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.

91.8% 101/110 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.

81.4 / 100
Cost $12.37
Duration 1h 18m
Filter:
Per-task results for run 021a60c0-85d1-4ce5-ab68-16f1fa1dd475
TaskDifficultyAttemptScoreTestsCompileDuration
CG-AL-E001easy1100.0 / 1007/7OK37.8s
CG-AL-E002easy1100.0 / 1006/6OK33.7s
CG-AL-E003easy1100.0 / 1005/5OK41.5s
CG-AL-E004easy1100.0 / 1006/6OK43.8s
CG-AL-E005easy1100.0 / 10013/13OK48.2s
CG-AL-E006easy1100.0 / 1007/7OK1m 5s
CG-AL-E007easy1100.0 / 1007/7OK38.7s
CG-AL-E008easy1100.0 / 1006/6OK24.3s
CG-AL-E009easy1100.0 / 1005/5OK20.7s
CG-AL-E010easy1100.0 / 1005/5OK18.4s
CG-AL-E031easy1100.0 / 1003/3OK19.3s
CG-AL-E032easy1100.0 / 1001/1OK21.3s
CG-AL-E045easy1100.0 / 1004/4OK19.1s
CG-AL-E050easy1100.0 / 10013/13OK28.2s
CG-AL-E051easy1100.0 / 10015/15OK36.2s
CG-AL-E052easy2100.0 / 10016/16OK19.8s
CG-AL-E053easy1100.0 / 1003/3OK53.4s
CG-AL-E054easy2100.0 / 1009/9OK21.8s
CG-AL-E055easy1100.0 / 1008/8OK19.2s
CG-AL-E056easy2100.0 / 10015/15OK22.8s
CG-AL-E057easy2100.0 / 1008/8OK37.3s
CG-AL-E058easy1100.0 / 1001/1OK17.3s
CG-AL-H001hard1100.0 / 10025/25OK18.4s
CG-AL-H002hard1100.0 / 1004/4OK21.4s
CG-AL-H003hard1100.0 / 1005/5OK23.3s
CG-AL-H004hard1100.0 / 10014/14OK19.2s
CG-AL-H005hard1100.0 / 1006/6OK22.8s
CG-AL-H006hard1100.0 / 1006/6OK17.7s
CG-AL-H007hard1100.0 / 10010/10OK27.7s
CG-AL-H008hard1100.0 / 10010/10OK19.8s
CG-AL-H009hard1100.0 / 10011/11OK21.9s
CG-AL-H010hard1100.0 / 1008/8OK19.2s
CG-AL-H011hard1100.0 / 1005/5OK19.2s
CG-AL-H013hard1100.0 / 1009/9OK25.7s
CG-AL-H014hard2100.0 / 1007/7OK22.9s
CG-AL-H015hard1100.0 / 1004/4OK17.9s
CG-AL-H016hard1100.0 / 1004/4OK22.0s
CG-AL-H017hard1100.0 / 1003/3OK27.9s
CG-AL-H018hard1100.0 / 1006/6OK30.5s
CG-AL-H019hard1100.0 / 1005/5OK20.4s
CG-AL-H020hard1100.0 / 10010/10OK24.4s
CG-AL-H021hard2100.0 / 10020/20OK29.0s
CG-AL-H022hard1100.0 / 10021/21OK30.4s
CG-AL-H023hard20.0 / 1000/0FAIL2m 45s
CG-AL-H024hard1100.0 / 1009/9OK23.9s
CG-AL-H025hard1100.0 / 1007/7OK19.0s
CG-AL-H026hard1100.0 / 1008/8OK19.8s
CG-AL-H027hard1100.0 / 1004/4OK24.6s
CG-AL-H028hard1100.0 / 1009/9OK21.0s
CG-AL-H029hard1100.0 / 10018/18OK44.4s
CG-AL-H030hard1100.0 / 10010/10OK28.6s
CG-AL-H031hard1100.0 / 10022/22OK37.5s
