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 7ec3ff4435d0c822bb73dc7b4689cc4908ca9883
parent 4bffa2cd4b2213f424528e1cc00cecce1fcd1a8e
Author: Brian Graham <brian@buildingbetterteams.de>
Date:   Thu,  9 Apr 2026 11:10:57 +0200

Add all 10 DOM games to calibration page

5 new entries (human tests unanswered, ready for testing).
5 existing entries already have human test data.

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

Diffstat:
Atasks/tetris/eval/gameplay-bot/calibration/1d08ee76.json | 34++++++++++++++++++++++++++++++++++
Atasks/tetris/eval/gameplay-bot/calibration/4949d521.json | 34++++++++++++++++++++++++++++++++++
Atasks/tetris/eval/gameplay-bot/calibration/9805c24a.json | 34++++++++++++++++++++++++++++++++++
Atasks/tetris/eval/gameplay-bot/calibration/bbb70053.json | 34++++++++++++++++++++++++++++++++++
Atasks/tetris/eval/gameplay-bot/calibration/cbbff570.json | 34++++++++++++++++++++++++++++++++++
5 files changed, 170 insertions(+), 0 deletions(-)

diff --git a/tasks/tetris/eval/gameplay-bot/calibration/1d08ee76.json b/tasks/tetris/eval/gameplay-bot/calibration/1d08ee76.json @@ -0,0 +1,33 @@ +{ + "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_run3", + "short_id": "1d08ee76", + "label": "DOM game (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_changes": 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 + } +} +\ No newline at end of file diff --git a/tasks/tetris/eval/gameplay-bot/calibration/4949d521.json b/tasks/tetris/eval/gameplay-bot/calibration/4949d521.json @@ -0,0 +1,33 @@ +{ + "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=simple_rndr=none_strat=usub_tst=none_tedit=on_tglob=off_tgrep=on_tread=on_twrite=on_web=on_run1", + "short_id": "4949d521", + "label": "DOM game (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_changes": 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 + } +} +\ No newline at end of file diff --git a/tasks/tetris/eval/gameplay-bot/calibration/9805c24a.json b/tasks/tetris/eval/gameplay-bot/calibration/9805c24a.json @@ -0,0 +1,33 @@ +{ + "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=simple_rndr=none_strat=usub_tst=none_tedit=off_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run2", + "short_id": "9805c24a", + "label": "DOM game (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_changes": 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 + } +} +\ No newline at end of file diff --git a/tasks/tetris/eval/gameplay-bot/calibration/bbb70053.json b/tasks/tetris/eval/gameplay-bot/calibration/bbb70053.json @@ -0,0 +1,33 @@ +{ + "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": "", + "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_changes": 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 + } +} +\ No newline at end of file diff --git a/tasks/tetris/eval/gameplay-bot/calibration/cbbff570.json b/tasks/tetris/eval/gameplay-bot/calibration/cbbff570.json @@ -0,0 +1,33 @@ +{ + "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_rndr=none_strat=usub_tst=none_tedit=on_tglob=on_tgrep=on_tread=on_twrite=on_web=on_run1", + "short_id": "cbbff570", + "label": "DOM game (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_changes": 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 + } +} +\ No newline at end of file

Impressum · Datenschutz