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.

78.2% 86/110 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.

60.3 / 100
Cost $14.19
Duration 4h 5m
Filter:
Per-task results for run c82c44d5-3561-48ca-b5c0-0b9f41695101
TaskDifficultyAttemptScoreTestsCompileDuration
CG-AL-E001easy1100.0 / 1007/7OK22.5s
CG-AL-E002easy1100.0 / 1006/6OK2m 50s
CG-AL-E003easy1100.0 / 1005/5OK19.3s
CG-AL-E004easy1100.0 / 1006/6OK26.7s
CG-AL-E005easy1100.0 / 10013/13OK1m 7s
CG-AL-E006easy1100.0 / 1007/7OK3m 3s
CG-AL-E007easy2100.0 / 1007/7OK23.3s
CG-AL-E008easy20.0 / 1000/0FAIL21.9s
CG-AL-E009easy1100.0 / 1005/5OK56.3s
CG-AL-E010easy1100.0 / 1005/5OK37.5s
CG-AL-E031easy1100.0 / 1003/3OK38.8s
CG-AL-E032easy1100.0 / 1001/1OK30.4s
CG-AL-E045easy1100.0 / 1004/4OK25.8s
CG-AL-E050easy20.0 / 1000/0FAIL1m 3s
CG-AL-E051easy1100.0 / 10015/15OK2m 16s
CG-AL-E052easy2100.0 / 10016/16OK21.1s
CG-AL-E053easy1100.0 / 1003/3OK2m 47s
CG-AL-E054easy2100.0 / 1009/9OK53.7s
CG-AL-E055easy1100.0 / 1008/8OK24.2s
CG-AL-E056easy2100.0 / 10015/15OK27.4s
CG-AL-E057easy2100.0 / 1008/8OK26.3s
CG-AL-E058easy1100.0 / 1001/1OK54.0s
CG-AL-H001hard1100.0 / 10025/25OK24.1s
CG-AL-H002hard1100.0 / 1004/4OK22.5s
CG-AL-H003hard1100.0 / 1005/5OK27.2s
CG-AL-H004hard1100.0 / 10014/14OK41.7s
CG-AL-H005hard1100.0 / 1006/6OK27.7s
CG-AL-H006hard1100.0 / 1006/6OK25.7s
CG-AL-H007hard2100.0 / 10010/10OK25.3s
CG-AL-H008hard1100.0 / 10010/10OK27.1s
CG-AL-H009hard1100.0 / 10011/11OK34.1s
CG-AL-H010hard1100.0 / 1008/8OK23.7s
CG-AL-H011hard2100.0 / 1005/5OK31.7s
CG-AL-H013hard1100.0 / 1009/9OK24.5s
CG-AL-H014hard20.0 / 1000/0FAIL17.0s
CG-AL-H015hard1100.0 / 1004/4OK28.5s
CG-AL-H016hard1100.0 / 1004/4OK30.7s
CG-AL-H017hard2100.0 / 1003/3OK24.5s
CG-AL-H018hard1100.0 / 1006/6OK1m 12s
CG-AL-H019hard1100.0 / 1005/5OK51.4s
CG-AL-H020hard2100.0 / 10010/10OK29.4s
CG-AL-H021hard20.0 / 1000/0FAIL18.8s
CG-AL-H022hard1100.0 / 10021/21OK51.8s
CG-AL-H023hard20.0 / 1000/0FAIL3m 37s
CG-AL-H024hard1100.0 / 1009/9OK1m 2s
CG-AL-H025hard1100.0 / 1007/7OK25.0s
CG-AL-H026hard1100.0 / 1008/8OK34.3s
CG-AL-H027hard2100.0 / 1004/4OK25.5s
CG-AL-H028hard1100.0 / 1009/9OK1m 42s
CG-AL-H029hard20.0 / 1000/0FAIL2m 15s
CG-AL-H030hard2100.0 / 10010/10OK1m 59s
CG-AL-H031hard20.0 / 1000/0FAIL2m 23s
