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.

80.0% 88/110 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.

60.4 / 100
Cost $13.17
Duration 2h 59m
Filter:
Per-task results for run 31706279-fbc9-4a95-bddb-aa6475f73db6
TaskDifficultyAttemptScoreTestsCompileDuration
CG-AL-E001easy2100.0 / 1007/7OK25.7s
CG-AL-E002easy1100.0 / 1006/6OK2m 36s
CG-AL-E003easy1100.0 / 1005/5OK18.8s
CG-AL-E004easy1100.0 / 1006/6OK20.4s
CG-AL-E005easy1100.0 / 10013/13OK30.5s
CG-AL-E006easy1100.0 / 1007/7OK3m 9s
CG-AL-E007easy1100.0 / 1007/7OK33.4s
CG-AL-E008easy2100.0 / 1006/6OK34.9s
CG-AL-E009easy2100.0 / 1005/5OK23.8s
CG-AL-E010easy2100.0 / 1005/5OK18.2s
CG-AL-E031easy1100.0 / 1003/3OK35.3s
CG-AL-E032easy1100.0 / 1001/1OK25.4s
CG-AL-E045easy1100.0 / 1004/4OK24.0s
CG-AL-E050easy20.0 / 1000/0FAIL1m 13s
CG-AL-E051easy2100.0 / 10015/15OK39.2s
CG-AL-E052easy2100.0 / 10016/16OK21.2s
CG-AL-E053easy1100.0 / 1003/3OK2m 34s
CG-AL-E054easy2100.0 / 1009/9OK46.6s
CG-AL-E055easy1100.0 / 1008/8OK22.2s
CG-AL-E056easy2100.0 / 10015/15OK21.2s
CG-AL-E057easy2100.0 / 1008/8OK26.0s
CG-AL-E058easy2100.0 / 1001/1OK23.5s
CG-AL-H001hard1100.0 / 10025/25OK27.3s
CG-AL-H002hard1100.0 / 1004/4OK26.7s
CG-AL-H003hard1100.0 / 1005/5OK29.0s
CG-AL-H004hard1100.0 / 10014/14OK46.3s
CG-AL-H005hard2100.0 / 1006/6OK18.8s
CG-AL-H006hard1100.0 / 1006/6OK26.4s
CG-AL-H007hard1100.0 / 10010/10OK58.8s
CG-AL-H008hard1100.0 / 10010/10OK35.5s
CG-AL-H009hard1100.0 / 10011/11OK32.2s
CG-AL-H010hard1100.0 / 1008/8OK24.7s
CG-AL-H011hard1100.0 / 1005/5OK33.5s
CG-AL-H013hard1100.0 / 1009/9OK31.7s
CG-AL-H014hard20.0 / 1000/0FAIL14.2s
CG-AL-H015hard1100.0 / 1004/4OK23.0s
CG-AL-H016hard1100.0 / 1004/4OK1m 53s
CG-AL-H017hard1100.0 / 1003/3OK1m 26s
CG-AL-H018hard1100.0 / 1006/6OK1m 17s
CG-AL-H019hard2100.0 / 1005/5OK18.1s
CG-AL-H020hard2100.0 / 10010/10OK37.1s
CG-AL-H021hard20.0 / 1000/0FAIL18.2s
CG-AL-H022hard2100.0 / 10021/21OK59.5s
CG-AL-H023hard20.0 / 1000/0FAIL3m 46s
CG-AL-H024hard1100.0 / 1009/9OK54.6s
CG-AL-H025hard1100.0 / 1007/7OK26.4s
CG-AL-H026hard1100.0 / 1008/8OK36.5s
CG-AL-H027hard2100.0 / 1004/4OK43.6s
CG-AL-H028hard1100.0 / 1009/9OK56.5s
CG-AL-H029hard20.0 / 1000/0FAIL1m 2s
CG-AL-H030hard20.0 / 1000/0FAIL3m 50s
CG-AL-H031hard1100.0 / 10022/22OK2m 17s
