loop-benchmarking

commit fd8274318dc475fe75d10c9b588c4af38d451c91
parent 711df365354d81be00d01bce2428e7c283e0ec2b
Author: Brian Graham <brian@buildingbetterteams.de>
Date:   Thu, 16 Apr 2026 12:10:23 +0200

Add human labels for 3 more calibration runs

bbb70053 (haiku-4.5 DOM) flagged as very laggy -- playable but the
lag hurts playability. c1013100 (gemma-4-26b) fails to load.
e047cf3a (haiku-4.5) plays fully.

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

Diffstat:
M
tasks/tetris/eval/gameplay-bot/calibration/bbb70053.json
 | 
39
+++++++++++++++++++--------------------
M
tasks/tetris/eval/gameplay-bot/calibration/c1013100.json
 | 
9
++++-----
M
tasks/tetris/eval/gameplay-bot/calibration/e047cf3a.json
 | 
40
++++++++++++++++++++--------------------

3 files changed, 43 insertions(+), 45 deletions(-)
diff --git a/tasks/tetris/eval/gameplay-bot/calibration/bbb70053.json b/tasks/tetris/eval/gameplay-bot/calibration/bbb70053.json
@@ -2,33 +2,33 @@
   "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_rndr=none_strat=none_tst=none_tedit=off_tglob=off_tgrep=off_tread=on_twrite=off_web=on_run3",
   "short_id": "bbb70053",
   "label": "DOM game (haiku-4.5, en)",
-  "notes": "",
-  "human_tested_at": "",
+  "notes": "Very laggy; hurts playability even though it is playable.",
+  "human_tested_at": "2026-04-16",
   "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,
+    "game_loads": true,
+    "game_starts": true,
+    "auto_drop": true,
+    "move_left": true,
+    "move_right": true,
+    "move_down": true,
+    "rotate": true,
+    "hard_drop": true,
     "all_pieces_rotate": null,
-    "piece_locks": null,
-    "new_piece_spawns": null,
-    "multiple_pieces": null,
-    "line_clear": null,
+    "piece_locks": true,
+    "new_piece_spawns": true,
+    "multiple_pieces": true,
+    "line_clear": true,
     "score_increases_on_clear": null,
     "score_element_visible": null,
-    "game_over": null,
-    "playable_30s": null,
+    "game_over": true,
+    "playable_30s": true,
     "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,
+    "game_over_display": true,
+    "counter_clockwise_rotation": true,
     "soft_drop_distinct": 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
@@ -3,10 +3,10 @@
   "short_id": "c1013100",
   "label": "Calibration (gemma-4-26b, en)",
   "notes": "",
-  "human_tested_at": "",
+  "human_tested_at": "2026-04-16",
   "human_tests": {
-    "game_loads": null,
-    "game_starts": null,
+    "game_loads": false,
+    "game_starts": false,
     "auto_drop": null,
     "move_left": null,
     "move_right": null,
@@ -32,4 +32,4 @@
     "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
@@ -3,33 +3,34 @@
   "short_id": "e047cf3a",
   "label": "Calibration (haiku-4.5, en)",
   "notes": "",
-  "human_tested_at": "",
+  "human_tested_at": "2026-04-16",
   "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,
+    "game_loads": true,
+    "game_starts": true,
+    "auto_drop": true,
+    "move_left": true,
+    "move_right": true,
+    "move_down": true,
+    "rotate": true,
+    "hard_drop": true,
+    "all_pieces_rotate": true,
+    "piece_locks": true,
+    "new_piece_spawns": true,
     "multiple_pieces": null,
-    "line_clear": null,
+    "line_clear": true,
     "score_increases_on_clear": null,
     "score_element_visible": null,
-    "game_over": null,
-    "playable_30s": null,
+    "game_over": true,
+    "playable_30s": true,
     "multi_line_clear": null,
     "score_scaling": null,
     "level_progression": null,
     "speed_progression": null,
-    "next_piece_preview": null,
-    "game_over_display": null,
+    "next_piece_preview": true,
+    "game_over_display": true,
     "counter_clockwise_rotation": null,
     "soft_drop_distinct": null,
-    "rendering_clean": null
+    "rendering_clean": null,
+    "score_changes": true
   }
-}
-\ No newline at end of file
+}