CG-AL-H032hard1100.0 / 10019/19OK1m 3s
CG-AL-H033hard1100.0 / 1005/5OK2m 44s
CG-AL-H034hard1100.0 / 1003/3OK34.4s
CG-AL-H035hard1100.0 / 1003/3OK21.1s
CG-AL-H036hard20.0 / 1000/0FAIL32.8s
CG-AL-H037hard20.0 / 1000/0FAIL39.6s
CG-AL-H038hard1100.0 / 1003/3OK34.2s
CG-AL-H039hard1100.0 / 1004/4OK33.5s
CG-AL-H040hard1100.0 / 1002/2OK41.5s
CG-AL-H041hard1100.0 / 1003/3OK45.4s
CG-AL-H042hard1100.0 / 1003/3OK22.8s
CG-AL-H043hard1100.0 / 1005/5OK23.2s
CG-AL-H050hard2100.0 / 1003/3OK23.9s
CG-AL-H051hard1100.0 / 1004/4OK23.6s
CG-AL-H052hard1100.0 / 1005/5OK28.1s
CG-AL-H053hard1100.0 / 1004/4OK25.0s
CG-AL-H054hard20.0 / 1000/0FAIL14.4s
CG-AL-H056hard20.0 / 1000/0FAIL13.5s
CG-AL-H057hard1100.0 / 1004/4OK2m 39s
CG-AL-H058hard1100.0 / 1005/5OK23.7s
CG-AL-H205hard1100.0 / 1006/6OK27.9s
CG-AL-M001medium20.0 / 1000/0FAIL18.2s
CG-AL-M002medium1100.0 / 10022/22OK1m 5s
CG-AL-M003medium2100.0 / 1009/9OK29.0s
CG-AL-M004medium1100.0 / 10012/12OK4m 34s
CG-AL-M005medium20.0 / 1000/0FAIL3m 49s
CG-AL-M006medium20.0 / 1000/0FAIL3m 38s
CG-AL-M007medium20.0 / 1000/0FAIL3m 16s
CG-AL-M008medium20.0 / 1000/0FAIL3m 48s
CG-AL-M009medium20.0 / 1000/0FAIL2m 29s
CG-AL-M010medium20.0 / 1000/0FAIL2m 4s
CG-AL-M020medium262.5 / 1000/0OK13m 19s
CG-AL-M021medium2100.0 / 10011/11OK55.2s
CG-AL-M022medium2100.0 / 1009/9OK1m 1s
CG-AL-M023medium262.5 / 10010/11OK2m 30s
CG-AL-M024medium2100.0 / 10010/10OK54.9s
CG-AL-M025medium262.5 / 1002/7OK25.9s
CG-AL-M026medium1100.0 / 1008/8OK41.5s
CG-AL-M027medium2100.0 / 10018/18OK46.0s
CG-AL-M028medium2100.0 / 1003/3OK2m 33s
CG-AL-M029medium2100.0 / 1003/3OK2m 30s
CG-AL-M031medium2100.0 / 1002/2OK1m 5s
CG-AL-M032medium1100.0 / 1003/3OK24.5s
CG-AL-M033medium1100.0 / 1002/2OK34.8s
CG-AL-M034medium262.5 / 1001/2OK1m 10s
CG-AL-M035medium1100.0 / 1002/2OK18.0s
CG-AL-M036medium2100.0 / 1002/2OK31.1s
CG-AL-M037medium20.0 / 1000/0FAIL23.9s
CG-AL-M038medium1100.0 / 1002/2OK24.2s
CG-AL-M039medium1100.0 / 1002/2OK2m 49s
CG-AL-M040medium20.0 / 1000/0FAIL14.7s
CG-AL-M041medium1100.0 / 1003/3OK18.1s
CG-AL-M042medium1100.0 / 1008/8OK26.4s
CG-AL-M043medium2100.0 / 1005/5OK21.8s
CG-AL-M044medium1100.0 / 1006/6OK2m 52s
CG-AL-M045medium1100.0 / 1006/6OK43.4s
CG-AL-M088medium1100.0 / 1006/6OK26.3s
CG-AL-M112medium1100.0 / 1004/4OK29.6s