CG-AL-H032hard1100.0 / 10019/19OK36.1s
CG-AL-H033hard1100.0 / 1005/5OK49.7s
CG-AL-H034hard1100.0 / 1003/3OK23.2s
CG-AL-H035hard1100.0 / 1003/3OK23.6s
CG-AL-H036hard1100.0 / 1005/5OK35.9s
CG-AL-H037hard1100.0 / 1003/3OK22.0s
CG-AL-H038hard1100.0 / 1003/3OK22.2s
CG-AL-H039hard1100.0 / 1004/4OK18.3s
CG-AL-H040hard1100.0 / 1002/2OK18.5s
CG-AL-H041hard1100.0 / 1003/3OK25.9s
CG-AL-H042hard1100.0 / 1003/3OK20.6s
CG-AL-H043hard1100.0 / 1005/5OK23.7s
CG-AL-H050hard1100.0 / 1003/3OK27.3s
CG-AL-H051hard1100.0 / 1004/4OK18.1s
CG-AL-H052hard1100.0 / 1005/5OK16.6s
CG-AL-H053hard1100.0 / 1004/4OK18.8s
CG-AL-H054hard2100.0 / 1005/5OK20.1s
CG-AL-H056hard2100.0 / 1004/4OK22.8s
CG-AL-H057hard1100.0 / 1004/4OK31.3s
CG-AL-H058hard1100.0 / 1005/5OK25.1s
CG-AL-H205hard1100.0 / 1006/6OK21.3s
CG-AL-M001medium20.0 / 1000/0FAIL25.4s
CG-AL-M002medium1100.0 / 10022/22OK22.8s
CG-AL-M003medium1100.0 / 1009/9OK29.5s
CG-AL-M004medium1100.0 / 10012/12OK1m 13s
CG-AL-M005medium1100.0 / 10022/22OK56.0s
CG-AL-M006medium2100.0 / 10018/18OK32.7s
CG-AL-M007medium20.0 / 1000/0FAIL2m 28s
CG-AL-M008medium20.0 / 1000/0FAIL2m 53s
CG-AL-M009medium20.0 / 1000/0FAIL1m 30s
CG-AL-M010medium1100.0 / 10021/21OK2m 6s
CG-AL-M020medium1100.0 / 10017/17OK1m 40s
CG-AL-M021medium1100.0 / 10011/11OK52.7s
CG-AL-M022medium1100.0 / 1009/9OK52.5s
CG-AL-M023medium262.5 / 10010/11OK44.3s
CG-AL-M024medium1100.0 / 10010/10OK26.3s
CG-AL-M025medium1100.0 / 1007/7OK35.4s
CG-AL-M026medium1100.0 / 1008/8OK36.7s
CG-AL-M027medium1100.0 / 10018/18OK32.4s
CG-AL-M028medium2100.0 / 1003/3OK30.9s
CG-AL-M029medium2100.0 / 1003/3OK40.7s
CG-AL-M031medium2100.0 / 1002/2OK25.2s
CG-AL-M032medium1100.0 / 1003/3OK26.0s
CG-AL-M033medium1100.0 / 1002/2OK18.1s
CG-AL-M034medium262.5 / 1001/2OK21.1s
CG-AL-M035medium1100.0 / 1002/2OK16.9s
CG-AL-M036medium1100.0 / 1002/2OK19.0s
CG-AL-M037medium20.0 / 1000/0FAIL24.9s
CG-AL-M038medium1100.0 / 1002/2OK16.5s
CG-AL-M039medium1100.0 / 1002/2OK56.4s
CG-AL-M040medium262.5 / 1001/2OK17.8s
CG-AL-M041medium1100.0 / 1003/3OK17.4s
CG-AL-M042medium1100.0 / 1008/8OK19.7s
CG-AL-M043medium1100.0 / 1005/5OK18.1s
CG-AL-M044medium1100.0 / 1006/6OK33.7s
CG-AL-M045medium1100.0 / 1006/6OK23.6s
CG-AL-M088medium1100.0 / 1006/6OK25.2s
CG-AL-M112medium1100.0 / 1004/4OK22.0s