Run success rate

Run success rate

Tasks the run solved on its last attempt / tasks attempted in this run.

Formula: COUNT(distinct tasks where last attempt passed) / COUNT(distinct tasks attempted in this run)

Per-run metric for the model's "final answer" on each task. Differs from leaderboard pass_at_n: this denominator is the run's own attempted-task count, not the task set size, so partial runs are not penalised for unattempted tasks.

67.2% 43/64 of 64 tasks attempted in this run
Avg score

Avg attempt score

Mean per-attempt score on a 0–100 point scale (partial credit). Drill-down only.

Formula: Mean of attempt scores across all results rows: SUM(score) / COUNT(*) over the results table. Each attempt earns 0–100 points based on compile + test outcomes.

Drill-down companion to pass_at_n. Rewards partial credit but not directly comparable to pass rate; use for within-model analysis.

52.8 / 100
Cost $3.94
Duration 6h 58m
Filter:
Per-task results for run ab7b5438-b132-42f8-a6a4-e60ea3801047
TaskDifficultyAttemptScoreTestsCompileDuration
CG-AL-E001easy1100.0 / 1007/7OK3m 24s
CG-AL-E002easy1100.0 / 1006/6OK3m 37s
CG-AL-E003easy1100.0 / 1005/5OK2m 45s
CG-AL-E004easy2100.0 / 1006/6OK4m 32s
CG-AL-E005easy1100.0 / 10013/13OK4m 9s
CG-AL-E006easy2100.0 / 1007/7OK7m 11s
CG-AL-E007easy1100.0 / 1007/7OK4m 13s
CG-AL-E008easy2100.0 / 1006/6OK3m 56s
CG-AL-E009easy2100.0 / 1005/5OK4m 9s
CG-AL-E010easy1100.0 / 1005/5OK4m 53s
CG-AL-E031easy1100.0 / 1003/3OK5m 16s
CG-AL-E032easy2100.0 / 1001/1OK8m 0s
CG-AL-E045easy1100.0 / 1004/4OK3m 48s
CG-AL-E050easy20.0 / 1000/0FAIL2m 11s
CG-AL-E051easy2100.0 / 10015/15OK6m 13s
CG-AL-E052easy2100.0 / 10016/16OK4m 31s
CG-AL-E053easy1100.0 / 1003/3OK3m 42s
CG-AL-E054easy20.0 / 1000/0FAIL2m 45s
CG-AL-E055easy1100.0 / 1008/8OK3m 53s
CG-AL-H001easy1100.0 / 10025/25OK4m 33s
CG-AL-H002easy2100.0 / 1004/4OK3m 32s
CG-AL-H003easy1100.0 / 1005/5OK4m 35s
CG-AL-H004easy1100.0 / 10014/14OK4m 7s
CG-AL-H005easy262.5 / 1002/5OK6m 28s
CG-AL-H006easy1100.0 / 1006/6OK3m 52s
CG-AL-H007easy1100.0 / 10010/10OK5m 2s
CG-AL-H008easy1100.0 / 10010/10OK4m 32s
CG-AL-H009easy1100.0 / 10011/11OK5m 1s
CG-AL-H010easy1100.0 / 1008/8OK4m 16s
CG-AL-H011easy20.0 / 1000/0FAIL2m 27s
CG-AL-H013easy1100.0 / 1009/9OK4m 16s
CG-AL-H014easy20.0 / 1000/0FAIL29m 34s
CG-AL-H015easy1100.0 / 1004/4OK3m 54s
CG-AL-H016easy262.5 / 1003/4OK5m 57s
CG-AL-H017easy20.0 / 1000/0FAIL2m 11s
CG-AL-H018easy20.0 / 1000/0FAIL3m 3s
CG-AL-H019easy20.0 / 1000/0FAIL1m 46s
CG-AL-H020easy20.0 / 1000/0FAIL2m 17s
CG-AL-H021easy262.5 / 1006/20OK4m 46s
CG-AL-H022easy1100.0 / 10021/21OK5m 31s
CG-AL-H023easy20.0 / 1000/0FAIL6m 26s
CG-AL-H024easy2100.0 / 1009/9OK4m 46s
CG-AL-H025easy2100.0 / 1007/7OK4m 21s
CG-AL-H026easy1100.0 / 1008/8OK4m 36s
CG-AL-H205easy1100.0 / 1006/6OK5m 9s
CG-AL-M001easy262.5 / 1005/10OK5m 25s
CG-AL-M002easy1100.0 / 10022/22OK4m 18s
CG-AL-M003easy262.5 / 1003/9OK5m 42s
CG-AL-M004easy1100.0 / 10012/12OK5m 20s
CG-AL-M005easy20.0 / 1000/0FAIL3m 42s
CG-AL-M006easy2100.0 / 10018/18OK5m 23s
CG-AL-M007easy20.0 / 1000/0FAIL3m 15s
CG-AL-M008easy262.5 / 10011/12OK6m 5s
CG-AL-M009easy1100.0 / 10011/11OK6m 41s
CG-AL-M010easy262.5 / 10019/21OK6m 11s
CG-AL-M020easy20.0 / 1000/0FAIL3m 54s
CG-AL-M021easy20.0 / 1000/0FAIL3m 21s
CG-AL-M022easy2100.0 / 1009/9OK4m 26s
CG-AL-M023easy1100.0 / 10011/11OK5m 16s
CG-AL-M024easy1100.0 / 10010/10OK5m 58s
CG-AL-M025easy2100.0 / 1007/7OK3m 40s
CG-AL-M026easy1100.0 / 1008/8OK4m 13s
CG-AL-M088easy1100.0 / 1006/6OK4m 1s
CG-AL-M112easy262.5 / 1002/4OK4m 35s