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.

71.8% 79/110 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.

53.6 / 100
Cost $1.09
Duration 1h 37m
Filter:
Per-task results for run 2c01b44c-9f4a-4308-ba37-85444d3d3796
TaskDifficultyAttemptScoreTestsCompileDuration
CG-AL-E001easy1100.0 / 1007/7OK19.3s
CG-AL-E002easy1100.0 / 1006/6OK2m 21s
CG-AL-E003easy1100.0 / 1005/5OK22.3s
CG-AL-E004easy1100.0 / 1006/6OK25.7s
CG-AL-E005easy1100.0 / 10013/13OK29.7s
CG-AL-E006easy2100.0 / 1007/7OK2m 39s
CG-AL-E007easy1100.0 / 1007/7OK34.7s
CG-AL-E008easy1100.0 / 1006/6OK43.4s
CG-AL-E009easy2100.0 / 1005/5OK30.7s
CG-AL-E010easy1100.0 / 1005/5OK45.9s
CG-AL-E031easy1100.0 / 1003/3OK46.3s
CG-AL-E032easy1100.0 / 1001/1OK42.1s
CG-AL-E045easy1100.0 / 1004/4OK23.6s
CG-AL-E050easy20.0 / 1000/0FAIL14.4s
CG-AL-E051easy20.0 / 1000/0FAIL1m 13s
CG-AL-E052easy2100.0 / 10016/16OK29.7s
CG-AL-E053easy1100.0 / 1003/3OK2m 38s
CG-AL-E054easy1100.0 / 1009/9OK25.4s
CG-AL-E055easy1100.0 / 1008/8OK20.1s
CG-AL-E056easy2100.0 / 10015/15OK20.4s
CG-AL-E057easy20.0 / 1000/0FAIL41.4s
CG-AL-E058easy20.0 / 1000/0FAIL25.0s
CG-AL-H001hard1100.0 / 10025/25OK20.4s
CG-AL-H002hard1100.0 / 1004/4OK20.3s
CG-AL-H003hard1100.0 / 1005/5OK26.3s
CG-AL-H004hard1100.0 / 10014/14OK19.6s
CG-AL-H005hard1100.0 / 1006/6OK27.1s
CG-AL-H006hard1100.0 / 1006/6OK18.6s
CG-AL-H007hard1100.0 / 10010/10OK21.4s
CG-AL-H008hard1100.0 / 10010/10OK22.6s
CG-AL-H009hard2100.0 / 10011/11OK27.0s
CG-AL-H010hard1100.0 / 1008/8OK23.1s
CG-AL-H011hard2100.0 / 1005/5OK24.6s
CG-AL-H013hard1100.0 / 1009/9OK19.6s
CG-AL-H014hard20.0 / 1000/0FAIL17.2s
CG-AL-H015hard1100.0 / 1004/4OK18.5s
CG-AL-H016hard1100.0 / 1004/4OK21.2s
CG-AL-H017hard2100.0 / 1003/3OK31.6s
CG-AL-H018hard1100.0 / 1006/6OK21.5s
CG-AL-H019hard1100.0 / 1005/5OK19.9s
CG-AL-H020hard20.0 / 1000/0FAIL1m 17s
CG-AL-H021hard2100.0 / 10020/20OK35.8s
CG-AL-H022hard20.0 / 1000/0FAIL49.6s
CG-AL-H023hard20.0 / 1000/0FAIL57.1s
CG-AL-H024hard2100.0 / 1009/9OK30.2s
CG-AL-H025hard1100.0 / 1007/7OK19.7s
CG-AL-H026hard1100.0 / 1008/8OK23.4s
CG-AL-H027hard1100.0 / 1004/4OK28.0s
CG-AL-H028hard1100.0 / 1009/9OK24.6s
CG-AL-H029hard20.0 / 1000/0FAIL1m 18s
CG-AL-H030hard20.0 / 1000/0FAIL1m 39s
CG-AL-H031hard20.0 / 1000/0FAIL30.4s
