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.

82.7% 91/110 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.

65.2 / 100
Cost $2.78
Duration 1h 32m
Filter:
Per-task results for run 6a052f35-56aa-48f8-bcde-a5227e391df2
TaskDifficultyAttemptScoreTestsCompileDuration
CG-AL-E001easy1100.0 / 1007/7OK18.1s
CG-AL-E002easy1100.0 / 1006/6OK2m 26s
CG-AL-E003easy1100.0 / 1005/5OK21.3s
CG-AL-E004easy1100.0 / 1006/6OK28.9s
CG-AL-E005easy1100.0 / 10013/13OK33.4s
CG-AL-E006easy1100.0 / 1007/7OK2m 55s
CG-AL-E007easy1100.0 / 1007/7OK41.1s
CG-AL-E008easy1100.0 / 1006/6OK45.6s
CG-AL-E009easy1100.0 / 1005/5OK46.9s
CG-AL-E010easy20.0 / 1000/0FAIL11.9s
CG-AL-E031easy1100.0 / 1003/3OK50.9s
CG-AL-E032easy1100.0 / 1001/1OK49.0s
CG-AL-E045easy1100.0 / 1004/4OK18.6s
CG-AL-E050easy20.0 / 1000/0FAIL13.8s
CG-AL-E051easy1100.0 / 10015/15OK22.1s
CG-AL-E052easy2100.0 / 10016/16OK20.4s
CG-AL-E053easy1100.0 / 1003/3OK2m 34s
CG-AL-E054easy2100.0 / 1009/9OK23.5s
CG-AL-E055easy1100.0 / 1008/8OK20.6s
CG-AL-E056easy2100.0 / 10015/15OK19.0s
CG-AL-E057easy20.0 / 1000/0FAIL11.4s
CG-AL-E058easy2100.0 / 1001/1OK17.5s
CG-AL-H001hard1100.0 / 10025/25OK20.8s
CG-AL-H002hard1100.0 / 1004/4OK20.0s
CG-AL-H003hard1100.0 / 1005/5OK21.4s
CG-AL-H004hard1100.0 / 10014/14OK19.4s
CG-AL-H005hard1100.0 / 1006/6OK21.4s
CG-AL-H006hard1100.0 / 1006/6OK16.4s
CG-AL-H007hard1100.0 / 10010/10OK21.1s
CG-AL-H008hard1100.0 / 10010/10OK17.9s
CG-AL-H009hard1100.0 / 10011/11OK24.0s
CG-AL-H010hard1100.0 / 1008/8OK20.0s
CG-AL-H011hard2100.0 / 1005/5OK16.2s
CG-AL-H013hard1100.0 / 1009/9OK17.2s
CG-AL-H014hard2100.0 / 1007/7OK25.2s
CG-AL-H015hard1100.0 / 1004/4OK16.3s
CG-AL-H016hard1100.0 / 1004/4OK17.4s
CG-AL-H017hard20.0 / 1000/0FAIL10.6s
CG-AL-H018hard1100.0 / 1006/6OK19.4s
CG-AL-H019hard1100.0 / 1005/5OK15.8s
CG-AL-H020hard2100.0 / 10010/10OK21.8s
CG-AL-H021hard2100.0 / 10020/20OK34.2s
CG-AL-H022hard2100.0 / 10021/21OK26.9s
CG-AL-H023hard20.0 / 1000/0FAIL3m 17s
CG-AL-H024hard1100.0 / 1009/9OK28.4s
CG-AL-H025hard1100.0 / 1007/7OK38.7s
CG-AL-H026hard1100.0 / 1008/8OK18.4s
CG-AL-H027hard1100.0 / 1004/4OK17.7s
CG-AL-H028hard2100.0 / 1009/9OK24.3s
CG-AL-H029hard2100.0 / 10018/18OK34.0s
CG-AL-H030hard2100.0 / 10010/10OK22.9s
CG-AL-H031hard2100.0 / 10022/22OK27.8s
