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.

81.8% 90/110 of 110 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.

68.9 / 100
Cost $4.22
Duration 2h 6m
Filter:
Per-task results for run e5dcc595-a287-43b8-8191-f144e24b2a7b
TaskDifficultyAttemptScoreTestsCompileDuration
CG-AL-E001easy1100.0 / 1007/7OK20.8s
CG-AL-E002easy1100.0 / 1006/6OK2m 37s
CG-AL-E003easy1100.0 / 1005/5OK27.4s
CG-AL-E004easy2100.0 / 1006/6OK18.6s
CG-AL-E005easy2100.0 / 10013/13OK19.9s
CG-AL-E006easy1100.0 / 1007/7OK2m 55s
CG-AL-E007easy1100.0 / 1007/7OK49.1s
CG-AL-E008easy1100.0 / 1006/6OK53.8s
CG-AL-E009easy1100.0 / 1005/5OK59.3s
CG-AL-E010easy1100.0 / 1005/5OK1m 1s
CG-AL-E031easy1100.0 / 1003/3OK1m 4s
CG-AL-E032easy1100.0 / 1001/1OK10m 32s
CG-AL-E045easy1100.0 / 1004/4OK20.3s
CG-AL-E050easy2100.0 / 10013/13OK20.0s
CG-AL-E051easy1100.0 / 10015/15OK23.2s
CG-AL-E052easy2100.0 / 10016/16OK18.9s
CG-AL-E053easy1100.0 / 1003/3OK2m 43s
CG-AL-E054easy2100.0 / 1009/9OK20.4s
CG-AL-E055easy1100.0 / 1008/8OK18.7s
CG-AL-E056easy262.5 / 10013/15OK19.0s
CG-AL-E057easy20.0 / 1000/0FAIL10.7s
CG-AL-E058easy1100.0 / 1001/1OK16.7s
CG-AL-H001easy1100.0 / 10025/25OK18.8s
CG-AL-H002easy1100.0 / 1004/4OK22.5s
CG-AL-H003easy1100.0 / 1005/5OK24.4s
CG-AL-H004easy1100.0 / 10014/14OK21.2s
CG-AL-H005easy1100.0 / 1006/6OK24.2s
CG-AL-H006easy1100.0 / 1006/6OK19.2s
CG-AL-H007easy1100.0 / 10010/10OK23.6s
CG-AL-H008easy1100.0 / 10010/10OK30.2s
CG-AL-H009easy1100.0 / 10011/11OK26.0s
CG-AL-H010easy1100.0 / 1008/8OK21.3s
CG-AL-H011easy20.0 / 1000/0FAIL8.1s
CG-AL-H013easy1100.0 / 1009/9OK21.7s
CG-AL-H014easy20.0 / 1000/0FAIL11.7s
CG-AL-H015easy1100.0 / 1004/4OK18.8s
CG-AL-H016easy1100.0 / 1004/4OK19.0s
CG-AL-H017easy20.0 / 1000/0FAIL9.3s
CG-AL-H018easy1100.0 / 1006/6OK23.3s
CG-AL-H019easy1100.0 / 1005/5OK18.1s
CG-AL-H020easy2100.0 / 10010/10OK24.2s
CG-AL-H021easy2100.0 / 10020/20OK27.1s
CG-AL-H022easy1100.0 / 10021/21OK27.9s
CG-AL-H023easy20.0 / 1000/0FAIL2m 28s
CG-AL-H024easy1100.0 / 1009/9OK2m 11s
CG-AL-H025easy1100.0 / 1007/7OK21.1s
CG-AL-H026easy1100.0 / 1008/8OK20.6s
CG-AL-H027easy2100.0 / 1004/4OK21.8s
CG-AL-H028easy1100.0 / 1009/9OK30.5s
CG-AL-H029easy262.5 / 10016/18OK31.2s
CG-AL-H030easy262.5 / 1008/10OK29.9s
