loop-benchmarking

commit a8683609ce323889201069673c68c03616555eb6
parent da239183820ed8946e7f489fa3abfe7ff2513ba6
Author: Brian Graham <brian@buildingbetterteams.de>
Date:   Sun, 12 Apr 2026 18:23:03 +0200

Add 7 new games to calibration page

opus, qwen, glm-5.1, haiku, gemma-4-26b across various score ranges
(0-44%). Human tests unanswered, ready for testing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Diffstat:
A
tasks/tetris/eval/gameplay-bot/calibration/2763232d.json
 | 
36
++++++++++++++++++++++++++++++++++++
A
tasks/tetris/eval/gameplay-bot/calibration/5ae88633.json
 | 
36
++++++++++++++++++++++++++++++++++++
A
tasks/tetris/eval/gameplay-bot/calibration/6f157de1.json
 | 
36
++++++++++++++++++++++++++++++++++++
A
tasks/tetris/eval/gameplay-bot/calibration/7c167ef9.json
 | 
36
++++++++++++++++++++++++++++++++++++
A
tasks/tetris/eval/gameplay-bot/calibration/9b785a51.json
 | 
36
++++++++++++++++++++++++++++++++++++
A
tasks/tetris/eval/gameplay-bot/calibration/c1013100.json
 | 
36
++++++++++++++++++++++++++++++++++++
A
tasks/tetris/eval/gameplay-bot/calibration/e047cf3a.json
 | 
36
++++++++++++++++++++++++++++++++++++

