0, - "effect": 0.0, - "n": 3 - }, - "opus-4.6": { - "mean": 0.0, - "effect": 0.0, - "n": 52 + "none": { + "mean": 0.7999, + "effect": -0.0006, + "n": 500 }, - "qwen-3.6-plus": { - "mean": 0.0, - "effect": 0.0, - "n": 22 + "specific": { + "mean": 0.78, + "effect": -0.0205, + "n": 5 }, - "sonnet-4.6": { - "mean": 0.0, - "effect": 0.0, - "n": 53 + "vague": { + "mean": 0.878, + "effect": 0.0775, + "n": 5 } }, - "spread": 0.0 + "spread": 0.098 }, "playwright": { "values": { "available": { - "mean": 0.0, - "effect": 0.0, - "n": 163 + "mean": 0.7946, + "effect": -0.0058, + "n": 165 }, "instructed": { - "mean": 0.0, - "effect": 0.0, - "n": 9 + "mean": 0.7145, + "effect": -0.0859, + "n": 11 }, "off": { - "mean": 0.0, - "effect": 0.0, - "n": 279 + "mean": 0.8062, + "effect": 0.0057, + "n": 334 } }, - "spread": 0.0 + "spread": 0.0917 }, - "prompt_style": { + "max_budget": { "values": { - "detailed": { - "mean": 0.0, - "effect": 0.0, - "n": 28 + "high": { + "mean": 0.7421, + "effect": -0.0584, + "n": 24 }, - "simple": { - "mean": 0.0, - "effect": 0.0, - "n": 423 + "low": { + "mean": 0.8033, + "effect": 0.0029, + "n": 486 } }, - "spread": 0.0 + "spread": 0.0612 }, - "provider": { + "error_checking": { "values": { - "anthropic": { - "mean": 0.0, - "effect": 0.0, - "n": 194 - }, - "openrouter": { - "mean": 0.0, - "effect": 0.0, - "n": 71 + "none": { + "mean": 0.8008, + "effect": 0.0004, + "n": 506 }, - "zai": { - "mean": 0.0, - "effect": 0.0, - "n": 186 + "self_verify": { + "mean": 0.75, + "effect": -0.0505, + "n": 4 } }, - "spread": 0.0 + "spread": 0.0508 }, - "renderer": { + "effort": { "values": { - "canvas": { - "mean": 0.0, - "effect": 0.0, - "n": 1 - }, - "dom": { - "mean": 0.0, - "effect": 0.0, - "n": 4 - }, - "none": { - "mean": 0.0, - "effect": 0.0, - "n": 443 - }, - "svg": { - "mean": 0.0, - "effect": 0.0, - "n": 1 + "high": { + "mean": 0.8021, + "effect": 0.0017, + "n": 491 }, - "webgl": { - "mean": 0.0, - "effect": 0.0, - "n": 2 + "max": { + "mean": 0.7568, + "effect": -0.0436, + "n": 19 } }, - "spread": 0.0 + "spread": 0.0453 }, - "strategy": { + "tool_glob": { "values": { - "creative_validate": { - "mean": 0.0, - "effect": 0.0, - "n": 10 - }, - "delegate": { - "mean": 0.0, - "effect": 0.0, - "n": 5 + "off": { + "mean": 0.7613, + "effect": -0.0391, + "n": 30 }, - "iterate": { - "mean": 0.0, - "effect": 0.0, - "n": 9 + "on": { + "mean": 0.8029, + "effect": 0.0024, + "n": 480 + } + }, + "spread": 0.0416 + }, + "tool_grep": { + "values": { + "off": { + "mean": 0.8365, + "effect": 0.036, + "n": 31 }, + "on": { + "mean": 0.7981, + "effect": -0.0023, + "n": 479 + } + }, + "spread": 0.0384 + }, + "context_file": { + "values": { "none": { - "mean": 0.0, - "effect": 0.0, - "n": 249 - }, - "plan_first": { - "mean": 0.0, - "effect": 0.0, - "n": 7 + "mean": 0.7991, + "effect": -0.0014, + "n": 479 }, - "review": { - "mean": 0.0, - "effect": 0.0, - "n": 5 - }, - "split_work": { - "mean": 0.0, - "effect": 0.0, - "n": 5 - }, - "use_subagents": { - "mean": 0.0, - "effect": 0.0, - "n": 161 + "provided": { + "mean": 0.8219, + "effect": 0.0215, + "n": 31 } }, - "spread": 0.0 + "spread": 0.0228 }, - "tool_edit": { + "web_search": { "values": { "off": { - "mean": 0.0, - "effect": 0.0, - "n": 33 + "mean": 0.7797, + "effect": -0.0207, + "n": 36 }, "on": { - "mean": 0.0, - "effect": 0.0, - "n": 418 + "mean": 0.802, + "effect": 0.0016, + "n": 474 } }, - "spread": 0.0 + "spread": 0.0223 }, - "tool_glob": { + "tool_write": { "values": { "off": { - "mean": 0.0, - "effect": 0.0, - "n": 27 + "mean": 0.7824, + "effect": -0.018, + "n": 33 }, "on": { - "mean": 0.0, - "effect": 0.0, - "n": 424 + "mean": 0.8017, + "effect": 0.0012, + "n": 477 } }, - "spread": 0.0 + "spread": 0.0193 }, - "tool_grep": { + "tool_edit": { "values": { "off": { - "mean": 0.0, - "effect": 0.0, - "n": 30 + "mean": 0.8137, + "effect": 0.0133, + "n": 35 }, "on": { - "mean": 0.0, - "effect": 0.0, - "n": 421 + "mean": 0.7995, + "effect": -0.001, + "n": 475 } }, - "spread": 0.0 + "spread": 0.0142 }, - "tool_read": { + "human_language": { "values": { - "off": { - "mean": 0.0, - "effect": 0.0, - "n": 28 + "en": { + "mean": 0.8009, + "effect": 0.0005, + "n": 481 }, - "on": { - "mean": 0.0, - "effect": 0.0, - "n": 423 + "es": { + "mean": 0.7924, + "effect": -0.008, + "n": 29 } }, - "spread": 0.0 + "spread": 0.0085 }, - "tool_write": { + "tool_read": { "values": { "off": { - "mean": 0.0, - "effect": 0.0, + "mean": 0.8058, + "effect": 0.0054, "n": 31 }, "on": { - "mean": 0.0, - "effect": 0.0, - "n": 420 + "mean": 0.8001, + "effect": -0.0003, + "n": 479 } }, - "spread": 0.0 + "spread": 0.0057 }, - "web_search": { + "linter": { "values": { "off": { - "mean": 0.0, - "effect": 0.0, - "n": 33 + "mean": 0.7964, + "effect": -0.004, + "n": 39 }, "on": { - "mean": 0.0, - "effect": 0.0, - "n": 418 + "mean": 0.8008, + "effect": 0.0003, + "n": 471 + } + }, + "spread": 0.0044 + }, + "prompt_style": { + "values": { + "detailed": { + "mean": 0.798, + "effect": -0.0025, + "n": 30 + }, + "simple": { + "mean": 0.8006, + "effect": 0.0002, + "n": 480 } }, - "spread": 0.0 + "spread": 0.0026 } } \ No newline at end of file diff --git a/results/analysis/main_effects_structural.json b/results/analysis/main_effects_structural.json @@ -1,477 +1,477 @@ { - "context_noise": { + "model": { "values": { - "clean": { - "mean": 0.8566, - "effect": 0.019, - "n": 427 + "gemma-4-26b": { + "mean": 0.7442, + "effect": -0.144, + "n": 43 }, - "lorem_100k": { - "mean": 0.5, - "effect": -0.3376, - "n": 3 + "glm-4.5-air": { + "mean": 0.7927, + "effect": -0.0956, + "n": 41 }, - "lorem_10k": { - "mean": 0.5, - "effect": -0.3376, - "n": 3 + "glm-4.7": { + "mean": 0.8827, + "effect": -0.0055, + "n": 81 }, - "lorem_1k": { - "mean": 0.5, - "effect": -0.3376, - "n": 3 + "glm-5.1": { + "mean": 0.8923, + "effect": 0.004, + "n": 123 }, - "lorem_50k": { - "mean": 0.5, - "effect": -0.3376, - "n": 3 + "haiku-4.5": { + "mean": 0.8736, + "effect": -0.0146, + "n": 89 }, - "wikipedia_100k": { - "mean": 0.5, - "effect": -0.3376, + "kimi-k2.5": { + "mean": 0.75, + "effect": -0.1382, "n": 3 }, - "wikipedia_10k": { - "mean": 0.5, - "effect": -0.3376, + "minimax-m2.7": { + "mean": 0.9167, + "effect": 0.0284, "n": 3 }, - "wikipedia_1k": { - "mean": 0.5, - "effect": -0.3376, - "n": 3 + "opus-4.6": { + "mean": 0.9904, + "effect": 0.1021, + "n": 52 }, - "wikipedia_50k": { - "mean": 0.5, - "effect": -0.3376, - "n": 3 + "qwen-3.6-plus": { + "mean": 0.9659, + "effect": 0.0777, + "n": 22 + }, + "sonnet-4.6": { + "mean": 0.9764, + "effect": 0.0882, + "n": 53 } }, - "spread": 0.3566 + "spread": 0.2462 }, "strategy": { "values": { "creative_validate": { - "mean": 0.7, - "effect": -0.1376, - "n": 10 + "mean": 0.8125, + "effect": -0.0757, + "n": 8 }, "delegate": { - "mean": 0.65, - "effect": -0.1876, - "n": 5 + "mean": 0.8929, + "effect": 0.0046, + "n": 7 }, "iterate": { - "mean": 0.75, - "effect": -0.0876, - "n": 9 + "mean": 0.8636, + "effect": -0.0246, + "n": 11 }, "none": { - "mean": 0.7992, - "effect": -0.0384, - "n": 249 + "mean": 0.8683, + "effect": -0.0199, + "n": 300 }, "plan_first": { - "mean": 0.7857, - "effect": -0.0519, - "n": 7 + "mean": 0.875, + "effect": -0.0132, + "n": 10 }, "review": { - "mean": 0.6, - "effect": -0.2376, + "mean": 0.85, + "effect": -0.0382, "n": 5 }, "split_work": { - "mean": 0.6, - "effect": -0.2376, + "mean": 0.7, + "effect": -0.1882, "n": 5 }, "use_subagents": { - "mean": 0.9332, - "effect": 0.0956, - "n": 161 + "mean": 0.9375, + "effect": 0.0493, + "n": 164 } }, - "spread": 0.3332 + "spread": 0.2375 }, - "model": { + "renderer": { "values": { - "gemma-4-26b": { - "mean": 0.7442, - "effect": -0.0934, - "n": 43 - }, - "glm-4.5-air": { - "mean": 0.7927, - "effect": -0.0449, - "n": 41 + "canvas": { + "mean": 0.9286, + "effect": 0.0403, + "n": 7 }, - "glm-4.7": { - "mean": 0.8661, - "effect": 0.0285, - "n": 28 + "dom": { + "mean": 0.9, + "effect": 0.0118, + "n": 5 }, - "glm-5.1": { - "mean": 0.6987, - "effect": -0.1389, - "n": 117 + "none": { + "mean": 0.8886, + "effect": 0.0004, + "n": 487 }, - "haiku-4.5": { - "mean": 0.8736, - "effect": 0.036, - "n": 89 + "svg": { + "mean": 0.8929, + "effect": 0.0046, + "n": 7 }, - "kimi-k2.5": { + "webgl": { "mean": 0.75, - "effect": -0.0876, - "n": 3 + "effect": -0.1382, + "n": 4 + } + }, + "spread": 0.1786 + }, + "context_noise": { + "values": { + "clean": { + "mean": 0.8873, + "effect": -0.0009, + "n": 477 }, - "minimax-m2.7": { + "lorem_100k": { + "mean": 0.875, + "effect": -0.0132, + "n": 6 + }, + "lorem_10k": { + "mean": 0.9167, + "effect": 0.0284, + "n": 6 + }, + "lorem_1k": { "mean": 0.9167, - "effect": 0.0791, + "effect": 0.0284, "n": 3 }, - "opus-4.6": { - "mean": 0.9904, - "effect": 0.1528, - "n": 52 + "lorem_50k": { + "mean": 0.875, + "effect": -0.0132, + "n": 6 }, - "qwen-3.6-plus": { - "mean": 0.9659, - "effect": 0.1283, - "n": 22 + "wikipedia_100k": { + "mean": 1.0, + "effect": 0.1118, + "n": 3 }, - "sonnet-4.6": { - "mean": 0.9764, - "effect": 0.1388, - "n": 53 + "wikipedia_10k": { + "mean": 0.8333, + "effect": -0.0549, + "n": 3 + }, + "wikipedia_1k": { + "mean": 0.9167, + "effect": 0.0284, + "n": 3 + }, + "wikipedia_50k": { + "mean": 0.9167, + "effect": 0.0284, + "n": 3 } }, - "spread": 0.2917 + "spread": 0.1667 }, "error_checking": { "values": { "none": { - "mean": 0.84, - "effect": 0.0025, - "n": 447 + "mean": 0.8893, + "effect": 0.0011, + "n": 506 }, "self_verify": { - "mean": 0.5625, - "effect": -0.2751, + "mean": 0.75, + "effect": -0.1382, "n": 4 } }, - "spread": 0.2775 + "spread": 0.1393 }, - "renderer": { + "language": { "values": { - "canvas": { + "javascript": { "mean": 1.0, - "effect": 0.1624, - "n": 1 + "effect": 0.1118, + "n": 21 }, - "dom": { - "mean": 0.875, - "effect": 0.0374, - "n": 4 - }, - "none": { - "mean": 0.8375, - "effect": -0.0001, - "n": 443 - }, - "svg": { - "mean": 0.75, - "effect": -0.0876, - "n": 1 + "typescript": { + "mean": 0.8785, + "effect": -0.0098, + "n": 469 }, - "webgl": { - "mean": 0.75, - "effect": -0.0876, - "n": 2 + "unspecified": { + "mean": 1.0, + "effect": 0.1118, + "n": 20 } }, - "spread": 0.25 + "spread": 0.1215 }, - "playwright": { + "provider": { "values": { - "available": { - "mean": 0.931, - "effect": 0.0934, - "n": 163 + "anthropic": { + "mean": 0.933, + "effect": 0.0448, + "n": 194 }, - "instructed": { - "mean": 0.6944, - "effect": -0.1431, - "n": 9 + "openrouter": { + "mean": 0.8204, + "effect": -0.0678, + "n": 71 }, - "off": { - "mean": 0.7876, - "effect": -0.0499, - "n": 279 + "zai": { + "mean": 0.8724, + "effect": -0.0158, + "n": 245 } }, - "spread": 0.2366 + "spread": 0.1126 }, - "architecture": { + "playwright": { "values": { - "best_practices": { - "mean": 0.625, - "effect": -0.2126, - "n": 4 + "available": { + "mean": 0.9303, + "effect": 0.0421, + "n": 165 }, - "none": { - "mean": 0.8411, - "effect": 0.0035, - "n": 442 + "instructed": { + "mean": 0.8182, + "effect": -0.0701, + "n": 11 }, - "separation": { - "mean": 0.7, - "effect": -0.1376, - "n": 5 + "off": { + "mean": 0.8698, + "effect": -0.0185, + "n": 334 } }, - "spread": 0.2161 + "spread": 0.1121 }, "design_guidance": { "values": { "none": { - "mean": 0.8418, - "effect": 0.0043, - "n": 441 + "mean": 0.8895, + "effect": 0.0013, + "n": 500 }, "specific": { - "mean": 0.65, - "effect": -0.1876, + "mean": 0.85, + "effect": -0.0382, "n": 5 }, "vague": { - "mean": 0.65, - "effect": -0.1876, + "mean": 0.8, + "effect": -0.0882, "n": 5 } }, - "spread": 0.1918 + "spread": 0.0895 }, - "provider": { + "architecture": { "values": { - "anthropic": { - "mean": 0.933, - "effect": 0.0954, - "n": 194 + "best_practices": { + "mean": 0.9375, + "effect": 0.0493, + "n": 4 }, - "openrouter": { - "mean": 0.8204, - "effect": -0.0172, - "n": 71 + "none": { + "mean": 0.8882, + "effect": -0.0, + "n": 501 }, - "zai": { - "mean": 0.7446, - "effect": -0.093, - "n": 186 + "separation": { + "mean": 0.85, + "effect": -0.0382, + "n": 5 } }, - "spread": 0.1884 + "spread": 0.0875 }, - "language": { + "tool_write": { "values": { - "javascript": { - "mean": 1.0, - "effect": 0.1624, - "n": 20 - }, - "typescript": { - "mean": 0.8218, - "effect": -0.0158, - "n": 411 + "off": { + "mean": 0.8258, + "effect": -0.0625, + "n": 33 }, - "unspecified": { - "mean": 1.0, - "effect": 0.1624, - "n": 20 + "on": { + "mean": 0.8926, + "effect": 0.0043, + "n": 477 } }, - "spread": 0.1782 + "spread": 0.0668 }, - "max_budget": { + "prompt_style": { "values": { - "high": { - "mean": 0.913, - "effect": 0.0755, - "n": 23 + "detailed": { + "mean": 0.8333, + "effect": -0.0549, + "n": 30 }, - "low": { - "mean": 0.8335, - "effect": -0.0041, - "n": 428 + "simple": { + "mean": 0.8917, + "effect": 0.0034, + "n": 480 } }, - "spread": 0.0795 + "spread": 0.0584 }, "effort": { "values": { "high": { - "mean": 0.8351, - "effect": -0.0025, - "n": 435 + "mean": 0.887, + "effect": -0.0013, + "n": 491 }, "max": { - "mean": 0.9062, - "effect": 0.0687, - "n": 16 - } - }, - "spread": 0.0711 - }, - "context_file": { - "values": { - "none": { - "mean": 0.8341, - "effect": -0.0035, - "n": 422 - }, - "provided": { - "mean": 0.8879, - "effect": 0.0503, - "n": 29 + "mean": 0.9211, + "effect": 0.0328, + "n": 19 } }, - "spread": 0.0538 + "spread": 0.0341 }, - "tool_edit": { + "max_budget": { "values": { - "off": { - "mean": 0.8864, - "effect": 0.0488, - "n": 33 + "high": { + "mean": 0.9167, + "effect": 0.0284, + "n": 24 }, - "on": { - "mean": 0.8337, - "effect": -0.0039, - "n": 418 + "low": { + "mean": 0.8868, + "effect": -0.0014, + "n": 486 } }, - "spread": 0.0527 + "spread": 0.0299 }, - "tool_glob": { + "human_language": { "values": { - "off": { - "mean": 0.8796, - "effect": 0.042, - "n": 27 + "en": { + "mean": 0.8898, + "effect": 0.0016, + "n": 481 }, - "on": { - "mean": 0.8349, - "effect": -0.0027, - "n": 424 + "es": { + "mean": 0.8621, + "effect": -0.0262, + "n": 29 } }, - "spread": 0.0447 + "spread": 0.0277 }, - "tool_read": { + "tool_grep": { "values": { "off": { - "mean": 0.875, - "effect": 0.0374, - "n": 28 + "mean": 0.8629, + "effect": -0.0253, + "n": 31 }, "on": { - "mean": 0.8351, - "effect": -0.0025, - "n": 423 + "mean": 0.8899, + "effect": 0.0016, + "n": 479 } }, - "spread": 0.0399 + "spread": 0.027 }, - "web_search": { + "tool_glob": { "values": { "off": { - "mean": 0.8712, - "effect": 0.0336, - "n": 33 + "mean": 0.8667, + "effect": -0.0216, + "n": 30 }, "on": { - "mean": 0.8349, - "effect": -0.0027, - "n": 418 + "mean": 0.8896, + "effect": 0.0013, + "n": 480 } }, - "spread": 0.0363 + "spread": 0.0229 }, "linter": { "values": { "off": { - "mean": 0.8684, - "effect": 0.0308, - "n": 38 + "mean": 0.8718, + "effect": -0.0164, + "n": 39 }, "on": { - "mean": 0.8347, - "effect": -0.0028, - "n": 413 + "mean": 0.8896, + "effect": 0.0014, + "n": 