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.

80.9% 89/110 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.

64.3 / 100
Cost $3.38
Duration 1h 38m
Filter:
Per-task results for run 9e7838df-bf03-48e4-b68e-4124d9649e65
TaskDifficultyAttemptScoreTestsCompileDuration
CG-AL-E001easy1100.0 / 1007/7OK34.6s
CG-AL-E002easy1100.0 / 1006/6OK3m 10s
CG-AL-E003easy1100.0 / 1005/5OK39.8s
CG-AL-E004easy1100.0 / 1006/6OK45.9s
CG-AL-E005easy1100.0 / 10013/13OK42.3s
CG-AL-E006easy1100.0 / 1007/7OK3m 43s
CG-AL-E007easy1100.0 / 1007/7OK54.0s
CG-AL-E008easy1100.0 / 1006/6OK57.5s
CG-AL-E009easy1100.0 / 1005/5OK59.9s
CG-AL-E010easy20.0 / 1000/0FAIL10.3s
CG-AL-E031easy1100.0 / 1003/3OK1m 5s
CG-AL-E032easy1100.0 / 1001/1OK1m 2s
CG-AL-E045easy1100.0 / 1004/4OK21.9s
CG-AL-E050easy20.0 / 1000/0FAIL15.0s
CG-AL-E051easy1100.0 / 10015/15OK29.1s
CG-AL-E052easy2100.0 / 10016/16OK23.1s
CG-AL-E053easy1100.0 / 1003/3OK3m 14s
CG-AL-E054easy20.0 / 1000/0FAIL12.6s
CG-AL-E055easy1100.0 / 1008/8OK21.1s
CG-AL-E056easy2100.0 / 10015/15OK24.3s
CG-AL-E057easy20.0 / 1000/0FAIL10.1s
CG-AL-E058easy20.0 / 1000/0FAIL15.9s
CG-AL-H001hard1100.0 / 10025/25OK23.4s
CG-AL-H002hard1100.0 / 1004/4OK24.6s
CG-AL-H003hard1100.0 / 1005/5OK26.1s
CG-AL-H004hard1100.0 / 10014/14OK24.6s
CG-AL-H005hard1100.0 / 1006/6OK26.3s
CG-AL-H006hard1100.0 / 1006/6OK22.1s
CG-AL-H007hard1100.0 / 10010/10OK26.2s
CG-AL-H008hard1100.0 / 10010/10OK21.6s
CG-AL-H009hard1100.0 / 10011/11OK27.6s
CG-AL-H010hard1100.0 / 1008/8OK21.4s
CG-AL-H011hard2100.0 / 1005/5OK21.6s
CG-AL-H013hard1100.0 / 1009/9OK21.5s
CG-AL-H014hard2100.0 / 1007/7OK26.4s
CG-AL-H015hard1100.0 / 1004/4OK18.7s
CG-AL-H016hard1100.0 / 1004/4OK20.5s
CG-AL-H017hard20.0 / 1000/0FAIL10.9s
CG-AL-H018hard1100.0 / 1006/6OK25.0s
CG-AL-H019hard1100.0 / 1005/5OK18.9s
CG-AL-H020hard2100.0 / 10010/10OK28.9s
CG-AL-H021hard2100.0 / 10020/20OK30.1s
CG-AL-H022hard2100.0 / 10021/21OK25.0s
CG-AL-H023hard20.0 / 1000/0FAIL2m 39s
CG-AL-H024hard1100.0 / 1009/9OK43.9s
CG-AL-H025hard1100.0 / 1007/7OK18.2s
CG-AL-H026hard1100.0 / 1008/8OK19.6s
CG-AL-H027hard1100.0 / 1004/4OK19.5s
CG-AL-H028hard2100.0 / 1009/9OK25.0s
CG-AL-H029hard262.5 / 10015/18OK36.8s
CG-AL-H030hard2100.0 / 10010/10OK26.2s
CG-AL-H031hard2100.0 / 10022/22OK26.2s