CG-AL-H031easy1100.0 / 10022/22OK32.3s
CG-AL-H032easy1100.0 / 10019/19OK31.7s
CG-AL-H033easy1100.0 / 1005/5OK3m 15s
CG-AL-H034easy2100.0 / 1003/3OK18.4s
CG-AL-H035easy1100.0 / 1003/3OK17.7s
CG-AL-H036easy20.0 / 1000/0FAIL9.2s
CG-AL-H037easy1100.0 / 1003/3OK19.1s
CG-AL-H038easy1100.0 / 1003/3OK19.0s
CG-AL-H039easy1100.0 / 1004/4OK21.2s
CG-AL-H040easy1100.0 / 1002/2OK19.7s
CG-AL-H041easy1100.0 / 1003/3OK21.3s
CG-AL-H042easy1100.0 / 1003/3OK18.7s
CG-AL-H043easy1100.0 / 1005/5OK17.0s
CG-AL-H050easy2100.0 / 1003/3OK18.9s
CG-AL-H051easy1100.0 / 1004/4OK19.3s
CG-AL-H052easy1100.0 / 1005/5OK17.9s
CG-AL-H053easy1100.0 / 1004/4OK19.0s
CG-AL-H054easy20.0 / 1000/0FAIL10.5s
CG-AL-H056easy20.0 / 1000/0FAIL7.8s
CG-AL-H057easy1100.0 / 1004/4OK2m 34s
CG-AL-H058easy1100.0 / 1005/5OK20.6s
CG-AL-H205easy1100.0 / 1006/6OK29.0s
CG-AL-M001easy20.0 / 1000/0FAIL11.9s
CG-AL-M002easy1100.0 / 10022/22OK28.5s
CG-AL-M003easy1100.0 / 1009/9OK27.4s
CG-AL-M004easy2100.0 / 10012/12OK2m 58s
CG-AL-M005easy1100.0 / 10022/22OK40.8s
CG-AL-M006easy1100.0 / 10018/18OK35.0s
CG-AL-M007easy20.0 / 1000/0FAIL27.1s
CG-AL-M008easy2100.0 / 10012/12OK1m 4s
CG-AL-M009easy1100.0 / 10011/11OK2m 9s
CG-AL-M010easy1100.0 / 10021/21OK5m 5s
CG-AL-M020easy2100.0 / 10017/17OK43.0s
CG-AL-M021easy2100.0 / 10011/11OK28.4s
CG-AL-M022easy1100.0 / 1009/9OK33.6s
CG-AL-M023easy262.5 / 10010/11OK24.0s
CG-AL-M024easy1100.0 / 10010/10OK27.4s
CG-AL-M025easy1100.0 / 1007/7OK20.5s
CG-AL-M026easy20.0 / 1000/0FAIL20.6s
CG-AL-M027easy2100.0 / 10018/18OK33.5s
CG-AL-M028easy20.0 / 1000/0FAIL11.7s
CG-AL-M029easy2100.0 / 1003/3OK2m 32s
CG-AL-M031easy20.0 / 1000/0FAIL15.1s
CG-AL-M032easy1100.0 / 1003/3OK18.2s
CG-AL-M033easy1100.0 / 1002/2OK20.8s
CG-AL-M034easy262.5 / 1000/2OK17.1s
CG-AL-M035easy1100.0 / 1002/2OK17.9s
CG-AL-M036easy1100.0 / 1002/2OK19.9s
CG-AL-M037easy20.0 / 1000/0FAIL9.5s
CG-AL-M038easy1100.0 / 1002/2OK19.2s
CG-AL-M039easy1100.0 / 1002/2OK2m 34s
CG-AL-M040easy20.0 / 1000/0FAIL9.8s
CG-AL-M041easy1100.0 / 1003/3OK17.5s
CG-AL-M042easy1100.0 / 1008/8OK20.4s
CG-AL-M043easy1100.0 / 1005/5OK20.7s
CG-AL-M044easy1100.0 / 1006/6OK2m 43s
CG-AL-M045easy1100.0 / 1006/6OK17.7s
CG-AL-M088easy1100.0 / 1006/6OK21.6s
CG-AL-M112easy1100.0 / 1004/4OK26.0s