471 } }, - "spread": 0.0337 + "spread": 0.0178 }, - "tool_grep": { + "tool_read": { "values": { "off": { - "mean": 0.8667, - "effect": 0.0291, - "n": 30 + "mean": 0.879, + "effect": -0.0092, + "n": 31 }, "on": { - "mean": 0.8355, - "effect": -0.0021, - "n": 421 + "mean": 0.8888, + "effect": 0.0006, + "n": 479 } }, - "spread": 0.0312 + "spread": 0.0098 }, - "human_language": { + "context_file": { "values": { - "en": { - "mean": 0.8363, - "effect": -0.0013, - "n": 423 + "none": { + "mean": 0.8878, + "effect": -0.0004, + "n": 479 }, - "es": { - "mean": 0.8571, - "effect": 0.0196, - "n": 28 + "provided": { + "mean": 0.8952, + "effect": 0.0069, + "n": 31 } }, - "spread": 0.0208 + "spread": 0.0074 }, - "tool_write": { + "web_search": { "values": { "off": { - "mean": 0.8226, - "effect": -0.015, - "n": 31 + "mean": 0.8819, + "effect": -0.0063, + "n": 36 }, "on": { - "mean": 0.8387, - "effect": 0.0011, - "n": 420 + "mean": 0.8887, + "effect": 0.0005, + "n": 474 } }, - "spread": 0.0161 + "spread": 0.0068 }, - "prompt_style": { + "tool_edit": { "values": { - "detailed": { - "mean": 0.8393, - "effect": 0.0017, - "n": 28 + "off": { + "mean": 0.8857, + "effect": -0.0025, + "n": 35 }, - "simple": { - "mean": 0.8375, - "effect": -0.0001, - "n": 423 + "on": { + "mean": 0.8884, + "effect": 0.0002, + "n": 475 } }, - "spread": 0.0018 + "spread": 0.0027 } } \ No newline at end of file diff --git a/results/analysis/main_effects_transcript.json b/results/analysis/main_effects_transcript.json @@ -3,52 +3,52 @@ "values": { "gemma-4-26b": { "mean": 0.9814, - "effect": 0.0375, + "effect": 0.0449, "n": 43 }, "glm-4.5-air": { "mean": 0.9488, - "effect": 0.0049, + "effect": 0.0123, "n": 41 }, "glm-4.7": { - "mean": 0.9286, - "effect": -0.0153, - "n": 28 + "mean": 0.8926, + "effect": -0.0439, + "n": 81 }, "glm-5.1": { - "mean": 0.9927, - "effect": 0.0488, - "n": 117 + "mean": 0.9898, + "effect": 0.0534, + "n": 123 }, "haiku-4.5": { "mean": 0.7949, - "effect": -0.149, + "effect": -0.1415, "n": 89 }, "kimi-k2.5": { "mean": 0.9333, - "effect": -0.0106, + "effect": -0.0031, "n": 3 }, "minimax-m2.7": { "mean": 1.0, - "effect": 0.0561, + "effect": 0.0635, "n": 3 }, "opus-4.6": { "mean": 1.0, - "effect": 0.0561, + "effect": 0.0635, "n": 52 }, "qwen-3.6-plus": { "mean": 0.9864, - "effect": 0.0425, + "effect": 0.0499, "n": 22 }, "sonnet-4.6": { "mean": 0.9849, - "effect": 0.041, + "effect": 0.0484, "n": 53 } }, @@ -57,421 +57,421 @@ "renderer": { "values": { "canvas": { - "mean": 0.85, - "effect": -0.0939, - "n": 1 + "mean": 0.9071, + "effect": -0.0293, + "n": 7 }, "dom": { "mean": 1.0, - "effect": 0.0561, - "n": 4 + "effect": 0.0635, + "n": 5 }, "none": { - "mean": 0.9438, - "effect": -0.0001, - "n": 443 + "mean": 0.9368, + "effect": 0.0003, + "n": 487 }, "svg": { - "mean": 0.95, - "effect": 0.0061, - "n": 1 + "mean": 0.9, + "effect": -0.0365, + "n": 7 }, "webgl": { - "mean": 0.9, - "effect": -0.0439, - "n": 2 + "mean": 0.9375, + "effect": 0.001, + "n": 4 } }, - "spread": 0.15 + "spread": 0.1 }, - "tool_write": { + "context_noise": { "values": { - "off": { - "mean": 0.8597, - "effect": -0.0842, - "n": 31 + "clean": { + "mean": 0.9345, + "effect": -0.002, + "n": 477 }, - "on": { - "mean": 0.9501, - "effect": 0.0062, - "n": 420 + "lorem_100k": { + "mean": 0.9167, + "effect": -0.0198, + "n": 6 + }, + "lorem_10k": { + "mean": 0.9333, + "effect": -0.0031, + "n": 6 + }, + "lorem_1k": { + "mean": 1.0, + "effect": 0.0635, + "n": 3 + }, + "lorem_50k": { + "mean": 0.9583, + "effect": 0.0219, + "n": 6 + }, + "wikipedia_100k": { + "mean": 1.0, + "effect": 0.0635, + "n": 3 + }, + "wikipedia_10k": { + "mean": 1.0, + "effect": 0.0635, + "n": 3 + }, + "wikipedia_1k": { + "mean": 1.0, + "effect": 0.0635, + "n": 3 + }, + "wikipedia_50k": { + "mean": 1.0, + "effect": 0.0635, + "n": 3 } }, - "spread": 0.0904 + "spread": 0.0833 }, "strategy": { "values": { "creative_validate": { - "mean": 0.975, - "effect": 0.0311, - "n": 10 + "mean": 0.9688, + "effect": 0.0323, + "n": 8 }, "delegate": { - "mean": 0.97, - "effect": 0.0261, - "n": 5 + "mean": 0.9286, + "effect": -0.0079, + "n": 7 }, "iterate": { - "mean": 0.9722, - "effect": 0.0283, - "n": 9 + "mean": 0.9455, + "effect": 0.009, + "n": 11 }, "none": { - "mean": 0.9548, - "effect": 0.0109, - "n": 249 + "mean": 0.9448, + "effect": 0.0084, + "n": 300 }, "plan_first": { - "mean": 0.9643, - "effect": 0.0204, - "n": 7 + "mean": 0.94, + "effect": 0.0035, + "n": 10 }, "review": { - "mean": 0.95, - "effect": 0.0061, + "mean": 0.92, + "effect": -0.0165, "n": 5 }, "split_work": { "mean": 1.0, - "effect": 0.0561, + "effect": 0.0635, "n": 5 }, "use_subagents": { - "mean": 0.9199, - "effect": -0.024, - "n": 161 + "mean": 0.9177, + "effect": -0.0188, + "n": 164 } }, - "spread": 0.0801 + "spread": 0.0823 }, "provider": { "values": { "anthropic": { "mean": 0.9018, - "effect": -0.0421, + "effect": -0.0347, "n": 194 }, "openrouter": { "mean": 0.9817, - "effect": 0.0378, + "effect": 0.0452, "n": 71 }, "zai": { - "mean": 0.9734, - "effect": 0.0295, - "n": 186 + "mean": 0.9508, + "effect": 0.0143, + "n": 245 } }, "spread": 0.0799 }, - "tool_read": { + "tool_write": { "values": { "off": { - "mean": 0.8732, - "effect": -0.0707, - "n": 28 + "mean": 0.8621, + "effect": -0.0743, + "n": 33 }, "on": { - "mean": 0.9486, - "effect": 0.0047, - "n": 423 + "mean": 0.9416, + "effect": 0.0051, + "n": 477 } }, - "spread": 0.0754 + "spread": 0.0795 }, - "tool_edit": { + "tool_glob": { "values": { "off": { - "mean": 0.8773, - "effect": -0.0666, - "n": 33 + "mean": 0.8733, + "effect": -0.0631, + "n": 30 }, "on": { - "mean": 0.9492, - "effect": 0.0053, - "n": 418 + "mean": 0.9404, + "effect": 0.0039, + "n": 480 } }, - "spread": 0.0719 + "spread": 0.0671 }, "context_file": { "values": { "none": { - "mean": 0.9483, - "effect": 0.0044, - "n": 422 + "mean": 0.9404, + "effect": 0.0039, + "n": 479 }, "provided": { - "mean": 0.8793, - "effect": -0.0646, - "n": 29 + "mean": 0.8758, + "effect": -0.0607, + "n": 31 } }, - "spread": 0.069 + "spread": 0.0646 }, - "tool_glob": { + "tool_read": { "values": { "off": { - "mean": 0.8815, - "effect": -0.0624, - "n": 27 + "mean": 0.8774, + "effect": -0.0591, + "n": 31 }, "on": { - "mean": 0.9479, - "effect": 0.004, - "n": 424 + "mean": 0.9403, + "effect": 0.0038, + "n": 479 } }, - "spread": 0.0664 + "spread": 0.0629 }, "human_language": { "values": { "en": { - "mean": 0.948, - "effect": 0.0041, - "n": 423 + "mean": 0.94, + "effect": 0.0036, + "n": 481 }, "es": { - "mean": 0.8821, - "effect": -0.0618, - "n": 28 + "mean": 0.8776, + "effect": -0.0589, + "n": 29 } }, - "spread": 0.0659 + "spread": 0.0624 }, - "prompt_style": { + "tool_edit": { "values": { - "detailed": { - "mean": 0.8821, - "effect": -0.0618, - "n": 28 + "off": { + "mean": 0.88, + "effect": -0.0565, + "n": 35 }, - "simple": { - "mean": 0.948, - "effect": 0.0041, - "n": 423 + "on": { + "mean": 0.9406, + "effect": 0.0042, + "n": 475 } }, - "spread": 0.0659 + "spread": 0.0606 }, - "web_search": { + "linter": { "values": { "off": { - "mean": 0.8833, - "effect": -0.0606, - "n": 33 + "mean": 0.8821, + "effect": -0.0544, + "n": 39 }, "on": { - "mean": 0.9487, - "effect": 0.0048, - "n": 418 + "mean": 0.941, + "effect": 0.0045, + "n": 471 } }, - "spread": 0.0654 + "spread": 0.0589 }, - "tool_grep": { + "language": { "values": { - "off": { - "mean": 0.8833, - "effect": -0.0606, - "n": 30 + "javascript": { + "mean": 0.9905, + "effect": 0.054, + "n": 21 }, - "on": { - "mean": 0.9482, - "effect": 0.0043, - "n": 421 + "typescript": { + "mean": 0.932, + "effect": -0.0045, + "n": 469 + }, + "unspecified": { + "mean": 0.985, + "effect": 0.0485, + "n": 20 } }, - "spread": 0.0649 + "spread": 0.0585 }, - "linter": { + "tool_grep": { "values": { "off": { - "mean": 0.8855, - "effect": -0.0584, - "n": 38 + "mean": 0.8823, + "effect": -0.0542, + "n": 31 }, "on": { - "mean": 0.9493, - "effect": 0.0054, - "n": 413 + "mean": 0.94, + "effect": 0.0035, + "n": 479 } }, - "spread": 0.0638 + "spread": 0.0577 }, - "context_noise": { + "playwright": { "values": { - "clean": { - "mean": 0.9407, - "effect": -0.0032, - "n": 427 - }, - "lorem_100k": { - "mean": 1.0, - "effect": 0.0561, - "n": 3 - }, - "lorem_10k": { - "mean": 1.0, - "effect": 0.0561, - "n": 3 - }, - "lorem_1k": { - "mean": 1.0, - "effect": 0.0561, - "n": 3 - }, - "lorem_50k": { - "mean": 1.0, - "effect": 0.0561, - "n": 3 - }, - "wikipedia_100k": { - "mean": 1.0, - "effect": 0.0561, - "n": 3 - }, - "wikipedia_10k": { - "mean": 1.0, - "effect": 0.0561, - "n": 3 + "available": { + "mean": 0.9155, + "effect": -0.021, + "n": 165 }, - "wikipedia_1k": { - "mean": 1.0, - "effect": 0.0561, - "n": 3 + "instructed": { + "mean": 0.9727, + "effect": 0.0363, + "n": 11 }, - "wikipedia_50k": { - "mean": 1.0, - "effect": 0.0561, - "n": 3 + "off": { + "mean": 0.9457, + "effect": 0.0092, + "n": 334 } }, - "spread": 0.0593 + "spread": 0.0572 }, - "playwright": { + "web_search": { "values": { - "available": { - "mean": 0.9147, - "effect": -0.0292, - "n": 163 - }, - "instructed": { - "mean": 0.9722, - "effect": 0.0283, - "n": 9 - }, "off": { - "mean": 0.96, - "effect": 0.0161, - "n": 279 + "mean": 0.8833, + "effect": -0.0531, + "n": 36 + }, + "on": { + "mean": 0.9405, + "effect": 0.004, + "n": 474 } }, - "spread": 0.0575 + "spread": 0.0572 }, "architecture": { "values": { "best_practices": { - "mean": 0.9875, - "effect": 0.0436, + "mean": 0.975, + "effect": 0.0385, "n": 4 }, "none": { - "mean": 0.9429, - "effect": -0.001, - "n": 442 + "mean": 0.9356, + "effect": -0.0008, + "n": 501 }, "separation": { - "mean": 1.0, - "effect": 0.0561, + "mean": 0.99, + "effect": 0.0535, "n": 5 } }, - "spread": 0.0571 + "spread": 0.0544 }, - "design_guidance": { + "prompt_style": { "values": { - "none": { - "mean": 0.9432, - "effect": -0.0007, - "n": 441 - }, - "specific": { - "mean": 0.95, - "effect": 0.0061, - "n": 5 + "detailed": { + "mean": 0.89, + "effect": -0.0465, + "n": 30 }, - "vague": { - "mean": 1.0, - "effect": 0.0561, - "n": 5 + "simple": { + "mean": 0.9394, + "effect": 0.0029, + "n": 480 } }, - "spread": 0.0568 + "spread": 0.0494 }, "max_budget": { "values": { "high": { - "mean": 0.8935, - "effect": -0.0504, - "n": 23 + "mean": 0.8917, + "effect": -0.0448, + "n": 24 }, "low": { - "mean": 0.9466, - "effect": 0.0027, - "n": 428 + "mean": 0.9387, + "effect": 0.0022, + "n": 486 } }, - "spread": 0.0531 + "spread": 0.047 }, - "language": { + "design_guidance": { "values": { - "javascript": { - "mean": 0.9875, - "effect": 0.0436, - "n": 20 + "none": { + "mean": 0.936, + "effect": -0.0005, + "n": 500 }, - "typescript": { - "mean": 0.9398, - "effect": -0.0041, - "n": 411 + "specific": { + "mean": 0.95, + "effect": 0.0135, + "n": 5 }, - "unspecified": { - "mean": 0.985, - "effect": 0.0411, - "n": 20 + "vague": { + "mean": 0.97, + "effect": 0.0335, + "n": 5 } }, - "spread": 0.0477 + "spread": 0.034 }, "error_checking": { "values": { "none": { - "mean": 0.9437, + "mean": 0.9363, "effect": -0.0002, - "n": 447 + "n": 506 }, "self_verify": { "mean": 0.9625, - "effect": 0.0186, + "effect": 0.026, "n": 4 } }, - "spread": 0.0188 + "spread": 0.0262 }, "effort": { "values": { "high": { - "mean": 0.9441, - "effect": 0.0002, - "n": 435 + "mean": 0.9363, + "effect": -0.0002, + "n": 491 }, "max": { - "mean": 0.9375, - "effect": -0.0064, - "n": 16 + "mean": 0.9421, + "effect": 0.0056, + "n": 19 } }, - "spread": 0.0066 + "spread": 0.0058 } } \ No newline at end of file diff --git a/results/analysis/main_effects_turns.json b/results/analysis/main_effects_turns.json @@ -3,17 +3,17 @@ "values": { "best_practices": { "mean": 50.0, - "effect": 25.1094, + "effect": 24.502, "n": 4 }, "none": { - "mean": 24.7031, - "effect": -0.1875, - "n": 448 + "mean": 25.3413, + "effect": -0.1567, + "n": 501 }, "separation": { "mean": 21.6, - "effect": -3.2906, + "effect": -3.898, "n": 5 } }, @@ -23,97 +23,97 @@ "values": { "creative_validate": { "mean": 41.875, - "effect": 16.9844, + "effect": 16.377, "n": 8 }, "delegate": { - "mean": 29.6, - "effect": 4.7094, - "n": 5 + "mean": 38.5714, + "effect": 13.0734, + "n": 7 }, "iterate": { - "mean": 35.8889, - "effect": 10.9983, - "n": 9 + "mean": 40.0909, + "effect": 14.5929, + "n": 11 }, "none": { - "mean": 24.035, - "effect": -0.8556, - "n": 257 + "mean": 24.5733, + "effect": -0.9247, + "n": 300 }, "plan_first": { - "mean": 38.7143, - "effect": 13.8237, - "n": 7 + "mean": 36.0, + "effect": 10.502, + "n": 10 }, "review": { "mean": 46.0, - "effect": 21.1094, + "effect": 20.502, "n": 5 }, "split_work": { "mean": 49.2, - "effect": 24.3094, + "effect": 23.702, "n": 5 }, "use_subagents": { - "mean": 22.6398, - "effect": -2.2508, - "n": 161 + "mean": 22.8659, + "effect": -2.6322, + "n": 164 } }, - "spread": 26.5602 + "spread": 26.3341 }, "model": { "values": { "gemma-4-26b": { "mean": 45.2558, - "effect": 20.3652, + "effect": 19.7578, "n": 43 }, "glm-4.5-air": { "mean": 23.6585, - "effect": -1.2321, + "effect": -1.8395, "n": 41 }, "glm-4.7": { - "mean": 21.3571, - "effect": -3.5334, - "n": 28 + "mean": 27.4938, + "effect": 1.9958, + "n": 81 }, "glm-5.1": { "mean": 22.0569, - "effect": -2.8337, + "effect": -3.4411, "n": 123 }, "haiku-4.5": { "mean": 27.5393, - "effect": 2.6487, + "effect": 2.0413, "n": 89 }, "kimi-k2.5": { "mean": 27.0, - "effect": 2.1094, + "effect": 1.502, "n": 3 }, "minimax-m2.7": { "mean": 32.6667, - "effect": 7.7761, + "effect": 7.1686, "n": 3 }, "opus-4.6": { "mean": 19.4808, - "effect": -5.4098, + "effect": -6.0173, "n": 52 }, "qwen-3.6-plus": { "mean": 20.3182, - "effect": -4.5724, + "effect": -5.1799, "n": 22 }, "sonnet-4.6": { "mean": 19.9623, - "effect": -4.9283, + "effect": -5.5358, "n": 53 } }, @@ -122,356 +122,356 @@ "playwright": { "values": { "available": { - "mean": 22.3497, - "effect": -2.5409, - "n": 163 + "mean": 22.5697, + "effect": -2.9283, + "n": 165 }, "instructed": { - "mean": 41.2222, - "effect": 16.3316, - "n": 9 + "mean": 43.8182, + "effect": 18.3201, + "n": 11 }, "off": { - "mean": 25.8281, - "effect": 0.9375, - "n": 285 + "mean": 26.3413, + "effect": 0.8433, + "n": 334 } }, - "spread": 18.8725 + "spread": 21.2485 }, "error_checking": { "values": { "none": { - "mean": 24.7439, - "effect": -0.1467, - "n": 453 + "mean": 25.3715, + "effect": -0.1265, + "n": 506 }, "self_verify": { "mean": 41.5, - "effect": 16.6094, + "effect": 16.002, "n": 4 } }, - "spread": 16.7561 + "spread": 16.1285 }, "language": { "values": { "javascript": { - "mean": 13.6, - "effect": -11.2906, - "n": 20 + "mean": 13.1905, + "effect": -12.3076, + "n": 21 }, "typescript": { - "mean": 26.1031, - "effect": 1.2125, - "n": 417 + "mean": 26.6716, + "effect": 1.1736, + "n": 469 }, "unspecified": { "mean": 10.9, - "effect": -13.9906, + "effect": -14.598, "n": 20 } }, - "spread": 15.2031 + "spread": 15.7716 }, "provider": { "values": { "anthropic": { "mean": 23.3093, - "effect": -1.5813, + "effect": -2.1888, "n": 194 }, "openrouter": { "mean": 36.2254, - "effect": 11.3348, + "effect": 10.7273, "n": 71 }, "zai": { - "mean": 22.2969, - "effect": -2.5937, - "n": 192 + "mean": 24.1224, + "effect": -1.3756, + "n": 245 } }, - "spread": 13.9285 + "spread": 12.9161 }, "context_noise": { "values": { "clean": { - "mean": 25.3372, - "effect": 0.4466, - "n": 433 + "mean": 25.9182, + "effect": 0.4202, + "n": 477 }, "lorem_100k": { - "mean": 14.6667, - "effect": -10.2239, - "n": 3 + "mean": 21.8333, + "effect": -3.6647, + "n": 6 }, "lorem_10k": { - "mean": 15.6667, - "effect": -9.2239, - "n": 3 + "mean": 20.5, + "effect": -4.998, + "n": 6 }, "lorem_1k": { "mean": 23.3333, - "effect": -1.5573, + "effect": -2.1647, "n": 3 }, "lorem_50k": { - "mean": 14.0, - "effect": -10.8906, - "n": 3 + "mean": 19.3333, + "effect": -6.1647, + "n": 6 }, "wikipedia_100k": { "mean": 15.6667, - "effect": -9.2239, + "effect": -9.8314, "n": 3 }, "wikipedia_10k": { "mean": 15.0, - "effect": -9.8906, + "effect": -10.498, "n": 3 }, "wikipedia_1k": { "mean": 16.0, - "effect": -8.8906, + "effect": -9.498, "n": 3 }, "wikipedia_50k": { "mean": 20.3333, - "effect": -4.5573, + "effect": -5.1647, "n": 3 } }, - "spread": 11.3372 + "spread": 10.9182 }, "design_guidance": { "values": { "none": { - "mean": 24.9597, - "effect": 0.0691, - "n": 447 + "mean": 25.572, + "effect": 0.074, + "n": 500 }, "specific": { "mean": 18.0, - "effect": -6.8906, + "effect": -7.498, "n": 5 }, "vague": { "mean": 25.6, - "effect": 0.7094, + "effect": 0.102, "n": 5 } }, "spread": 7.6 }, + "prompt_style": { + "values": { + "detailed": { + "mean": 18.9, + "effect": -6.598, + "n": 30 + }, + "simple": { + "mean": 25.9104, + "effect": 0.4124, + "n": 480 + } + }, + "spread": 7.0104 + }, + "linter": { + "values": { + "off": { + "mean": 20.6667, + "effect": -4.8314, + "n": 39 + }, + "on": { + "mean": 25.8981, + "effect": 0.4, + "n": 471 + } + }, + "spread": 5.2314 + }, "renderer": { "values": { "canvas": { - "mean": 27.75, - "effect": 2.8594, - "n": 4 + "mean": 28.1429, + "effect": 2.6448, + "n": 7 }, "dom": { - "mean": 29.25, - "effect": 4.3594, - "n": 4 + "mean": 27.4, + "effect": 1.902, + "n": 5 }, "none": { - "mean": 24.7596, - "effect": -0.131, - "n": 441 + "mean": 25.3778, + "effect": -0.1202, + "n": 487 }, "svg": { - "mean": 26.5, - "effect": 1.6094, - "n": 4 + "mean": 27.0, + "effect": 1.502, + "n": 7 }, "webgl": { "mean": 30.5, - "effect": 5.6094, + "effect": 5.002, "n": 4 } }, - "spread": 5.7404 + "spread": 5.1222 }, - "prompt_style": { + "max_budget": { "values": { - "detailed": { - "mean": 19.8929, - "effect": -4.9977, - "n": 28 + "high": { + "mean": 21.7083, + "effect": -3.7897, + "n": 24 }, - "simple": { - "mean": 25.2168, - "effect": 0.3262, - "n": 429 + "low": { + "mean": 25.6852, + "effect": 0.1871, + "n": 486 } }, - "spread": 5.3239 + "spread": 3.9769 }, - "linter": { + "context_file": { "values": { - "off": { - "mean": 20.3684, - "effect": -4.5222, - "n": 38 + "none": { + "mean": 25.6743, + "effect": 0.1763, + "n": 479 }, - "on": { - "mean": 25.3007, - "effect": 0.4101, - "n": 419 + "provided": { + "mean": 22.7742, + "effect": -2.7238, + "n": 31 } }, - "spread": 4.9323 + "spread": 2.9001 }, - "max_budget": { + "human_language": { "values": { - "high": { - "mean": 21.8696, - "effect": -3.021, - "n": 23 + "en": { + "mean": 25.657, + "effect": 0.1589, + "n": 481 }, - "low": { - "mean": 25.0507, - "effect": 0.1601, - "n": 434 + "es": { + "mean": 22.8621, + "effect": -2.636, + "n": 29 } }, - "spread": 3.1811 + "spread": 2.7949 }, "tool_glob": { "values": { "off": { - "mean": 27.8148, - "effect": 2.9242, - "n": 27 + "mean": 27.9333, + "effect": 2.4353, + "n": 30 }, "on": { - "mean": 24.707, - "effect": -0.1836, - "n": 430 + "mean": 25.3458, + "effect": -0.1522, + "n": 480 } }, - "spread": 3.1078 + "spread": 2.5875 }, "tool_grep": { "values": { "off": { - "mean": 27.6, - "effect": 2.7094, - "n": 30 + "mean": 27.4516, + "effect": 1.9536, + "n": 31 }, "on": { - "mean": 24.7002, - "effect": -0.1904, - "n": 427 - } - }, - "spread": 2.8998 - }, - "human_language": { - "values": { - "en": { - "mean": 25.0536, - "effect": 0.163, - "n": 429 - }, - "es": { - "mean": 22.3929, - "effect": -2.4977, - "n": 28 + "mean": 25.3716, + "effect": -0.1264, + "n": 479 } }, - "spread": 2.6607 + "spread": 2.08 }, - "context_file": { - "values": { - "none": { - "mean": 25.0491, - "effect": 0.1585, - "n": 428 - }, - "provided": { - "mean": 22.5517, - "effect": -2.3389, - "n": 29 - } - }, - "spread": 2.4974 - }, - "tool_write": { + "web_search": { "values": { "off": { - "mean": 27.0968, - "effect": 2.2062, - "n": 31 + "mean": 24.0278, + "effect": -1.4703, + "n": 36 }, "on": { - "mean": 24.73, - "effect": -0.1605, - "n": 426 + "mean": 25.6097, + "effect": 0.1117, + "n": 474 } }, - "spread": 2.3668 + "spread": 1.5819 }, - "tool_read": { + "tool_write": { "values": { "off": { - "mean": 26.8571, - "effect": 1.9666, - "n": 28 + "mean": 26.6364, + "effect": 1.1383, + "n": 33 }, "on": { - "mean": 24.7622, - "effect": -0.1284, - "n": 429 + "mean": 25.4193, + "effect": -0.0788, + "n": 477 } }, - "spread": 2.0949 + "spread": 1.2171 }, - "web_search": { + "tool_read": { "values": { "off": { - "mean": 23.6667, - "effect": -1.2239, - "n": 33 + "mean": 26.2903, + "effect": 0.7923, + "n": 31 }, "on": { - "mean": 24.9858, - "effect": 0.0953, - "n": 424 + "mean": 25.4468, + "effect": -0.0513, + "n": 479 } }, - "spread": 1.3191 + "spread": 0.8435 }, "effort": { "values": { "high": { - "mean": 24.8753, - "effect": -0.0153, - "n": 441 + "mean": 25.5132, + "effect": 0.0152, + "n": 491 }, "max": { - "mean": 25.3125, - "effect": 0.4219, - "n": 16 + "mean": 25.1053, + "effect": -0.3928, + "n": 19 } }, - "spread": 0.4372 + "spread": 0.4079 }, "tool_edit": { "values": { "off": { - "mean": 24.9091, - "effect": 0.0185, - "n": 33 + "mean": 25.1429, + "effect": -0.3552, + "n": 35 }, "on": { - "mean": 24.8892, - "effect": -0.0014, - "n": 424 + "mean": 25.5242, + "effect": 0.0262, + "n": 475 } }, - "spread": 0.0199 + "spread": 0.3813 } } \ No newline at end of file diff --git a/results/analysis/main_effects_wall_time.json b/results/analysis/main_effects_wall_time.json @@ -2,83 +2,83 @@ "renderer": { "values": { "canvas": { - "mean": 286.0, - "effect": -231.7309, - "n": 4 + "mean": 435.7143, + "effect": -82.3289, + "n": 7 }, "dom": { - "mean": 480.0, - "effect": -37.7309, - "n": 4 + "mean": 410.4, + "effect": -107.6431, + "n": 5 }, "none": { - "mean": 514.5488, - "effect": -3.1821, - "n": 441 + "mean": 515.0205, + "effect": -3.0226, + "n": 487 }, "svg": { - "mean": 545.25, - "effect": 27.5191, - "n": 4 + "mean": 549.0, + "effect": 30.9569, + "n": 7 }, "webgl": { "mean": 1110.5, - "effect": 592.7691, + "effect": 592.4569, "n": 4 } }, - "spread": 824.5 + "spread": 700.1 }, "model": { "values": { "gemma-4-26b": { "mean": 838.3953, - "effect": 320.6645, + "effect": 320.3522, "n": 43 }, "glm-4.5-air": { "mean": 629.7073, - "effect": 111.9765, + "effect": 111.6642, "n": 41 }, "glm-4.7": { - "mean": 521.5, - "effect": 3.7691, - "n": 28 + "mean": 521.0, + "effect": 2.9569, + "n": 81 }, "glm-5.1": { "mean": 533.8455, - "effect": 16.1147, + "effect": 15.8024, "n": 123 }, "haiku-4.5": { "mean": 228.5281, - "effect": -289.2028, + "effect": -289.515, "n": 89 }, "kimi-k2.5": { "mean": 674.6667, - "effect": 156.9358, + "effect": 156.6235, "n": 3 }, "minimax-m2.7": { "mean": 499.0, - "effect": -18.7309, + "effect": -19.0431, "n": 3 }, "opus-4.6": { "mean": 228.2308, - "effect": -289.5001, + "effect": -289.8124, "n": 52 }, "qwen-3.6-plus": { "mean": 743.7273, - "effect": 225.9964, + "effect": 225.6841, "n": 22 }, "sonnet-4.6": { "mean": 799.6038, - "effect": 281.8729, + "effect": 281.5606, "n": 53 } }, @@ -88,390 +88,390 @@ "values": { "best_practices": { "mean": 941.25, - "effect": 423.5191, + "effect": 423.2069, "n": 4 }, "none": { - "mean": 515.8817, - "effect": -1.8492, - "n": 448 + "mean": 516.3952, + "effect": -1.6479, + "n": 501 }, "separation": { "mean": 344.6, - "effect": -173.1309, + "effect": -173.4431, "n": 5 } }, "spread": 596.65 }, + "design_guidance": { + "values": { + "none": { + "mean": 511.946, + "effect": -6.0971, + "n": 500 + }, + "specific": { + "mean": 687.4, + "effect": 169.3569, + "n": 5 + }, + "vague": { + "mean": 958.4, + "effect": 440.3569, + "n": 5 + } + }, + "spread": 446.454 + }, + "provider": { + "values": { + "anthropic": { + "mean": 384.4639, + "effect": -133.5792, + "n": 194 + }, + "openrouter": { + "mean": 787.8028, + "effect": 269.7597, + "n": 71 + }, + "zai": { + "mean": 545.6408, + "effect": 27.5977, + "n": 245 + } + }, + "spread": 403.3389 + }, + "error_checking": { + "values": { + "none": { + "mean": 514.8913, + "effect": -3.1518, + "n": 506 + }, + "self_verify": { + "mean": 916.75, + "effect": 398.7069, + "n": 4 + } + }, + "spread": 401.8587 + }, "context_noise": { "values": { "clean": { - "mean": 527.8614, - "effect": 10.1306, - "n": 433 + "mean": 531.4549, + "effect": 13.4118, + "n": 477 }, "lorem_100k": { - "mean": 269.6667, - "effect": -248.0642, - "n": 3 + "mean": 232.1667, + "effect": -285.8765, + "n": 6 }, "lorem_10k": { - "mean": 286.6667, - "effect": -231.0642, - "n": 3 + "mean": 245.6667, + "effect": -272.3765, + "n": 6 }, "lorem_1k": { "mean": 346.6667, - "effect": -171.0642, + "effect": -171.3765, "n": 3 }, "lorem_50k": { - "mean": 750.6667, - "effect": 232.9358, - "n": 3 + "mean": 618.8333, + "effect": 100.7902, + "n": 6 }, "wikipedia_100k": { "mean": 270.0, - "effect": -247.7309, + "effect": -248.0431, "n": 3 }, "wikipedia_10k": { "mean": 255.3333, - "effect": -262.3975, + "effect": -262.7098, "n": 3 }, "wikipedia_1k": { "mean": 238.3333, - "effect": -279.3975, + "effect": -279.7098, "n": 3 }, "wikipedia_50k": { "mean": 262.3333, - "effect": -255.3975, + "effect": -255.7098, "n": 3 } }, - "spread": 512.3334 - }, - "design_guidance": { - "values": { - "none": { - "mean": 510.9038, - "effect": -6.8271, - "n": 447 - }, - "specific": { - "mean": 687.4, - "effect": 169.6691, - "n": 5 - }, - "vague": { - "mean": 958.4, - "effect": 440.6691, - "n": 5 - } - }, - "spread": 447.4962 + "spread": 386.6666 }, "strategy": { "values": { "creative_validate": { "mean": 782.0, - "effect": 264.2691, + "effect": 263.9569, "n": 8 }, "delegate": { - "mean": 856.4, - "effect": 338.6691, - "n": 5 + "mean": 759.4286, + "effect": 241.3854, + "n": 7 }, "iterate": { - "mean": 791.1111, - "effect": 273.3803, - "n": 9 + "mean": 760.3636, + "effect": 242.3205, + "n": 11 }, "none": { - "mean": 537.2062, - "effect": 19.4754, - "n": 257 + "mean": 528.6133, + "effect": 10.5702, + "n": 300 }, "plan_first": { - "mean": 837.1429, - "effect": 319.412, - "n": 7 + "mean": 801.4, + "effect": 283.3569, + "n": 10 }, "review": { "mean": 746.6, - "effect": 228.8691, + "effect": 228.5569, "n": 5 }, "split_work": { "mean": 780.4, - "effect": 262.6691, + "effect": 262.3569, "n": 5 }, "use_subagents": { - "mean": 418.559, - "effect": -99.1718, - "n": 161 + "mean": 427.0305, + "effect": -91.0126, + "n": 164 } }, - "spread": 437.841 + "spread": 374.3695 }, "playwright": { "values": { "available": { - "mean": 413.7301, - "effect": -104.0008, - "n": 163 + "mean": 419.0909, + "effect": -98.9522, + "n": 165 }, "instructed": { - "mean": 837.3333, - "effect": 319.6025, - "n": 9 + "mean": 775.6364, + "effect": 257.5932, + "n": 11 }, "off": { - "mean": 567.1193, - "effect": 49.3884, - "n": 285 + "mean": 558.4431, + "effect": 40.4, + "n": 334 } }, - "spread": 423.6032 - }, - "provider": { - "values": { - "anthropic": { - "mean": 384.4639, - "effect": -133.2669, - "n": 194 - }, - "openrouter": { - "mean": 787.8028, - "effect": 270.072, - "n": 71 - }, - "zai": { - "mean": 552.5156, - "effect": 34.7848, - "n": 192 - } - }, - "spread": 403.3389 - }, - "error_checking": { - "values": { - "none": { - "mean": 514.2075, - "effect": -3.5233, - "n": 453 - }, - "self_verify": { - "mean": 916.75, - "effect": 399.0191, - "n": 4 - } - }, - "spread": 402.5425 + "spread": 356.5455 }, "context_file": { "values": { "none": { - "mean": 530.9299, - "effect": 13.1991, - "n": 428 + "mean": 531.2881, + "effect": 13.245, + "n": 479 }, "provided": { - "mean": 322.931, - "effect": -194.7998, - "n": 29 - } - }, - "spread": 207.9989 - }, - "max_budget": { - "values": { - "high": { - "mean": 324.3913, - "effect": -193.3395, - "n": 23 - }, - "low": { - "mean": 527.977, - "effect": 10.2461, - "n": 434 + "mean": 313.3871, + "effect": -204.656, + "n": 31 } }, - "spread": 203.5857 + "spread": 217.901 }, "linter": { "values": { "off": { - "mean": 348.8421, - "effect": -168.8887, - "n": 38 + "mean": 348.1538, + "effect": -169.8893, + "n": 39 }, "on": { - "mean": 533.0477, - "effect": 15.3169, - "n": 419 + "mean": 532.1104, + "effect": 14.0673, + "n": 471 } }, - "spread": 184.2056 + "spread": 183.9566 }, - "language": { + "max_budget": { "values": { - "javascript": { - "mean": 439.3, - "effect": -78.4309, - "n": 20 - }, - "typescript": { - "mean": 527.3094, - "effect": 9.5785, - "n": 417 + "high": { + "mean": 360.875, + "effect": -157.1681, + "n": 24 }, - "unspecified": { - "mean": 396.45, - "effect": -121.2809, - "n": 20 + "low": { + "mean": 525.8045, + "effect": 7.7614, + "n": 486 } }, - "spread": 130.8594 + "spread": 164.9295 }, - "tool_read": { + "effort": { "values": { - "off": { - "mean": 399.6786, - "effect": -118.0523, - "n": 28 + "high": { + "mean": 512.7475, + "effect": -5.2957, + "n": 491 }, - "on": { - "mean": 525.4359, - "effect": 7.705, - "n": 429 + "max": { + "mean": 654.8947, + "effect": 136.8516, + "n": 19 } }, - "spread": 125.7573 + "spread": 142.1472 }, "prompt_style": { "values": { "detailed": { - "mean": 402.8214, - "effect": -114.9094, - "n": 28 + "mean": 386.0, + "effect": -132.0431, + "n": 30 }, "simple": { - "mean": 525.2308, - "effect": 7.4999, - "n": 429 + "mean": 526.2958, + "effect": 8.2527, + "n": 480 } }, - "spread": 122.4094 + "spread": 140.2958 }, "web_search": { "values": { "off": { - "mean": 410.6667, - "effect": -107.0642, - "n": 33 + "mean": 392.5, + "effect": -125.5431, + "n": 36 }, "on": { - "mean": 526.0637, - "effect": 8.3328, - "n": 424 + "mean": 527.5781, + "effect": 9.5349, + "n": 474 } }, - "spread": 115.397 + "spread": 135.0781 }, - "tool_grep": { + "language": { "values": { - "off": { - "mean": 410.8333, - "effect": -106.8975, - "n": 30 + "javascript": { + "mean": 427.2857, + "effect": -90.7574, + "n": 21 }, - "on": { - "mean": 525.2412, - "effect": 7.5104, - "n": 427 + "typescript": { + "mean": 527.2921, + "effect": 9.249, + "n": 469 + }, + "unspecified": { + "mean": 396.45, + "effect": -121.5931, + "n": 20 } }, - "spread": 114.4079 + "spread": 130.8421 }, - "tool_glob": { + "tool_grep": { "values": { "off": { - "mean": 410.8889, - "effect": -106.842, - "n": 27 + "mean": 403.7419, + "effect": -114.3012, + "n": 31 }, "on": { - "mean": 524.4395, - "effect": 6.7087, - "n": 430 + "mean": 525.4405, + "effect": 7.3974, + "n": 479 } }, - "spread": 113.5506 + "spread": 121.6986 }, "tool_edit": { "values": { "off": { - "mean": 417.0303, - "effect": -100.7006, - "n": 33 + "mean": 413.1714, + "effect": -104.8717, + "n": 35 }, "on": { - "mean": 525.5684, - "effect": 7.8375, - "n": 424 + "mean": 525.7705, + "effect": 7.7274, + "n": 475 } }, - "spread": 108.5381 + "spread": 112.5991 }, "human_language": { "values": { "en": { - "mean": 524.2727, - "effect": 6.5419, - "n": 429 + "mean": 524.2599, + "effect": 6.2167, + "n": 481 }, "es": { - "mean": 417.5, - "effect": -100.2309, - "n": 28 + "mean": 414.931, + "effect": -103.1121, + "n": 29 } }, - "spread": 106.7727 + "spread": 109.3289 }, - "tool_write": { + "tool_read": { "values": { "off": { - "mean": 436.1935, - "effect": -81.5373, + "mean": 420.9355, + "effect": -97.1077, "n": 31 }, "on": { - "mean": 523.6643, - "effect": 5.9335, - "n": 426 + "mean": 524.3278, + "effect": 6.2846, + "n": 479 } }, - "spread": 87.4708 + "spread": 103.3923 }, - "effort": { + "tool_write": { "values": { - "high": { - "mean": 516.4626, - "effect": -1.2683, - "n": 441 + "off": { + "mean": 422.7879, + "effect": -95.2553, + "n": 33 }, - "max": { - "mean": 552.6875, - "effect": 34.9566, - "n": 16 + "on": { + "mean": 524.6331, + "effect": 6.59, + "n": 477 + } + }, + "spread": 101.8452 + }, + "tool_glob": { + "values": { + "off": { + "mean": 429.1667, + "effect": -88.8765, + "n": 30 + }, + "on": { + "mean": 523.5979, + "effect": 5.5548, + "n": 480 } }, - "spread": 36.2249 + "spread": 94.4312 } } \ No newline at end of file diff --git a/results/index.jsonl b/results/index.jsonl @@ -1,12 +1,17 @@ {"run_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "42f30c6b", "short_cell_id": "24e38369", "completed_at": "2026-04-07T20:59:02.945667+00:00"} +{"run_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3a4446e0", "short_cell_id": "d305e89b", "completed_at": "2026-04-14T18:15:30.333023+00:00"} +{"run_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e9675236", "short_cell_id": "d305e89b", "completed_at": "2026-04-14T18:33:54.509350+00:00"} +{"run_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "a6720fb3", "short_cell_id": "d305e89b", "completed_at": "2026-04-14T18:35:22.187209+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=gemma426b_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "gemma-4-26b", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=gemma426b_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ed36af6d", "short_cell_id": "9ee24e4e", "completed_at": "2026-04-08T05:49:14.278137+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=gemma426b_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "gemma-4-26b", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=gemma426b_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "df938a74", "short_cell_id": "9ee24e4e", "completed_at": "2026-04-08T05:44:38.602045+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=gemma426b_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "gemma-4-26b", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=gemma426b_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ee6e9adf", "short_cell_id": "9ee24e4e", "completed_at": "2026-04-08T05:48:14.993905+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "35048b14", "short_cell_id": "92c2221d", "completed_at": "2026-04-07T16:09:39.858933+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "85cfb3b7", "short_cell_id": "503191b4", "completed_at": "2026-04-07T06:40:52.932185+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6614890c", "short_cell_id": "503191b4", "completed_at": "2026-04-15T16:38:57.024106+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c530817e", "short_cell_id": "503191b4", "completed_at": "2026-04-07T07:00:02.695067+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5ea5d539", "short_cell_id": "9186d6b4", "completed_at": "2026-04-07T14:08:07.030553+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f2ff7829", "short_cell_id": "9186d6b4", "completed_at": "2026-04-07T14:11:06.590554+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6b848132", "short_cell_id": "9186d6b4", "completed_at": "2026-04-15T12:17:20.891422+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run4", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e047cf3a", "short_cell_id": "a04d517f", "completed_at": "2026-04-03T19:59:11.076296+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run5", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5ae88633", "short_cell_id": "a04d517f", "completed_at": "2026-04-03T19:59:32.351290+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run6", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1d08ee76", "short_cell_id": "a04d517f", "completed_at": "2026-04-03T19:59:55.659323+00:00"} @@ -29,6 +34,7 @@ {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "413c1f93", "short_cell_id": "23a09071", "completed_at": "2026-04-06T17:35:26.899056+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9a9774f0", "short_cell_id": "19154aeb", "completed_at": "2026-04-07T09:16:50.008872+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "4a154f54", "short_cell_id": "19154aeb", "completed_at": "2026-04-07T09:24:49.967659+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d072c92b", "short_cell_id": "19154aeb", "completed_at": "2026-04-15T18:24:55.173501+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "05601da1", "short_cell_id": "77325cdf", "completed_at": "2026-04-06T18:03:05.716164+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "a6d9fb9c", "short_cell_id": "ae538652", "completed_at": "2026-04-06T17:51:21.325858+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7c167ef9", "short_cell_id": "3c84c672", "completed_at": "2026-04-07T14:59:58.688411+00:00"} @@ -38,11 +44,11 @@ {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run5", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "586c6b0a", "short_cell_id": "65bee0d9", "completed_at": "2026-04-03T20:37:09.900301+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run6", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "71fa204f", "short_cell_id": "65bee0d9", "completed_at": "2026-04-03T20:35:10.729588+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=detailed_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=detailed_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "c151a356", "short_cell_id": "908ef15a", "completed_at": "2026-04-04T20:24:23.986627+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f89a8a70", "short_cell_id": "9ea013c2", "completed_at": "2026-04-07T16:25:43.057787+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run4", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off", "short_id": "b29d066e", "short_cell_id": "7e05a3fa", "completed_at": "2026-04-03T18:37:03.014208+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run5", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off", "short_id": "1e13c72f", "short_cell_id": "7e05a3fa", "completed_at": "2026-04-03T18:37:23.108082+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off_run6", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=off_twrite=off_web=off", "short_id": "56088123", "short_cell_id": "7e05a3fa", "completed_at": "2026-04-03T18:41:13.333121+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "1fdd595b", "short_cell_id": "c09eba14", "completed_at": "2026-04-04T20:17:47.627694+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f89a8a70", "short_cell_id": "9ea013c2", "completed_at": "2026-04-07T16:25:43.057787+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run4", "task": "tetris", "model": "opus-4.6", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bd51c309", "short_cell_id": "617518b5", "completed_at": "2026-04-05T21:43:50.904766+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run5", "task": "tetris", "model": "opus-4.6", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d184704b", "short_cell_id": "617518b5", "completed_at": "2026-04-05T21:45:00.368788+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run6", "task": "tetris", "model": "opus-4.6", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=opus46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "135b43a3", "short_cell_id": "617518b5", "completed_at": "2026-04-05T21:48:01.764611+00:00"} @@ -51,6 +57,7 @@ {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run5", "task": "tetris", "model": "sonnet-4.6", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f8a57948", "short_cell_id": "eec69acb", "completed_at": "2026-04-05T05:44:43.169610+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run6", "task": "tetris", "model": "sonnet-4.6", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=sonnet46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "69bb8919", "short_cell_id": "eec69acb", "completed_at": "2026-04-05T19:39:10.870002+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1f33a77b", "short_cell_id": "ed58978d", "completed_at": "2026-04-06T20:41:11.429747+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "006df88f", "short_cell_id": "ed58978d", "completed_at": "2026-04-15T20:09:11.562880+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f2b6194f", "short_cell_id": "ed58978d", "completed_at": "2026-04-06T20:45:51.496530+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ec163e63", "short_cell_id": "e8fb2da7", "completed_at": "2026-04-07T15:43:13.910256+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "38de2555", "short_cell_id": "e8fb2da7", "completed_at": "2026-04-07T15:40:04.606967+00:00"} @@ -123,29 +130,79 @@ {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "971a1a50", "short_cell_id": "6741744d", "completed_at": "2026-04-07T21:06:22.224492+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "53ca551d", "short_cell_id": "b61cccaa", "completed_at": "2026-04-07T21:28:18.769747+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "fa2674ac", "short_cell_id": "544657c2", "completed_at": "2026-04-07T09:30:26.934464+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1a707fda", "short_cell_id": "544657c2", "completed_at": "2026-04-15T18:45:50.998500+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "579bb01f", "short_cell_id": "544657c2", "completed_at": "2026-04-15T18:55:23.748804+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c22109f8", "short_cell_id": "0d2ad982", "completed_at": "2026-04-07T10:02:13.411054+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b29d8782", "short_cell_id": "0d2ad982", "completed_at": "2026-04-15T19:08:12.227637+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0172e311", "short_cell_id": "0d2ad982", "completed_at": "2026-04-15T19:18:50.830718+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "df766a22", "short_cell_id": "760f3512", "completed_at": "2026-04-15T16:31:42.707612+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "56afde62", "short_cell_id": "760f3512", "completed_at": "2026-04-07T06:34:27.157064+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9539a678", "short_cell_id": "760f3512", "completed_at": "2026-04-15T16:34:55.659718+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "08a7e577", "short_cell_id": "25aea78d", "completed_at": "2026-04-15T23:44:37.049047+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "72e3256f", "short_cell_id": "25aea78d", "completed_at": "2026-04-15T23:48:22.507198+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8170834b", "short_cell_id": "25aea78d", "completed_at": "2026-04-16T00:02:30.032611+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0048ecdc", "short_cell_id": "33751719", "completed_at": "2026-04-16T00:34:47.571996+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6a743388", "short_cell_id": "1e1c37e8", "completed_at": "2026-04-06T21:38:13.008032+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "af5e84fc", "short_cell_id": "1e1c37e8", "completed_at": "2026-04-06T21:53:59.145803+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2f761815", "short_cell_id": "1e1c37e8", "completed_at": "2026-04-06T21:50:33.427319+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7fc5c868", "short_cell_id": "7a585619", "completed_at": "2026-04-15T22:09:41.752028+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "725bc5af", "short_cell_id": "7a585619", "completed_at": "2026-04-15T22:20:15.081159+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e0237626", "short_cell_id": "bc8005ed", "completed_at": "2026-04-06T21:23:54.623418+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b02a62f0", "short_cell_id": "bc8005ed", "completed_at": "2026-04-15T20:58:48.324252+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d46e8439", "short_cell_id": "bc8005ed", "completed_at": "2026-04-15T21:10:04.001224+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ae68d5c1", "short_cell_id": "ae2b0831", "completed_at": "2026-04-15T17:36:09.940392+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "31a529dc", "short_cell_id": "ae2b0831", "completed_at": "2026-04-07T08:22:54.088254+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1d046ee9", "short_cell_id": "ae2b0831", "completed_at": "2026-04-15T17:41:54.955595+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "97dcc55e", "short_cell_id": "8205db2d", "completed_at": "2026-04-15T17:47:32.154216+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "fe0ccd52", "short_cell_id": "8205db2d", "completed_at": "2026-04-15T17:53:22.991216+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "65b5c05a", "short_cell_id": "8205db2d", "completed_at": "2026-04-15T18:14:21.652758+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "6a018f5e", "short_cell_id": "d5a5cfd4", "completed_at": "2026-04-07T09:00:35.267937+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "03271a40", "short_cell_id": "d5a5cfd4", "completed_at": "2026-04-15T18:18:39.968005+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "ed0b0147", "short_cell_id": "d5a5cfd4", "completed_at": "2026-04-07T09:22:23.004446+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "43bf214b", "short_cell_id": "c0a91942", "completed_at": "2026-04-15T16:51:22.477802+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "b1f67906", "short_cell_id": "c0a91942", "completed_at": "2026-04-15T16:58:51.414379+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "34c22060", "short_cell_id": "c0a91942", "completed_at": "2026-04-15T17:19:41.235594+