CG-AL-H032hard1100.0 / 10019/19OK28.1s
CG-AL-H033hard1100.0 / 1005/5OK2m 52s
CG-AL-H034hard2100.0 / 1003/3OK16.5s
CG-AL-H035hard1100.0 / 1003/3OK16.3s
CG-AL-H036hard1100.0 / 1005/5OK16.5s
CG-AL-H037hard2100.0 / 1003/3OK17.1s
CG-AL-H038hard2100.0 / 1003/3OK21.9s
CG-AL-H039hard1100.0 / 1004/4OK19.1s
CG-AL-H040hard1100.0 / 1002/2OK17.5s
CG-AL-H041hard2100.0 / 1003/3OK21.7s
CG-AL-H042hard1100.0 / 1003/3OK16.1s
CG-AL-H043hard1100.0 / 1005/5OK16.0s
CG-AL-H050hard2100.0 / 1003/3OK29.8s
CG-AL-H051hard1100.0 / 1004/4OK16.8s
CG-AL-H052hard1100.0 / 1005/5OK16.6s
CG-AL-H053hard1100.0 / 1004/4OK18.0s
CG-AL-H054hard20.0 / 1000/0FAIL15.1s
CG-AL-H056hard20.0 / 1000/0FAIL7.1s
CG-AL-H057hard1100.0 / 1004/4OK2m 33s
CG-AL-H058hard1100.0 / 1005/5OK19.0s
CG-AL-H205hard1100.0 / 1006/6OK19.3s
CG-AL-M001medium20.0 / 1000/0FAIL13.1s
CG-AL-M002medium1100.0 / 10022/22OK21.0s
CG-AL-M003medium1100.0 / 1009/9OK24.1s
CG-AL-M004medium1100.0 / 10012/12OK2m 56s
CG-AL-M005medium1100.0 / 10022/22OK39.1s
CG-AL-M006medium262.5 / 10017/18OK29.7s
CG-AL-M007medium20.0 / 1000/0FAIL3m 42s
CG-AL-M008medium20.0 / 1000/0FAIL2m 52s
CG-AL-M009medium2100.0 / 10011/11OK46.6s
CG-AL-M010medium2100.0 / 10021/21OK2m 53s
CG-AL-M020medium2100.0 / 10017/17OK24.7s
CG-AL-M021medium1100.0 / 10011/11OK22.0s
CG-AL-M022medium1100.0 / 1009/9OK22.8s
CG-AL-M023medium262.5 / 10010/11OK22.5s
CG-AL-M024medium1100.0 / 10010/10OK23.0s
CG-AL-M025medium262.5 / 1002/7OK21.0s
CG-AL-M026medium1100.0 / 1008/8OK18.9s
CG-AL-M027medium2100.0 / 10018/18OK38.2s
CG-AL-M028medium2100.0 / 1003/3OK2m 34s
CG-AL-M029medium2100.0 / 1003/3OK2m 30s
CG-AL-M031medium20.0 / 1000/0FAIL18.3s
CG-AL-M032medium1100.0 / 1003/3OK17.3s
CG-AL-M033medium1100.0 / 1002/2OK17.7s
CG-AL-M034medium262.5 / 1001/2OK24.0s
CG-AL-M035medium1100.0 / 1002/2OK19.8s
CG-AL-M036medium2100.0 / 1002/2OK19.5s
CG-AL-M037medium20.0 / 1000/0FAIL9.1s
CG-AL-M038medium1100.0 / 1002/2OK16.6s
CG-AL-M039medium20.0 / 1000/0FAIL17.5s
CG-AL-M040medium20.0 / 1000/0FAIL8.1s
CG-AL-M041medium1100.0 / 1003/3OK16.1s
CG-AL-M042medium2100.0 / 1008/8OK19.0s
CG-AL-M043medium1100.0 / 1005/5OK20.5s
CG-AL-M044medium1100.0 / 1006/6OK2m 33s
CG-AL-M045medium1100.0 / 1006/6OK16.7s
CG-AL-M088medium1100.0 / 1006/6OK19.8s
CG-AL-M112medium1100.0 / 1004/4OK23.1s