CG-AL-H032hard1100.0 / 10019/19OK38.8s
CG-AL-H033hard1100.0 / 1005/5OK2m 54s
CG-AL-H034hard2100.0 / 1003/3OK15.2s
CG-AL-H035hard1100.0 / 1003/3OK15.6s
CG-AL-H036hard1100.0 / 1005/5OK15.9s
CG-AL-H037hard2100.0 / 1003/3OK17.2s
CG-AL-H038hard2100.0 / 1003/3OK21.9s
CG-AL-H039hard1100.0 / 1004/4OK17.6s
CG-AL-H040hard1100.0 / 1002/2OK19.8s
CG-AL-H041hard2100.0 / 1003/3OK28.2s
CG-AL-H042hard1100.0 / 1003/3OK17.3s
CG-AL-H043hard1100.0 / 1005/5OK16.5s
CG-AL-H050hard1100.0 / 1003/3OK23.7s
CG-AL-H051hard1100.0 / 1004/4OK16.7s
CG-AL-H052hard1100.0 / 1005/5OK18.2s
CG-AL-H053hard1100.0 / 1004/4OK18.4s
CG-AL-H054hard20.0 / 1000/0FAIL11.6s
CG-AL-H056hard20.0 / 1000/0FAIL7.8s
CG-AL-H057hard1100.0 / 1004/4OK2m 28s
CG-AL-H058hard1100.0 / 1005/5OK17.1s
CG-AL-H205hard1100.0 / 1006/6OK20.2s
CG-AL-M001medium2100.0 / 10010/10OK2m 45s
CG-AL-M002medium1100.0 / 10022/22OK22.2s
CG-AL-M003medium1100.0 / 1009/9OK24.4s
CG-AL-M004medium1100.0 / 10012/12OK3m 24s
CG-AL-M005medium262.5 / 10014/22OK37.3s
CG-AL-M006medium262.5 / 10017/18OK35.3s
CG-AL-M007medium20.0 / 1000/0FAIL45.8s
CG-AL-M008medium20.0 / 1000/0FAIL2m 58s
CG-AL-M009medium2100.0 / 10011/11OK55.7s
CG-AL-M010medium2100.0 / 10021/21OK3m 9s
CG-AL-M020medium2100.0 / 10017/17OK22.8s
CG-AL-M021medium2100.0 / 10011/11OK21.4s
CG-AL-M022medium1100.0 / 1009/9OK23.3s
CG-AL-M023medium262.5 / 10010/11OK22.9s
CG-AL-M024medium1100.0 / 10010/10OK25.2s
CG-AL-M025medium262.5 / 1002/7OK22.0s
CG-AL-M026medium1100.0 / 1008/8OK18.5s
CG-AL-M027medium2100.0 / 10018/18OK35.2s
CG-AL-M028medium2100.0 / 1003/3OK2m 38s
CG-AL-M029medium2100.0 / 1003/3OK2m 37s
CG-AL-M031medium20.0 / 1000/0FAIL20.9s
CG-AL-M032medium1100.0 / 1003/3OK16.9s
CG-AL-M033medium1100.0 / 1002/2OK17.7s
CG-AL-M034medium262.5 / 1001/2OK23.2s
CG-AL-M035medium1100.0 / 1002/2OK15.1s
CG-AL-M036medium20.0 / 1000/0FAIL14.4s
CG-AL-M037medium20.0 / 1000/0FAIL13.3s
CG-AL-M038medium1100.0 / 1002/2OK15.8s
CG-AL-M039medium20.0 / 1000/0FAIL20.0s
CG-AL-M040medium20.0 / 1000/0FAIL8.1s
CG-AL-M041medium1100.0 / 1003/3OK16.5s
CG-AL-M042medium1100.0 / 1008/8OK18.2s
CG-AL-M043medium1100.0 / 1005/5OK21.1s
CG-AL-M044medium1100.0 / 1006/6OK2m 50s
CG-AL-M045medium1100.0 / 1006/6OK17.4s
CG-AL-M088medium1100.0 / 1006/6OK24.0s
CG-AL-M112medium1100.0 / 1004/4OK21.5s