7 files changed, 252 insertions(+), 0 deletions(-)
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/2763232d.json b/tasks/tetris/eval/gameplay-bot/calibration/2763232d.json
@@ -0,0 +1,35 @@
+{
+  "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_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",
+  "short_id": "2763232d",
+  "label": "Calibration (qwen-3.6-plus, en)",
+  "notes": "",
+  "human_tested_at": "",
+  "human_tests": {
+    "game_loads": null,
+    "game_starts": null,
+    "auto_drop": null,
+    "move_left": null,
+    "move_right": null,
+    "move_down": null,
+    "rotate": null,
+    "hard_drop": null,
+    "all_pieces_rotate": null,
+    "piece_locks": null,
+    "new_piece_spawns": null,
+    "multiple_pieces": null,
+    "line_clear": null,
+    "score_increases_on_clear": null,
+    "score_element_visible": null,
+    "game_over": null,
+    "playable_30s": null,
+    "multi_line_clear": null,
+    "score_scaling": null,
+    "level_progression": null,
+    "speed_progression": null,
+    "next_piece_preview": null,
+    "game_over_display": null,
+    "counter_clockwise_rotation": null,
+    "soft_drop_distinct": null,
+    "rendering_clean": null
+  }
+}
+\ No newline at end of file
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/5ae88633.json b/tasks/tetris/eval/gameplay-bot/calibration/5ae88633.json
@@ -0,0 +1,35 @@
+{
+  "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_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2",
+  "short_id": "5ae88633",
+  "label": "Calibration (haiku-4.5, en)",
+  "notes": "",
+  "human_tested_at": "",
+  "human_tests": {
+    "game_loads": null,
+    "game_starts": null,
+    "auto_drop": null,
+    "move_left": null,
+    "move_right": null,
+    "move_down": null,
+    "rotate": null,
+    "hard_drop": null,
+    "all_pieces_rotate": null,
+    "piece_locks": null,
+    "new_piece_spawns": null,
+    "multiple_pieces": null,
+    "line_clear": null,
+    "score_increases_on_clear": null,
+    "score_element_visible": null,
+    "game_over": null,
+    "playable_30s": null,
+    "multi_line_clear": null,
+    "score_scaling": null,
+    "level_progression": null,
+    "speed_progression": null,
+    "next_piece_preview": null,
+    "game_over_display": null,
+    "counter_clockwise_rotation": null,
+    "soft_drop_distinct": null,
+    "rendering_clean": null
+  }
+}
+\ No newline at end of file
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/6f157de1.json b/tasks/tetris/eval/gameplay-bot/calibration/6f157de1.json
@@ -0,0 +1,35 @@
+{
+  "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=js_lint=on_budget=low_model=opus46_pw=avail_prompt=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run3",
+  "short_id": "6f157de1",
+  "label": "Calibration (opus-4.6, en)",
+  "notes": "",
+  "human_tested_at": "",
+  "human_tests": {
+    "game_loads": null,
+    "game_starts": null,
+    "auto_drop": null,
+    "move_left": null,
+    "move_right": null,
+    "move_down": null,
+    "rotate": null,
+    "hard_drop": null,
+    "all_pieces_rotate": null,
+    "piece_locks": null,
+    "new_piece_spawns": null,
+    "multiple_pieces": null,
+    "line_clear": null,
+    "score_increases_on_clear": null,
+    "score_element_visible": null,
+    "game_over": null,
+    "playable_30s": null,
+    "multi_line_clear": null,
+    "score_scaling": null,
+    "level_progression": null,
+    "speed_progression": null,
+    "next_piece_preview": null,
+    "game_over_display": null,
+    "counter_clockwise_rotation": null,
+    "soft_drop_distinct": null,
+    "rendering_clean": null
+  }
+}
+\ No newline at end of file
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/7c167ef9.json b/tasks/tetris/eval/gameplay-bot/calibration/7c167ef9.json
@@ -0,0 +1,35 @@
+{
+  "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",
+  "short_id": "7c167ef9",
+  "label": "Calibration (glm-5.1, en)",
+  "notes": "",
+  "human_tested_at": "",
+  "human_tests": {
+    "game_loads": null,
+    "game_starts": null,
+    "auto_drop": null,
+    "move_left": null,
+    "move_right": null,
+    "move_down": null,
+    "rotate": null,
+    "hard_drop": null,
+    "all_pieces_rotate": null,
+    "piece_locks": null,
+    "new_piece_spawns": null,
+    "multiple_pieces": null,
+    "line_clear": null,
+    "score_increases_on_clear": null,
+    "score_element_visible": null,
+    "game_over": null,
+    "playable_30s": null,
+    "multi_line_clear": null,
+    "score_scaling": null,
+    "level_progression": null,
+    "speed_progression": null,
+    "next_piece_preview": null,
+    "game_over_display": null,
+    "counter_clockwise_rotation": null,
+    "soft_drop_distinct": null,
+    "rendering_clean": null
+  }
+}
+\ No newline at end of file
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/9b785a51.json b/tasks/tetris/eval/gameplay-bot/calibration/9b785a51.json
@@ -0,0 +1,35 @@
+{
+  "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_run3",
+  "short_id": "9b785a51",
+  "label": "Calibration (glm-5.1, en)",
+  "notes": "",
+  "human_tested_at": "",
+  "human_tests": {
+    "game_loads": null,
+    "game_starts": null,
+    "auto_drop": null,
+    "move_left": null,
+    "move_right": null,
+    "move_down": null,
+    "rotate": null,
+    "hard_drop": null,
+    "all_pieces_rotate": null,
+    "piece_locks": null,
+    "new_piece_spawns": null,
+    "multiple_pieces": null,
+    "line_clear": null,
+    "score_increases_on_clear": null,
+    "score_element_visible": null,
+    "game_over": null,
+    "playable_30s": null,
+    "multi_line_clear": null,
+    "score_scaling": null,
+    "level_progression": null,
+    "speed_progression": null,
+    "next_piece_preview": null,
+    "game_over_display": null,
+    "counter_clockwise_rotation": null,
+    "soft_drop_distinct": null,
+    "rendering_clean": null
+  }
+}
+\ No newline at end of file
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/c1013100.json b/tasks/tetris/eval/gameplay-bot/calibration/c1013100.json
@@ -0,0 +1,35 @@
+{
+  "run_id": "tetris_arch=none_ctx=none_noise=clean_dsgn=none_eff=high_echk=none_hlang=en_lang=ts_lint=off_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",
+  "short_id": "c1013100",
+  "label": "Calibration (gemma-4-26b, en)",
+  "notes": "",
+  "human_tested_at": "",
+  "human_tests": {
+    "game_loads": null,
+    "game_starts": null,
+    "auto_drop": null,
+    "move_left": null,
+    "move_right": null,
+    "move_down": null,
+    "rotate": null,
+    "hard_drop": null,
+    "all_pieces_rotate": null,
+    "piece_locks": null,
+    "new_piece_spawns": null,
+    "multiple_pieces": null,
+    "line_clear": null,
+    "score_increases_on_clear": null,
+    "score_element_visible": null,
+    "game_over": null,
+    "playable_30s": null,
+    "multi_line_clear": null,
+    "score_scaling": null,
+    "level_progression": null,
+    "speed_progression": null,
+    "next_piece_preview": null,
+    "game_over_display": null,
+    "counter_clockwise_rotation": null,
+    "soft_drop_distinct": null,
+    "rendering_clean": null
+  }
+}
+\ No newline at end of file
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/e047cf3a.json b/tasks/tetris/eval/gameplay-bot/calibration/e047cf3a.json
@@ -0,0 +1,35 @@
+{
+  "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_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1",
+  "short_id": "e047cf3a",
+  "label": "Calibration (haiku-4.5, en)",
+  "notes": "",
+  "human_tested_at": "",
+  "human_tests": {
+    "game_loads": null,
+    "game_starts": null,
+    "auto_drop": null,
+    "move_left": null,
+    "move_right": null,
+    "move_down": null,
+    "rotate": null,
+    "hard_drop": null,
+    "all_pieces_rotate": null,
+    "piece_locks": null,
+    "new_piece_spawns": null,
+    "multiple_pieces": null,
+    "line_clear": null,
+    "score_increases_on_clear": null,
+    "score_element_visible": null,
+    "game_over": null,
+    "playable_30s": null,
+    "multi_line_clear": null,
+    "score_scaling": null,
+    "level_progression": null,
+    "speed_progression": null,
+    "next_piece_preview": null,
+    "game_over_display": null,
+    "counter_clockwise_rotation": null,
+    "soft_drop_distinct": null,
+    "rendering_clean": null
+  }
+}
+\ No newline at end of file