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "f4d7e3a0", "short_cell_id": "d3be6bfd", "completed_at": "2026-04-15T17:24:48.390756+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "e8d32946", "short_cell_id": "d3be6bfd", "completed_at": "2026-04-07T08:08:09.733116+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "184f81dd", "short_cell_id": "d3be6bfd", "completed_at": "2026-04-15T17:28:38.931389+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "b025b603", "short_cell_id": "0733ce28", "completed_at": "2026-04-15T19:35:38.230225+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "76f89680", "short_cell_id": "0733ce28", "completed_at": "2026-04-15T19:39:47.933122+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "2e5ad7e5", "short_cell_id": "0733ce28", "completed_at": "2026-04-15T19:43:58.890768+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0a030357", "short_cell_id": "4e01e897", "completed_at": "2026-04-07T05:32:35.908202+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "101e6752", "short_cell_id": "6477596a", "completed_at": "2026-04-15T20:30:36.395332+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "626b3efd", "short_cell_id": "6477596a", "completed_at": "2026-04-15T20:41:30.606885+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0d5536fc", "short_cell_id": "6477596a", "completed_at": "2026-04-15T20:48:14.531225+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "60136e04", "short_cell_id": "f26b52d8", "completed_at": "2026-04-15T21:35:16.435812+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2e6a64f1", "short_cell_id": "f26b52d8", "completed_at": "2026-04-15T21:56:15.365359+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "750d7f27", "short_cell_id": "f26b52d8", "completed_at": "2026-04-15T22:01:14.345094+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "a41e7e52", "short_cell_id": "2095260c", "completed_at": "2026-04-16T00:07:54.266433+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "a23cb59b", "short_cell_id": "2095260c", "completed_at": "2026-04-16T00:28:32.698499+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9fed9f45", "short_cell_id": "2095260c", "completed_at": "2026-04-16T00:32:03.225999+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7c7dfa27", "short_cell_id": "421300b7", "completed_at": "2026-04-07T15:15:35.313053+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5afe9b8e", "short_cell_id": "421300b7", "completed_at": "2026-04-15T12:26:14.442886+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7e2cf342", "short_cell_id": "421300b7", "completed_at": "2026-04-07T15:06:43.419284+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "437b474b", "short_cell_id": "d2616211", "completed_at": "2026-04-14T11:47:59.923073+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c5ae5908", "short_cell_id": "d2616211", "completed_at": "2026-04-14T11:44:18.145049+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "98dee8cd", "short_cell_id": "d2616211", "completed_at": "2026-04-07T15:34:49.807548+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6abf96c7", "short_cell_id": "00c25732", "completed_at": "2026-04-07T14:08:59.313798+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8bcd3ae0", "short_cell_id": "00c25732", "completed_at": "2026-04-07T14:04:20.006080+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "496e0334", "short_cell_id": "00c25732", "completed_at": "2026-04-07T14:08:17.140903+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "30531578", "short_cell_id": "9e8c7e48", "completed_at": "2026-04-15T13:35:20.009435+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d8fc25ba", "short_cell_id": "9e8c7e48", "completed_at": "2026-04-15T13:39:55.396107+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "aa3d18d8", "short_cell_id": "9e8c7e48", "completed_at": "2026-04-15T13:40:11.251655+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "11b37482", "short_cell_id": "86ee3001", "completed_at": "2026-04-07T01:48:05.623201+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "63c0c2ab", "short_cell_id": "86ee3001", "completed_at": "2026-04-07T01:48:29.575707+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5da14018", "short_cell_id": "86ee3001", "completed_at": "2026-04-07T02:03:27.157428+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c2652712", "short_cell_id": "b76e8f59", "completed_at": "2026-04-15T12:41:32.160955+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "84fc4ae0", "short_cell_id": "759e378e", "completed_at": "2026-04-14T13:15:03.020242+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d8fe95e5", "short_cell_id": "759e378e", "completed_at": "2026-04-15T13:06:05.932668+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "62f7453c", "short_cell_id": "759e378e", "completed_at": "2026-04-14T13:26:07.423309+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b77a5e30", "short_cell_id": "97ed83b9", "completed_at": "2026-04-07T15:54:28.937589+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "03c54dda", "short_cell_id": "97ed83b9", "completed_at": "2026-04-14T12:18:29.701413+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "fa543cfc", "short_cell_id": "97ed83b9", "completed_at": "2026-04-14T12:18:27.096491+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "140cba7f", "short_cell_id": "9c9a14a9", "completed_at": "2026-04-07T14:39:03.652335+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "06c93bc4", "short_cell_id": "9c9a14a9", "completed_at": "2026-04-07T14:41:31.296419+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6a89452c", "short_cell_id": "9c9a14a9", "completed_at": "2026-04-15T12:21:07.641547+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5e2f9389", "short_cell_id": "58e6d7f7", "completed_at": "2026-04-07T14:44:47.368990+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6cf8d774", "short_cell_id": "58e6d7f7", "completed_at": "2026-04-07T14:45:56.819255+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "61f8b45c", "short_cell_id": "58e6d7f7", "completed_at": "2026-04-07T14:53:05.123017+00:00"} @@ -161,10 +218,27 @@ {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "05ad5c61", "short_cell_id": "dc986a52", "completed_at": "2026-04-07T15:34:14.091995+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "79bef8d0", "short_cell_id": "dc986a52", "completed_at": "2026-04-07T15:34:33.832723+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "bb3dc885", "short_cell_id": "dc986a52", "completed_at": "2026-04-07T15:38:03.755211+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "71d588fb", "short_cell_id": "28574c8b", "completed_at": "2026-04-14T11:07:13.191185+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "781c564b", "short_cell_id": "28574c8b", "completed_at": "2026-04-06T18:28:51.570857+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3e9975cb", "short_cell_id": "28574c8b", "completed_at": "2026-04-06T18:30:32.314734+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f8d9ace7", "short_cell_id": "7d3d74dc", "completed_at": "2026-04-14T17:15:40.023172+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2620a1cf", "short_cell_id": "7d3d74dc", "completed_at": "2026-04-14T12:09:17.110863+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0503113f", "short_cell_id": "7d3d74dc", "completed_at": "2026-04-07T16:00:59.931209+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "a4d1e302", "short_cell_id": "cb4390ae", "completed_at": "2026-04-15T13:12:18.643528+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2267b9f4", "short_cell_id": "cb4390ae", "completed_at": "2026-04-14T13:52:23.788816+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e3a6ea3c", "short_cell_id": "cb4390ae", "completed_at": "2026-04-14T14:05:46.340368+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bb361eb9", "short_cell_id": "41c9a1c4", "completed_at": "2026-04-14T14:01:43.491089+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "28bf03d9", "short_cell_id": "41c9a1c4", "completed_at": "2026-04-14T14:16:58.917378+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "63a42bc7", "short_cell_id": "41c9a1c4", "completed_at": "2026-04-14T14:16:28.662674+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ede08543", "short_cell_id": "93c78717", "completed_at": "2026-04-14T12:51:31.997491+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d65aa9f3", "short_cell_id": "93c78717", "completed_at": "2026-04-14T13:00:24.355516+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5514ba1d", "short_cell_id": "93c78717", "completed_at": "2026-04-14T13:12:43.404125+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f3626e24", "short_cell_id": "a4c12deb", "completed_at": "2026-04-15T13:50:05.391086+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5411d5ce", "short_cell_id": "a4c12deb", "completed_at": "2026-04-15T14:05:17.524141+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8cf0fbde", "short_cell_id": "a4c12deb", "completed_at": "2026-04-15T13:59:43.462584+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "16dab3d1", "short_cell_id": "cd8ad131", "completed_at": "2026-04-15T14:19:52.115903+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "14486646", "short_cell_id": "cd8ad131", "completed_at": "2026-04-07T02:19:50.929133+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "31d60e5a", "short_cell_id": "cd8ad131", "completed_at": "2026-04-15T14:26:18.058041+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=avail_prompt=detailed_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run4", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=avail_prompt=detailed_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "cbbff570", "short_cell_id": "c2189e69", "completed_at": "2026-04-03T19:53:09.020668+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=avail_prompt=detailed_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run5", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=avail_prompt=detailed_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "62c70152", "short_cell_id": "c2189e69", "completed_at": "2026-04-03T19:58:22.294680+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=avail_prompt=detailed_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run6", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=avail_prompt=detailed_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "80f1c3d5", "short_cell_id": "c2189e69", "completed_at": "2026-04-03T19:58:45.116530+00:00"} @@ -200,11 +274,11 @@ {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "030815a1", "short_cell_id": "ea092383", "completed_at": "2026-04-07T16:20:38.282019+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "7d789f16", "short_cell_id": "03b928b0", "completed_at": "2026-04-07T16:20:16.596068+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ddb0ec43", "short_cell_id": "d107279e", "completed_at": "2026-04-07T16:12:06.868178+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d09227cd", "short_cell_id": "88f325e6", "completed_at": "2026-04-07T16:38:52.675062+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d654ce03", "short_cell_id": "dd9b012b", "completed_at": "2026-04-07T16:40:25.650246+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run5", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "79675074", "short_cell_id": "25036421", "completed_at": "2026-04-06T14:25:53.194123+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run6", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c0d3fd49", "short_cell_id": "25036421", "completed_at": "2026-04-06T14:32:23.577315+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run7", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1fbd2965", "short_cell_id": "25036421", "completed_at": "2026-04-06T14:39:00.766938+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d09227cd", "short_cell_id": "88f325e6", "completed_at": "2026-04-07T16:38:52.675062+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d654ce03", "short_cell_id": "dd9b012b", "completed_at": "2026-04-07T16:40:25.650246+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run5", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c9b0a190", "short_cell_id": "5f9e5779", "completed_at": "2026-04-03T20:36:23.056914+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run6", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c31b514e", "short_cell_id": "5f9e5779", "completed_at": "2026-04-03T20:39:17.839627+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run7", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8de1a3c2", "short_cell_id": "5f9e5779", "completed_at": "2026-04-03T20:41:00.673494+00:00"} @@ -312,6 +386,7 @@ {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "179f583c", "short_cell_id": "1a05a1cb", "completed_at": "2026-04-07T16:29:35.587221+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ea686a12", "short_cell_id": "1a05a1cb", "completed_at": "2026-04-06T18:34:08.575979+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "fa02f9f7", "short_cell_id": "1a05a1cb", "completed_at": "2026-04-06T18:33:38.621190+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "586b5641", "short_cell_id": "c5dd26c2", "completed_at": "2026-04-15T16:45:38.388150+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7c1248e2", "short_cell_id": "c5dd26c2", "completed_at": "2026-04-07T07:31:19.574335+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c924670c", "short_cell_id": "c5dd26c2", "completed_at": "2026-04-07T07:32:19.471427+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "187c67ef", "short_cell_id": "c358a5f2", "completed_at": "2026-04-07T14:22:45.061262+00:00"} @@ -332,9 +407,16 @@ {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run5", "task": "tetris", "model": "sonnet-4.6", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "12f4a113", "short_cell_id": "19f28e41", "completed_at": "2026-04-04T21:53:14.676366+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run6", "task": "tetris", "model": "sonnet-4.6", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=sonnet46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6031abcf", "short_cell_id": "19f28e41", "completed_at": "2026-04-04T22:11:07.374754+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "fadc2681", "short_cell_id": "b038c034", "completed_at": "2026-04-07T21:02:44.852439+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "44bdca2e", "short_cell_id": "8710c3bf", "completed_at": "2026-04-14T18:47:55.704682+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "039adf80", "short_cell_id": "8710c3bf", "completed_at": "2026-04-15T13:29:01.895590+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b21b62e8", "short_cell_id": "8710c3bf", "completed_at": "2026-04-14T19:01:24.447453+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=gemma426b_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "gemma-4-26b", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=gemma426b_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "165fc6e4", "short_cell_id": "cf4b5fc7", "completed_at": "2026-04-08T05:28:42.131157+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=gemma426b_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "gemma-4-26b", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=gemma426b_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d2e96e2c", "short_cell_id": "cf4b5fc7", "completed_at": "2026-04-08T05:39:38.779236+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d179f825", "short_cell_id": "1fbc3a23", "completed_at": "2026-04-06T18:35:22.981284+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ef24fb84", "short_cell_id": "d333417b", "completed_at": "2026-04-15T15:41:30.985703+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1e9c0a3b", "short_cell_id": "d333417b", "completed_at": "2026-04-15T16:02:45.090813+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "76c2aa85", "short_cell_id": "d333417b", "completed_at": "2026-04-15T16:23:43.510515+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e128b57c", "short_cell_id": "67a470d0", "completed_at": "2026-04-15T12:04:17.924338+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "025bcc22", "short_cell_id": "67a470d0", "completed_at": "2026-04-07T13:49:13.014291+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "cd3f3c84", "short_cell_id": "67a470d0", "completed_at": "2026-04-07T13:49:24.635418+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run4", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7e61c670", "short_cell_id": "db24182c", "completed_at": "2026-04-03T19:50:12.863462+00:00"} @@ -348,9 +430,48 @@ {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run5", "task": "tetris", "model": "sonnet-4.6", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "20dc3752", "short_cell_id": "6ac26553", "completed_at": "2026-04-04T21:37:35.722817+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run6", "task": "tetris", "model": "sonnet-4.6", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=sonnet46_pw=avail_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "4905874d", "short_cell_id": "6ac26553", "completed_at": "2026-04-04T21:36:09.154037+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "20ecfcc4", "short_cell_id": "3832db77", "completed_at": "2026-04-07T20:40:44.887945+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "aff304c1", "short_cell_id": "927ab396", "completed_at": "2026-04-14T14:50:22.929810+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1005e419", "short_cell_id": "927ab396", "completed_at": "2026-04-14T18:02:01.314534+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "80b5cf08", "short_cell_id": "927ab396", "completed_at": "2026-04-14T14:58:49.341932+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=qwen36p_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "qwen-3.6-plus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=qwen36p_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "fb0c6aef", "short_cell_id": "a9986a6c", "completed_at": "2026-04-07T23:48:37.370470+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "a7393fb0", "short_cell_id": "a6a43d35", "completed_at": "2026-04-07T20:31:04.413327+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c0ca12f7", "short_cell_id": "290d5e90", "completed_at": "2026-04-14T17:57:53.292587+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ae8a9e3a", "short_cell_id": "290d5e90", "completed_at": "2026-04-15T13:27:22.757180+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3e78199f", "short_cell_id": "290d5e90", "completed_at": "2026-04-14T14:44:30.509397+00:00"} {"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=qwen36p_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "qwen-3.6-plus", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=qwen36p_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "602fba4b", "short_cell_id": "53fef114", "completed_at": "2026-04-07T23:35:06.565720+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f4281547", "short_cell_id": "9607ddcf", "completed_at": "2026-04-15T23:14:49.669859+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "083647f8", "short_cell_id": "9607ddcf", "completed_at": "2026-04-15T23:18:52.993840+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c8f6a35c", "short_cell_id": "9607ddcf", "completed_at": "2026-04-15T23:23:35.950999+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "32860f58", "short_cell_id": "169ba8fa", "completed_at": "2026-04-14T20:20:18.900460+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3813f826", "short_cell_id": "169ba8fa", "completed_at": "2026-04-14T20:29:11.476245+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "699cf77b", "short_cell_id": "169ba8fa", "completed_at": "2026-04-15T13:34:35.321122+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2ae87d54", "short_cell_id": "916716db", "completed_at": "2026-04-15T22:34:15.201534+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "64b059c8", "short_cell_id": "916716db", "completed_at": "2026-04-15T22:37:23.312589+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c273dfb3", "short_cell_id": "916716db", "completed_at": "2026-04-15T22:43:18.934638+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bc23f2b0", "short_cell_id": "bc69429e", "completed_at": "2026-04-14T19:51:15.045569+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1e9fac18", "short_cell_id": "bc69429e", "completed_at": "2026-04-14T19:57:07.185271+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0c02f27a", "short_cell_id": "bc69429e", "completed_at": "2026-04-14T20:02:06.713393+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b0889b2f", "short_cell_id": "6423abf6", "completed_at": "2026-04-14T19:47:04.450125+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3e650991", "short_cell_id": "6423abf6", "completed_at": "2026-04-14T19:46:52.059749+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "527ae718", "short_cell_id": "6423abf6", "completed_at": "2026-04-14T19:54:55.720434+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5759a070", "short_cell_id": "54058c6c", "completed_at": "2026-04-15T23:04:31.441908+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "71592253", "short_cell_id": "54058c6c", "completed_at": "2026-04-15T23:08:08.183867+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0cd7b5c0", "short_cell_id": "54058c6c", "completed_at": "2026-04-15T23:10:31.143739+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f0919def", "short_cell_id": "05eb7233", "completed_at": "2026-04-14T20:11:13.325369+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "374c9fe4", "short_cell_id": "05eb7233", "completed_at": "2026-04-14T20:11:20.574496+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "120783c1", "short_cell_id": "05eb7233", "completed_at": "2026-04-14T20:32:10.504434+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e12838e5", "short_cell_id": "96e82faf", "completed_at": "2026-04-14T19:31:48.605154+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "cac6bb65", "short_cell_id": "96e82faf", "completed_at": "2026-04-14T19:39:11.365973+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3a8321c5", "short_cell_id": "96e82faf", "completed_at": "2026-04-14T19:41:34.662220+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8b81a68b", "short_cell_id": "d2310ebd", "completed_at": "2026-04-14T19:13:36.184084+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bb9af51e", "short_cell_id": "d2310ebd", "completed_at": "2026-04-14T19:17:11.631772+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9bda026f", "short_cell_id": "d2310ebd", "completed_at": "2026-04-14T19:22:07.024967+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0f274b03", "short_cell_id": "ae0125a7", "completed_at": "2026-04-14T19:05:01.116848+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "485a520f", "short_cell_id": "ae0125a7", "completed_at": "2026-04-14T19:06:33.486663+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7a7443d8", "short_cell_id": "ae0125a7", "completed_at": "2026-04-14T19:11:25.768687+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0bde7ee4", "short_cell_id": "89541b58", "completed_at": "2026-04-14T19:25:05.464206+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3021ad25", "short_cell_id": "89541b58", "completed_at": "2026-04-14T19:26:08.287842+00:00"} +{"run_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f34781bd", "short_cell_id": "89541b58", "completed_at": "2026-04-14T19:29:44.709718+00:00"} {"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run4", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on", "short_id": "1e3f4cdb", "short_cell_id": "7a06a9c5", "completed_at": "2026-04-06T11:05:30.834325+00:00"} {"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run5", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on", "short_id": "c7b0bb6b", "short_cell_id": "7a06a9c5", "completed_at": "2026-04-06T11:05:09.726350+00:00"} {"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run6", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=haiku45_pw=avail_prompt=simple_prov=anth_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on", "short_id": "bbb70053", "short_cell_id": "7a06a9c5", "completed_at": "2026-04-06T11:09:25.622402+00:00"} @@ -361,6 +482,8 @@ {"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0f8c8b62", "short_cell_id": "f5072fb0", "completed_at": "2026-04-07T18:48:00.870407+00:00"} {"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b13700b7", "short_cell_id": "f5072fb0", "completed_at": "2026-04-06T18:41:35.644789+00:00"} {"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8d789027", "short_cell_id": "2b182faa", "completed_at": "2026-04-07T10:10:13.270815+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bb561270", "short_cell_id": "2b182faa", "completed_at": "2026-04-15T19:23:02.089069+00:00"} +{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "485c959f", "short_cell_id": "2b182faa", "completed_at": "2026-04-15T19:27:02.008158+00:00"} {"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7fc5f846", "short_cell_id": "92507609", "completed_at": "2026-04-07T15:22:25.669862+00:00"} {"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8d7679dc", "short_cell_id": "92507609", "completed_at": "2026-04-07T15:28:06.564974+00:00"} {"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8d96f61d", "short_cell_id": "92507609", "completed_at": "2026-04-07T15:32:26.960637+00:00"} @@ -381,218 +504,7 @@ {"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run5", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off", "short_id": "ccc32a02", "short_cell_id": "b0ec2d7c", "completed_at": "2026-04-06T11:06:57.859005+00:00"} {"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off_run6", "task": "tetris", "model": "haiku-4.5", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=high_model=haiku45_pw=off_prompt=simple_prov=anth_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=off_web=off", "short_id": "edcf7c7c", "short_cell_id": "b0ec2d7c", "completed_at": "2026-04-06T11:04:14.817177+00:00"} {"run_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.5-air", "cell_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm45air_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ec92f0b3", "short_cell_id": "5ba81d4a", "completed_at": "2026-04-07T20:37:00.799060+00:00"} -{"run_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=qwen36p_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "qwen-3.6-plus", "cell_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=qwen36p_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "eade1121", "short_cell_id": "43f63f08", "completed_at": "2026-04-07T23:57:16.612996+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5514ba1d", "short_cell_id": "93c78717", "completed_at": "2026-04-13T19:29:06.650685+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "84fc4ae0", "short_cell_id": "759e378e", "completed_at": "2026-04-13T19:32:32.754694+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "62f7453c", "short_cell_id": "759e378e", "completed_at": "2026-04-13T19:35:56.173733+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2267b9f4", "short_cell_id": "cb4390ae", "completed_at": "2026-04-13T19:39:17.036458+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e3a6ea3c", "short_cell_id": "cb4390ae", "completed_at": "2026-04-13T19:39:15.940402+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "28bf03d9", "short_cell_id": "41c9a1c4", "completed_at": "2026-04-13T19:42:45.713670+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bb361eb9", "short_cell_id": "41c9a1c4", "completed_at": "2026-04-13T19:42:47.858542+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c0ca12f7", "short_cell_id": "290d5e90", "completed_at": "2026-04-13T19:46:06.703120+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "63a42bc7", "short_cell_id": "41c9a1c4", "completed_at": "2026-04-13T19:46:06.625285+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3e78199f", "short_cell_id": "290d5e90", "completed_at": "2026-04-13T19:49:31.577848+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1005e419", "short_cell_id": "927ab396", "completed_at": "2026-04-13T19:52:47.695927+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "aff304c1", "short_cell_id": "927ab396", "completed_at": "2026-04-13T19:52:58.824092+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "80b5cf08", "short_cell_id": "927ab396", "completed_at": "2026-04-13T19:56:09.108934+00:00"} -{"run_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "100a4faf", "short_cell_id": "c5c25967", "completed_at": "2026-04-13T19:56:20.730792+00:00"} -{"run_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2ef3a411", "short_cell_id": "c5c25967", "completed_at": "2026-04-13T19:59:25.168475+00:00"} -{"run_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7ed01455", "short_cell_id": "c5c25967", "completed_at": "2026-04-13T19:59:43.296478+00:00"} -{"run_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3a4446e0", "short_cell_id": "d305e89b", "completed_at": "2026-04-13T20:02:53.361989+00:00"} -{"run_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e9675236", "short_cell_id": "d305e89b", "completed_at": "2026-04-13T20:02:59.673740+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "44bdca2e", "short_cell_id": "8710c3bf", "completed_at": "2026-04-13T20:06:19.559477+00:00"} -{"run_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "a6720fb3", "short_cell_id": "d305e89b", "completed_at": "2026-04-13T20:06:25.017501+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b21b62e8", "short_cell_id": "8710c3bf", "completed_at": "2026-04-13T20:09:55.958069+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "485a520f", "short_cell_id": "ae0125a7", "completed_at": "2026-04-13T20:39:29.925822+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7a7443d8", "short_cell_id": "ae0125a7", "completed_at": "2026-04-13T20:39:32.079253+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8b81a68b", "short_cell_id": "d2310ebd", "completed_at": "2026-04-13T20:39:36.796799+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0f274b03", "short_cell_id": "ae0125a7", "completed_at": "2026-04-13T20:39:39.048376+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9bda026f", "short_cell_id": "d2310ebd", "completed_at": "2026-04-13T20:42:49.585108+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3021ad25", "short_cell_id": "89541b58", "completed_at": "2026-04-13T20:42:51.893016+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0bde7ee4", "short_cell_id": "89541b58", "completed_at": "2026-04-13T20:42:53.950533+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bb9af51e", "short_cell_id": "d2310ebd", "completed_at": "2026-04-13T20:42:58.754299+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f34781bd", "short_cell_id": "89541b58", "completed_at": "2026-04-13T20:46:13.993708+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e12838e5", "short_cell_id": "96e82faf", "completed_at": "2026-04-13T20:46:17.848620+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "cac6bb65", "short_cell_id": "96e82faf", "completed_at": "2026-04-13T20:46:20.683583+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3a8321c5", "short_cell_id": "96e82faf", "completed_at": "2026-04-13T20:46:31.788138+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b0889b2f", "short_cell_id": "6423abf6", "completed_at": "2026-04-13T20:49:41.974999+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "527ae718", "short_cell_id": "6423abf6", "completed_at": "2026-04-13T20:49:44.528928+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3e650991", "short_cell_id": "6423abf6", "completed_at": "2026-04-13T20:49:45.532274+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bc23f2b0", "short_cell_id": "bc69429e", "completed_at": "2026-04-13T20:49:48.441041+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1e9fac18", "short_cell_id": "bc69429e", "completed_at": "2026-04-13T20:53:05.800134+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f0919def", "short_cell_id": "05eb7233", "completed_at": "2026-04-13T20:53:11.861132+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0c02f27a", "short_cell_id": "bc69429e", "completed_at": "2026-04-13T20:53:16.166445+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "374c9fe4", "short_cell_id": "05eb7233", "completed_at": "2026-04-13T20:53:17.273965+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "32860f58", "short_cell_id": "169ba8fa", "completed_at": "2026-04-13T20:56:32.948969+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "120783c1", "short_cell_id": "05eb7233", "completed_at": "2026-04-13T20:56:34.147103+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3813f826", "short_cell_id": "169ba8fa", "completed_at": "2026-04-13T20:56:49.141855+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5514ba1d", "short_cell_id": "93c78717", "completed_at": "2026-04-14T02:33:51.486064+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "84fc4ae0", "short_cell_id": "759e378e", "completed_at": "2026-04-14T02:37:12.393004+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "62f7453c", "short_cell_id": "759e378e", "completed_at": "2026-04-14T02:40:23.412105+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2267b9f4", "short_cell_id": "cb4390ae", "completed_at": "2026-04-14T02:43:40.425471+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e3a6ea3c", "short_cell_id": "cb4390ae", "completed_at": "2026-04-14T02:43:51.193316+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bb361eb9", "short_cell_id": "41c9a1c4", "completed_at": "2026-04-14T02:47:05.609486+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "28bf03d9", "short_cell_id": "41c9a1c4", "completed_at": "2026-04-14T02:47:13.139375+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "63a42bc7", "short_cell_id": "41c9a1c4", "completed_at": "2026-04-14T02:50:25.963238+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c0ca12f7", "short_cell_id": "290d5e90", "completed_at": "2026-04-14T02:50:26.349894+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3e78199f", "short_cell_id": "290d5e90", "completed_at": "2026-04-14T02:53:40.080187+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "aff304c1", "short_cell_id": "927ab396", "completed_at": "2026-04-14T02:56:51.540385+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1005e419", "short_cell_id": "927ab396", "completed_at": "2026-04-14T02:57:01.852149+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "80b5cf08", "short_cell_id": "927ab396", "completed_at": "2026-04-14T03:00:05.862085+00:00"} -{"run_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "100a4faf", "short_cell_id": "c5c25967", "completed_at": "2026-04-14T03:00:29.684886+00:00"} -{"run_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2ef3a411", "short_cell_id": "c5c25967", "completed_at": "2026-04-14T03:03:22.245675+00:00"} -{"run_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7ed01455", "short_cell_id": "c5c25967", "completed_at": "2026-04-14T03:03:51.064198+00:00"} -{"run_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3a4446e0", "short_cell_id": "d305e89b", "completed_at": "2026-04-14T03:06:36.191245+00:00"} -{"run_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e9675236", "short_cell_id": "d305e89b", "completed_at": "2026-04-14T03:07:05.950278+00:00"} -{"run_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "a6720fb3", "short_cell_id": "d305e89b", "completed_at": "2026-04-14T03:09:52.847960+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "44bdca2e", "short_cell_id": "8710c3bf", "completed_at": "2026-04-14T03:10:14.343592+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b21b62e8", "short_cell_id": "8710c3bf", "completed_at": "2026-04-14T03:13:34.881958+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0f274b03", "short_cell_id": "ae0125a7", "completed_at": "2026-04-14T03:16:35.971681+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "485a520f", "short_cell_id": "ae0125a7", "completed_at": "2026-04-14T03:17:07.700963+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7a7443d8", "short_cell_id": "ae0125a7", "completed_at": "2026-04-14T03:19:56.313309+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8b81a68b", "short_cell_id": "d2310ebd", "completed_at": "2026-04-14T03:20:24.251937+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bb9af51e", "short_cell_id": "d2310ebd", "completed_at": "2026-04-14T03:23:14.159665+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9bda026f", "short_cell_id": "d2310ebd", "completed_at": "2026-04-14T03:23:49.831152+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0bde7ee4", "short_cell_id": "89541b58", "completed_at": "2026-04-14T03:26:25.720927+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3021ad25", "short_cell_id": "89541b58", "completed_at": "2026-04-14T03:27:12.628832+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f34781bd", "short_cell_id": "89541b58", "completed_at": "2026-04-14T03:29:54.045059+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e12838e5", "short_cell_id": "96e82faf", "completed_at": "2026-04-14T03:30:31.965124+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "cac6bb65", "short_cell_id": "96e82faf", "completed_at": "2026-04-14T03:33:15.518292+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3a8321c5", "short_cell_id": "96e82faf", "completed_at": "2026-04-14T03:33:57.359808+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b0889b2f", "short_cell_id": "6423abf6", "completed_at": "2026-04-14T03:36:53.491335+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3e650991", "short_cell_id": "6423abf6", "completed_at": "2026-04-14T03:37:14.860668+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "527ae718", "short_cell_id": "6423abf6", "completed_at": "2026-04-14T03:40:19.327505+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bc23f2b0", "short_cell_id": "bc69429e", "completed_at": "2026-04-14T03:40:34.202830+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1e9fac18", "short_cell_id": "bc69429e", "completed_at": "2026-04-14T03:43:38.471506+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0c02f27a", "short_cell_id": "bc69429e", "completed_at": "2026-04-14T03:43:49.768225+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f0919def", "short_cell_id": "05eb7233", "completed_at": "2026-04-14T03:47:07.641759+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "374c9fe4", "short_cell_id": "05eb7233", "completed_at": "2026-04-14T03:47:14.104496+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "120783c1", "short_cell_id": "05eb7233", "completed_at": "2026-04-14T03:50:35.126223+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "32860f58", "short_cell_id": "169ba8fa", "completed_at": "2026-04-14T03:50:36.277870+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3813f826", "short_cell_id": "169ba8fa", "completed_at": "2026-04-14T03:54:04.671800+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "71d588fb", "short_cell_id": "28574c8b", "completed_at": "2026-04-14T11:07:13.191185+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c5ae5908", "short_cell_id": "d2616211", "completed_at": "2026-04-14T11:44:18.145049+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "437b474b", "short_cell_id": "d2616211", "completed_at": "2026-04-14T11:47:59.923073+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2620a1cf", "short_cell_id": "7d3d74dc", "completed_at": "2026-04-14T12:09:17.110863+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "03c54dda", "short_cell_id": "97ed83b9", "completed_at": "2026-04-14T12:18:29.701413+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "fa543cfc", "short_cell_id": "97ed83b9", "completed_at": "2026-04-14T12:18:27.096491+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ede08543", "short_cell_id": "93c78717", "completed_at": "2026-04-14T12:51:31.997491+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d65aa9f3", "short_cell_id": "93c78717", "completed_at": "2026-04-14T13:00:24.355516+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5514ba1d", "short_cell_id": "93c78717", "completed_at": "2026-04-14T13:12:43.404125+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "84fc4ae0", "short_cell_id": "759e378e", "completed_at": "2026-04-14T13:15:03.020242+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "62f7453c", "short_cell_id": "759e378e", "completed_at": "2026-04-14T13:26:07.423309+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2267b9f4", "short_cell_id": "cb4390ae", "completed_at": "2026-04-14T13:52:23.788816+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bb361eb9", "short_cell_id": "41c9a1c4", "completed_at": "2026-04-14T14:01:43.491089+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e3a6ea3c", "short_cell_id": "cb4390ae", "completed_at": "2026-04-14T14:05:46.340368+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "63a42bc7", "short_cell_id": "41c9a1c4", "completed_at": "2026-04-14T14:16:28.662674+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=split_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "28bf03d9", "short_cell_id": "41c9a1c4", "completed_at": "2026-04-14T14:16:58.917378+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3e78199f", "short_cell_id": "290d5e90", "completed_at": "2026-04-14T14:44:30.509397+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "aff304c1", "short_cell_id": "927ab396", "completed_at": "2026-04-14T14:50:22.929810+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "80b5cf08", "short_cell_id": "927ab396", "completed_at": "2026-04-14T14:58:49.341932+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f8d9ace7", "short_cell_id": "7d3d74dc", "completed_at": "2026-04-14T17:15:40.023172+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c0ca12f7", "short_cell_id": "290d5e90", "completed_at": "2026-04-14T17:57:53.292587+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=specific_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1005e419", "short_cell_id": "927ab396", "completed_at": "2026-04-14T18:02:01.314534+00:00"} {"run_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "100a4faf", "short_cell_id": "c5c25967", "completed_at": "2026-04-14T18:06:29.972149+00:00"} {"run_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2ef3a411", "short_cell_id": "c5c25967", "completed_at": "2026-04-14T18:06:28.610786+00:00"} {"run_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7ed01455", "short_cell_id": "c5c25967", "completed_at": "2026-04-14T18:12:55.472379+00:00"} -{"run_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3a4446e0", "short_cell_id": "d305e89b", "completed_at": "2026-04-14T18:15:30.333023+00:00"} -{"run_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e9675236", "short_cell_id": "d305e89b", "completed_at": "2026-04-14T18:33:54.509350+00:00"} -{"run_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=bp_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "a6720fb3", "short_cell_id": "d305e89b", "completed_at": "2026-04-14T18:35:22.187209+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "44bdca2e", "short_cell_id": "8710c3bf", "completed_at": "2026-04-14T18:47:55.704682+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b21b62e8", "short_cell_id": "8710c3bf", "completed_at": "2026-04-14T19:01:24.447453+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "485a520f", "short_cell_id": "ae0125a7", "completed_at": "2026-04-14T19:06:33.486663+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0f274b03", "short_cell_id": "ae0125a7", "completed_at": "2026-04-14T19:05:01.116848+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7a7443d8", "short_cell_id": "ae0125a7", "completed_at": "2026-04-14T19:11:25.768687+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bb9af51e", "short_cell_id": "d2310ebd", "completed_at": "2026-04-14T19:17:11.631772+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8b81a68b", "short_cell_id": "d2310ebd", "completed_at": "2026-04-14T19:13:36.184084+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9bda026f", "short_cell_id": "d2310ebd", "completed_