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.

76.6% 49/64 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.

66.3 / 100
Cost $2.28
Duration 3h 12m
Filter:
Per-task results for run 75466b2c-00f2-4ba5-b7f9-e48607416da8
TaskDifficultyAttemptScoreTestsCompileDuration
CG-AL-E001easy1100.0 / 1007/7OK2m 45s
CG-AL-E002easy1100.0 / 1006/6OK2m 45s
CG-AL-E003easy1100.0 / 1005/5OK3m 2s
CG-AL-E004easy1100.0 / 1006/6OK2m 50s
CG-AL-E005easy1100.0 / 10013/13OK2m 55s
CG-AL-E006easy1100.0 / 1007/7OK3m 12s
CG-AL-E007easy1100.0 / 1007/7OK3m 7s
CG-AL-E008easy1100.0 / 1006/6OK3m 9s
CG-AL-E009easy1100.0 / 1005/5OK3m 15s
CG-AL-E010easy20.0 / 1000/0FAIL9.5s
CG-AL-E031easy1100.0 / 1003/3OK3m 26s
CG-AL-E032easy1100.0 / 1001/1OK3m 30s
CG-AL-E045easy1100.0 / 1004/4OK2m 34s
CG-AL-E050easy2100.0 / 10013/13OK2m 42s
CG-AL-E051easy1100.0 / 10015/15OK2m 43s
CG-AL-E052easy2100.0 / 10016/16OK2m 35s
CG-AL-E053easy1100.0 / 1003/3OK2m 35s
CG-AL-E054easy20.0 / 1000/0FAIL15.6s
CG-AL-E055easy1100.0 / 1008/8OK2m 39s
CG-AL-H001easy1100.0 / 10025/25OK2m 35s
CG-AL-H002easy1100.0 / 1004/4OK2m 37s
CG-AL-H003easy1100.0 / 1005/5OK2m 39s
CG-AL-H004easy1100.0 / 10014/14OK2m 36s
CG-AL-H005easy20.0 / 1000/0FAIL24.9s
CG-AL-H006easy1100.0 / 1006/6OK2m 32s
CG-AL-H007easy1100.0 / 10010/10OK2m 35s
CG-AL-H008easy1100.0 / 10010/10OK2m 33s
CG-AL-H009easy1100.0 / 10011/11OK2m 38s
CG-AL-H010easy1100.0 / 1008/8OK2m 34s
CG-AL-H011easy2100.0 / 1005/5OK2m 35s
CG-AL-H013easy1100.0 / 1009/9OK2m 34s
CG-AL-H014easy2100.0 / 1007/7OK2m 44s
CG-AL-H015easy1100.0 / 1004/4OK2m 32s
CG-AL-H016easy262.5 / 1003/4OK2m 27s
CG-AL-H017easy2100.0 / 1003/3OK2m 27s
CG-AL-H018easy1100.0 / 1006/6OK2m 31s
CG-AL-H019easy1100.0 / 1005/5OK2m 24s
CG-AL-H020easy2100.0 / 10010/10OK2m 31s
CG-AL-H021easy262.5 / 1006/20OK2m 30s
CG-AL-H022easy2100.0 / 10021/21OK2m 36s
CG-AL-H023easy20.0 / 1000/0FAIL2m 32s
CG-AL-H024easy1100.0 / 1009/9OK2m 41s
CG-AL-H025easy1100.0 / 1007/7OK2m 35s
CG-AL-H026easy1100.0 / 1008/8OK2m 38s
CG-AL-H205easy1100.0 / 1006/6OK2m 25s
CG-AL-M001easy262.5 / 1005/10OK2m 31s
CG-AL-M002easy1100.0 / 10022/22OK2m 28s
CG-AL-M003easy262.5 / 1008/9OK2m 32s
CG-AL-M004easy1100.0 / 10012/12OK2m 42s
CG-AL-M005easy20.0 / 1000/0FAIL29.0s
CG-AL-M006easy262.5 / 10017/18OK2m 36s
CG-AL-M007easy20.0 / 1000/0FAIL1m 9s
CG-AL-M008easy20.0 / 1000/0FAIL2m 58s
CG-AL-M009easy2100.0 / 10011/11OK2m 50s
CG-AL-M010easy262.5 / 10019/21OK2m 51s
CG-AL-M020easy2100.0 / 10017/17OK2m 42s
CG-AL-M021easy2100.0 / 10011/11OK2m 28s
CG-AL-M022easy1100.0 / 1009/9OK2m 33s
CG-AL-M023easy1100.0 / 10011/11OK2m 25s
CG-AL-M024easy1100.0 / 10010/10OK2m 31s
CG-AL-M025easy262.5 / 1000/0OK2m 22s
CG-AL-M026easy1100.0 / 1008/8OK2m 27s
CG-AL-M088easy1100.0 / 1006/6OK2m 28s
CG-AL-M112easy262.5 / 1002/4OK2m 21s