CG-AL-H032hard1100.0 / 10019/19OK2m 2s
CG-AL-H033hard1100.0 / 1005/5OK3m 15s
CG-AL-H034hard1100.0 / 1003/3OK24.2s
CG-AL-H035hard1100.0 / 1003/3OK31.4s
CG-AL-H036hard20.0 / 1000/0FAIL45.5s
CG-AL-H037hard2100.0 / 1003/3OK39.9s
CG-AL-H038hard1100.0 / 1003/3OK39.3s
CG-AL-H039hard1100.0 / 1004/4OK24.2s
CG-AL-H040hard1100.0 / 1002/2OK23.2s
CG-AL-H041hard1100.0 / 1003/3OK2m 22s
CG-AL-H042hard1100.0 / 1003/3OK22.4s
CG-AL-H043hard1100.0 / 1005/5OK23.3s
CG-AL-H050hard1100.0 / 1003/3OK47.8s
CG-AL-H051hard1100.0 / 1004/4OK25.2s
CG-AL-H052hard1100.0 / 1005/5OK39.0s
CG-AL-H053hard1100.0 / 1004/4OK23.8s
CG-AL-H054hard20.0 / 1000/0FAIL13.5s
CG-AL-H056hard20.0 / 1000/0FAIL24.0s
CG-AL-H057hard1100.0 / 1004/4OK2m 55s
CG-AL-H058hard1100.0 / 1005/5OK33.1s
CG-AL-H205hard1100.0 / 1006/6OK41.8s
CG-AL-M001medium20.0 / 1000/0FAIL18.7s
CG-AL-M002medium1100.0 / 10022/22OK28.0s
CG-AL-M003medium2100.0 / 1009/9OK37.7s
CG-AL-M004medium2100.0 / 10012/12OK2m 53s
CG-AL-M005medium20.0 / 1000/0FAIL3m 31s
CG-AL-M006medium20.0 / 1000/0FAIL3m 32s
CG-AL-M007medium20.0 / 1000/0FAIL3m 26s
CG-AL-M008medium20.0 / 1000/0FAIL2m 29s
CG-AL-M009medium20.0 / 1000/0FAIL59.7s
CG-AL-M010medium20.0 / 1000/0FAIL3m 39s
CG-AL-M020medium262.5 / 10013/17OK29.5s
CG-AL-M021medium1100.0 / 10011/11OK43.7s
CG-AL-M022medium2100.0 / 1009/9OK54.5s
CG-AL-M023medium262.5 / 10010/11OK23.9s
CG-AL-M024medium1100.0 / 10010/10OK43.9s
CG-AL-M025medium2100.0 / 1007/7OK33.7s
CG-AL-M026medium1100.0 / 1008/8OK33.1s
CG-AL-M027medium2100.0 / 10018/18OK32.2s
CG-AL-M028medium2100.0 / 1003/3OK2m 38s
CG-AL-M029medium2100.0 / 1003/3OK2m 41s
CG-AL-M031medium20.0 / 1000/0FAIL34.7s
CG-AL-M032medium1100.0 / 1003/3OK30.3s
CG-AL-M033medium1100.0 / 1002/2OK32.8s
CG-AL-M034medium262.5 / 1001/2OK1m 10s
CG-AL-M035medium1100.0 / 1002/2OK18.0s
CG-AL-M036medium2100.0 / 1002/2OK35.6s
CG-AL-M037medium20.0 / 1000/0FAIL15.3s
CG-AL-M038medium1100.0 / 1002/2OK23.9s
CG-AL-M039medium1100.0 / 1002/2OK2m 39s
CG-AL-M040medium20.0 / 1000/0FAIL35.5s
CG-AL-M041medium1100.0 / 1003/3OK17.5s
CG-AL-M042medium1100.0 / 1008/8OK25.4s
CG-AL-M043medium1100.0 / 1005/5OK41.8s
CG-AL-M044medium1100.0 / 1006/6OK2m 57s
CG-AL-M045medium1100.0 / 1006/6OK24.2s
CG-AL-M088medium1100.0 / 1006/6OK25.6s
CG-AL-M112medium1100.0 / 1004/4OK23.9s