CG-AL-H032hard2100.0 / 10019/19OK25.3s
CG-AL-H033hard20.0 / 1000/0FAIL1m 13s
CG-AL-H034hard20.0 / 1000/0FAIL1m 26s
CG-AL-H035hard1100.0 / 1003/3OK18.1s
CG-AL-H036hard2100.0 / 1005/5OK28.4s
CG-AL-H037hard1100.0 / 1003/3OK29.3s
CG-AL-H038hard1100.0 / 1003/3OK26.5s
CG-AL-H039hard1100.0 / 1004/4OK20.8s
CG-AL-H040hard1100.0 / 1002/2OK19.2s
CG-AL-H041hard1100.0 / 1003/3OK26.2s
CG-AL-H042hard2100.0 / 1003/3OK20.8s
CG-AL-H043hard1100.0 / 1005/5OK18.4s
CG-AL-H050hard262.5 / 1002/3OK32.0s
CG-AL-H051hard1100.0 / 1004/4OK52.6s
CG-AL-H052hard1100.0 / 1005/5OK28.9s
CG-AL-H053hard1100.0 / 1004/4OK22.3s
CG-AL-H054hard20.0 / 1000/0FAIL12.2s
CG-AL-H056hard20.0 / 1000/0FAIL9.3s
CG-AL-H057hard1100.0 / 1004/4OK2m 31s
CG-AL-H058hard1100.0 / 1005/5OK31.7s
CG-AL-H205hard1100.0 / 1006/6OK20.9s
CG-AL-M001medium20.0 / 1000/0FAIL12.8s
CG-AL-M002medium2100.0 / 10022/22OK18.9s
CG-AL-M003medium20.0 / 1000/0FAIL1m 17s
CG-AL-M004medium2100.0 / 10012/12OK3m 3s
CG-AL-M005medium1100.0 / 10022/22OK32.1s
CG-AL-M006medium20.0 / 1000/0FAIL1m 18s
CG-AL-M007medium20.0 / 1000/0FAIL1m 22s
CG-AL-M008medium20.0 / 1000/0FAIL1m 24s
CG-AL-M009medium2100.0 / 10011/11OK30.8s
CG-AL-M010medium20.0 / 1000/0FAIL1m 18s
CG-AL-M020medium2100.0 / 10017/17OK30.3s
CG-AL-M021medium1100.0 / 10011/11OK23.9s
CG-AL-M022medium1100.0 / 1009/9OK24.0s
CG-AL-M023medium20.0 / 1000/0FAIL1m 33s
CG-AL-M024medium1100.0 / 10010/10OK25.7s
CG-AL-M025medium1100.0 / 1007/7OK22.2s
CG-AL-M026medium1100.0 / 1008/8OK22.8s
CG-AL-M027medium20.0 / 1000/0FAIL1m 18s
CG-AL-M028medium20.0 / 1000/0FAIL14.3s
CG-AL-M029medium20.0 / 1000/0FAIL12.7s
CG-AL-M031medium20.0 / 1000/0FAIL18.8s
CG-AL-M032medium1100.0 / 1003/3OK21.7s
CG-AL-M033medium1100.0 / 1002/2OK22.5s
CG-AL-M034medium262.5 / 1001/2OK28.5s
CG-AL-M035medium1100.0 / 1002/2OK18.1s
CG-AL-M036medium20.0 / 1000/0FAIL16.6s
CG-AL-M037medium20.0 / 1000/0FAIL39.5s
CG-AL-M038medium1100.0 / 1002/2OK19.2s
CG-AL-M039medium1100.0 / 1002/2OK2m 30s
CG-AL-M040medium262.5 / 1001/2OK22.9s
CG-AL-M041medium1100.0 / 1003/3OK17.0s
CG-AL-M042medium1100.0 / 1008/8OK22.2s
CG-AL-M043medium2100.0 / 1005/5OK24.6s
CG-AL-M044medium1100.0 / 1006/6OK3m 0s
CG-AL-M045medium1100.0 / 1006/6OK23.9s
CG-AL-M088medium1100.0 / 1006/6OK22.3s
CG-AL-M112medium1100.0 / 1004/4OK26.6s