at": "2026-04-14T19:22:07.024967+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0bde7ee4", "short_cell_id": "89541b58", "completed_at": "2026-04-14T19:25:05.464206+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3021ad25", "short_cell_id": "89541b58", "completed_at": "2026-04-14T19:26:08.287842+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f34781bd", "short_cell_id": "89541b58", "completed_at": "2026-04-14T19:29:44.709718+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e12838e5", "short_cell_id": "96e82faf", "completed_at": "2026-04-14T19:31:48.605154+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "cac6bb65", "short_cell_id": "96e82faf", "completed_at": "2026-04-14T19:39:11.365973+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=wiki100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3a8321c5", "short_cell_id": "96e82faf", "completed_at": "2026-04-14T19:41:34.662220+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b0889b2f", "short_cell_id": "6423abf6", "completed_at": "2026-04-14T19:47:04.450125+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3e650991", "short_cell_id": "6423abf6", "completed_at": "2026-04-14T19:46:52.059749+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bc23f2b0", "short_cell_id": "bc69429e", "completed_at": "2026-04-14T19:51:15.045569+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor1k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "527ae718", "short_cell_id": "6423abf6", "completed_at": "2026-04-14T19:54:55.720434+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1e9fac18", "short_cell_id": "bc69429e", "completed_at": "2026-04-14T19:57:07.185271+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0c02f27a", "short_cell_id": "bc69429e", "completed_at": "2026-04-14T20:02:06.713393+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f0919def", "short_cell_id": "05eb7233", "completed_at": "2026-04-14T20:11:13.325369+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "374c9fe4", "short_cell_id": "05eb7233", "completed_at": "2026-04-14T20:11:20.574496+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "32860f58", "short_cell_id": "169ba8fa", "completed_at": "2026-04-14T20:20:18.900460+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "3813f826", "short_cell_id": "169ba8fa", "completed_at": "2026-04-14T20:29:11.476245+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "120783c1", "short_cell_id": "05eb7233", "completed_at": "2026-04-14T20:32:10.504434+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "e128b57c", "short_cell_id": "67a470d0", "completed_at": "2026-04-15T12:04:17.924338+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6a89452c", "short_cell_id": "9c9a14a9", "completed_at": "2026-04-15T12:21:07.641547+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6b848132", "short_cell_id": "9186d6b4", "completed_at": "2026-04-15T12:17:20.891422+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5afe9b8e", "short_cell_id": "421300b7", "completed_at": "2026-04-15T12:26:14.442886+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=cv_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c2652712", "short_cell_id": "b76e8f59", "completed_at": "2026-04-15T12:41:32.160955+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d8fe95e5", "short_cell_id": "759e378e", "completed_at": "2026-04-15T13:06:05.932668+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=review_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "a4d1e302", "short_cell_id": "cb4390ae", "completed_at": "2026-04-15T13:12:18.643528+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=vague_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ae8a9e3a", "short_cell_id": "290d5e90", "completed_at": "2026-04-15T13:27:22.757180+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=sv_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "039adf80", "short_cell_id": "8710c3bf", "completed_at": "2026-04-15T13:29:01.895590+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "699cf77b", "short_cell_id": "169ba8fa", "completed_at": "2026-04-15T13:34:35.321122+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "30531578", "short_cell_id": "9e8c7e48", "completed_at": "2026-04-15T13:35:20.009435+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d8fc25ba", "short_cell_id": "9e8c7e48", "completed_at": "2026-04-15T13:39:55.396107+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "aa3d18d8", "short_cell_id": "9e8c7e48", "completed_at": "2026-04-15T13:40:11.251655+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f3626e24", "short_cell_id": "a4c12deb", "completed_at": "2026-04-15T13:50:05.391086+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8cf0fbde", "short_cell_id": "a4c12deb", "completed_at": "2026-04-15T13:59:43.462584+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5411d5ce", "short_cell_id": "a4c12deb", "completed_at": "2026-04-15T14:05:17.524141+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "16dab3d1", "short_cell_id": "cd8ad131", "completed_at": "2026-04-15T14:19:52.115903+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-5.1", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm51_pw=off_prompt=simple_prov=zai_rndr=webgl_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "31d60e5a", "short_cell_id": "cd8ad131", "completed_at": "2026-04-15T14:26:18.058041+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ef24fb84", "short_cell_id": "d333417b", "completed_at": "2026-04-15T15:41:30.985703+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1e9c0a3b", "short_cell_id": "d333417b", "completed_at": "2026-04-15T16:02:45.090813+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=max_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "76c2aa85", "short_cell_id": "d333417b", "completed_at": "2026-04-15T16:23:43.510515+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "df766a22", "short_cell_id": "760f3512", "completed_at": "2026-04-15T16:31:42.707612+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=detailed_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9539a678", "short_cell_id": "760f3512", "completed_at": "2026-04-15T16:34:55.659718+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "6614890c", "short_cell_id": "503191b4", "completed_at": "2026-04-15T16:38:57.024106+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=es_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "586b5641", "short_cell_id": "c5dd26c2", "completed_at": "2026-04-15T16:45:38.388150+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "43bf214b", "short_cell_id": "c0a91942", "completed_at": "2026-04-15T16:51:22.477802+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "b1f67906", "short_cell_id": "c0a91942", "completed_at": "2026-04-15T16:58:51.414379+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=off_twrite=on_web=on", "short_id": "34c22060", "short_cell_id": "c0a91942", "completed_at": "2026-04-15T17:19:41.235594+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "f4d7e3a0", "short_cell_id": "d3be6bfd", "completed_at": "2026-04-15T17:24:48.390756+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=off_web=on", "short_id": "184f81dd", "short_cell_id": "d3be6bfd", "completed_at": "2026-04-15T17:28:38.931389+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "ae68d5c1", "short_cell_id": "ae2b0831", "completed_at": "2026-04-15T17:36:09.940392+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1d046ee9", "short_cell_id": "ae2b0831", "completed_at": "2026-04-15T17:41:54.955595+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "97dcc55e", "short_cell_id": "8205db2d", "completed_at": "2026-04-15T17:47:32.154216+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "fe0ccd52", "short_cell_id": "8205db2d", "completed_at": "2026-04-15T17:53:22.991216+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on", "short_id": "65b5c05a", "short_cell_id": "8205db2d", "completed_at": "2026-04-15T18:14:21.652758+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=off_tread=on_twrite=on_web=on", "short_id": "03271a40", "short_cell_id": "d5a5cfd4", "completed_at": "2026-04-15T18:18:39.968005+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d072c92b", "short_cell_id": "19154aeb", "completed_at": "2026-04-15T18:24:55.173501+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "1a707fda", "short_cell_id": "544657c2", "completed_at": "2026-04-15T18:45:50.998500+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=avail_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "579bb01f", "short_cell_id": "544657c2", "completed_at": "2026-04-15T18:55:23.748804+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b29d8782", "short_cell_id": "0d2ad982", "completed_at": "2026-04-15T19:08:12.227637+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=inst_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0172e311", "short_cell_id": "0d2ad982", "completed_at": "2026-04-15T19:18:50.830718+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "bb561270", "short_cell_id": "2b182faa", "completed_at": "2026-04-15T19:23:02.089069+00:00"} -{"run_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=provided_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "485c959f", "short_cell_id": "2b182faa", "completed_at": "2026-04-15T19:27:02.008158+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "b025b603", "short_cell_id": "0733ce28", "completed_at": "2026-04-15T19:35:38.230225+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "76f89680", "short_cell_id": "0733ce28", "completed_at": "2026-04-15T19:39:47.933122+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=off", "short_id": "2e5ad7e5", "short_cell_id": "0733ce28", "completed_at": "2026-04-15T19:43:58.890768+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=high_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "006df88f", "short_cell_id": "ed58978d", "completed_at": "2026-04-15T20:09:11.562880+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "101e6752", "short_cell_id": "6477596a", "completed_at": "2026-04-15T20:30:36.395332+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "626b3efd", "short_cell_id": "6477596a", "completed_at": "2026-04-15T20:41:30.606885+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=plan_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0d5536fc", "short_cell_id": "6477596a", "completed_at": "2026-04-15T20:48:14.531225+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "b02a62f0", "short_cell_id": "bc8005ed", "completed_at": "2026-04-15T20:58:48.324252+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=iterate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "d46e8439", "short_cell_id": "bc8005ed", "completed_at": "2026-04-15T21:10:04.001224+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "60136e04", "short_cell_id": "f26b52d8", "completed_at": "2026-04-15T21:35:16.435812+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2e6a64f1", "short_cell_id": "f26b52d8", "completed_at": "2026-04-15T21:56:15.365359+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "750d7f27", "short_cell_id": "f26b52d8", "completed_at": "2026-04-15T22:01:14.345094+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "7fc5c868", "short_cell_id": "7a585619", "completed_at": "2026-04-15T22:09:41.752028+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=delegate_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "725bc5af", "short_cell_id": "7a585619", "completed_at": "2026-04-15T22:20:15.081159+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "2ae87d54", "short_cell_id": "916716db", "completed_at": "2026-04-15T22:34:15.201534+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "64b059c8", "short_cell_id": "916716db", "completed_at": "2026-04-15T22:37:23.312589+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor10k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c273dfb3", "short_cell_id": "916716db", "completed_at": "2026-04-15T22:43:18.934638+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "5759a070", "short_cell_id": "54058c6c", "completed_at": "2026-04-15T23:04:31.441908+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "71592253", "short_cell_id": "54058c6c", "completed_at": "2026-04-15T23:08:08.183867+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor50k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0cd7b5c0", "short_cell_id": "54058c6c", "completed_at": "2026-04-15T23:10:31.143739+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "f4281547", "short_cell_id": "9607ddcf", "completed_at": "2026-04-15T23:14:49.669859+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "083647f8", "short_cell_id": "9607ddcf", "completed_at": "2026-04-15T23:18:52.993840+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=lor100k_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "c8f6a35c", "short_cell_id": "9607ddcf", "completed_at": "2026-04-15T23:23:35.950999+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "08a7e577", "short_cell_id": "25aea78d", "completed_at": "2026-04-15T23:44:37.049047+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "72e3256f", "short_cell_id": "25aea78d", "completed_at": "2026-04-15T23:48:22.507198+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=canvas_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "8170834b", "short_cell_id": "25aea78d", "completed_at": "2026-04-16T00:02:30.032611+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "a41e7e52", "short_cell_id": "2095260c", "completed_at": "2026-04-16T00:07:54.266433+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "a23cb59b", "short_cell_id": "2095260c", "completed_at": "2026-04-16T00:28:32.698499+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=svg_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "9fed9f45", "short_cell_id": "2095260c", "completed_at": "2026-04-16T00:32:03.225999+00:00"} -{"run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "glm-4.7", "cell_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=glm47_pw=off_prompt=simple_prov=zai_rndr=dom_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "0048ecdc", "short_cell_id": "33751719", "completed_at": "2026-04-16T00:34:47.571996+00:00"} +{"run_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=qwen36p_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", "task": "tetris", "model": "qwen-3.6-plus", "cell_id": "tetris_arch=sep_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=on_budget=low_model=qwen36p_pw=off_prompt=simple_prov=or_rndr=none_strat=none_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on", "short_id": "eade1121", "short_cell_id": "43f63f08", "completed_at": "2026-04-07T23:57:16.612996+00:00"}

Impressum · Datenschutz