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.

52.6 / 100
Cost $1.12
Duration 1h 36m
Filter:
Per-task results for run 90a07673-dba9-4713-971c-01581e2fdaac
TaskDifficultyAttemptScoreTestsCompileDuration
CG-AL-E001easy1100.0 / 1007/7OK18.6s
CG-AL-E002easy1100.0 / 1006/6OK2m 35s
CG-AL-E003easy1100.0 / 1005/5OK22.4s
CG-AL-E004easy1100.0 / 1006/6OK34.0s
CG-AL-E005easy1100.0 / 10013/13OK30.7s
CG-AL-E006easy2100.0 / 1007/7OK2m 38s
CG-AL-E007easy1100.0 / 1007/7OK37.9s
CG-AL-E008easy1100.0 / 1006/6OK46.9s
CG-AL-E009easy1100.0 / 1005/5OK42.7s
CG-AL-E010easy1100.0 / 1005/5OK47.4s
CG-AL-E031easy1100.0 / 1003/3OK50.9s
CG-AL-E032easy1100.0 / 1001/1OK42.5s
CG-AL-E045easy1100.0 / 1004/4OK21.6s
CG-AL-E050easy20.0 / 1000/0FAIL15.9s
CG-AL-E051easy2100.0 / 10015/15OK25.0s
CG-AL-E052easy2100.0 / 10016/16OK30.2s
CG-AL-E053easy1100.0 / 1003/3OK2m 21s
CG-AL-E054easy1100.0 / 1009/9OK25.3s
CG-AL-E055easy1100.0 / 1008/8OK21.5s
CG-AL-E056easy2100.0 / 10015/15OK22.9s
CG-AL-E057easy20.0 / 1000/0FAIL1m 7s
CG-AL-E058easy2100.0 / 1001/1OK45.2s
CG-AL-H001hard1100.0 / 10025/25OK20.4s
CG-AL-H002hard1100.0 / 1004/4OK19.6s
CG-AL-H003hard1100.0 / 1005/5OK22.4s
CG-AL-H004hard1100.0 / 10014/14OK19.7s
CG-AL-H005hard1100.0 / 1006/6OK26.5s
CG-AL-H006hard1100.0 / 1006/6OK20.2s
CG-AL-H007hard1100.0 / 10010/10OK27.8s
CG-AL-H008hard2100.0 / 10010/10OK18.9s
CG-AL-H009hard1100.0 / 10011/11OK22.8s
CG-AL-H010hard1100.0 / 1008/8OK27.0s
CG-AL-H011hard2100.0 / 1005/5OK18.1s
CG-AL-H013hard1100.0 / 1009/9OK21.0s
CG-AL-H014hard20.0 / 1000/0FAIL13.6s
CG-AL-H015hard1100.0 / 1004/4OK17.5s
CG-AL-H016hard1100.0 / 1004/4OK19.8s
CG-AL-H017hard2100.0 / 1003/3OK20.0s
CG-AL-H018hard2100.0 / 1006/6OK28.7s
CG-AL-H019hard2100.0 / 1005/5OK16.8s
CG-AL-H020hard20.0 / 1000/0FAIL1m 12s
CG-AL-H021hard2100.0 / 10020/20OK37.7s
CG-AL-H022hard20.0 / 1000/0FAIL19.7s
CG-AL-H023hard20.0 / 1000/0FAIL1m 11s
CG-AL-H024hard1100.0 / 1009/9OK27.5s
CG-AL-H025hard1100.0 / 1007/7OK18.8s
CG-AL-H026hard1100.0 / 1008/8OK21.2s
CG-AL-H027hard1100.0 / 1004/4OK46.8s
CG-AL-H028hard1100.0 / 1009/9OK27.9s
CG-AL-H029hard20.0 / 1000/0FAIL37.2s
CG-AL-H030hard20.0 / 1000/0FAIL39.4s
CG-AL-H031hard20.0 / 1000/0FAIL1m 8s
CG-AL-H032hard2100.0 / 10019/19OK24.6s
CG-AL-H033hard20.0 / 1000/0FAIL1m 8s
CG-AL-H034hard262.5 / 1002/3OK25.3s
CG-AL-H035hard1100.0 / 1003/3OK18.4s
CG-AL-H036hard2100.0 / 1005/5OK25.3s
CG-AL-H037hard2100.0 / 1003/3OK21.8s
CG-AL-H038hard1100.0 / 1003/3OK25.6s
CG-AL-H039hard1100.0 / 1004/4OK17.8s
CG-AL-H040hard1100.0 / 1002/2OK18.1s
CG-AL-H041hard1100.0 / 1003/3OK29.2s
CG-AL-H042hard2100.0 / 1003/3OK17.3s
CG-AL-H043hard1100.0 / 1005/5OK16.8s
CG-AL-H050hard2100.0 / 1003/3OK25.0s
CG-AL-H051hard1100.0 / 1004/4OK29.9s
CG-AL-H052hard1100.0 / 1005/5OK29.2s
CG-AL-H053hard1100.0 / 1004/4OK17.9s
CG-AL-H054hard20.0 / 1000/0FAIL14.9s
CG-AL-H056hard20.0 / 1000/0FAIL9.7s
CG-AL-H057hard1100.0 / 1004/4OK2m 42s
CG-AL-H058hard1100.0 / 1005/5OK30.5s
CG-AL-H205hard1100.0 / 1006/6OK20.2s
CG-AL-M001medium20.0 / 1000/0FAIL11.2s
CG-AL-M002medium20.0 / 1000/0FAIL1m 20s
CG-AL-M003medium20.0 / 1000/0FAIL22.0s
CG-AL-M004medium1100.0 / 10012/12OK2m 55s
CG-AL-M005medium20.0 / 1000/0FAIL52.5s
CG-AL-M006medium20.0 / 1000/0FAIL1m 12s
CG-AL-M007medium20.0 / 1000/0FAIL50.5s
CG-AL-M008medium20.0 / 1000/0FAIL1m 22s
CG-AL-M009medium20.0 / 1000/0FAIL31.2s
CG-AL-M010medium20.0 / 1000/0FAIL1m 12s
CG-AL-M020medium2100.0 / 10017/17OK48.4s
CG-AL-M021medium1100.0 / 10011/11OK21.0s
CG-AL-M022medium1100.0 / 1009/9OK25.3s
CG-AL-M023medium20.0 / 1000/0FAIL1m 23s
CG-AL-M024medium2100.0 / 10010/10OK24.5s
CG-AL-M025medium1100.0 / 1007/7OK21.6s
CG-AL-M026medium262.5 / 1006/8OK28.1s
CG-AL-M027medium20.0 / 1000/0FAIL1m 13s
CG-AL-M028medium20.0 / 1000/0FAIL16.3s
CG-AL-M029medium2100.0 / 1003/3OK2m 37s
CG-AL-M031medium20.0 / 1000/0FAIL18.8s
CG-AL-M032medium1100.0 / 1003/3OK20.6s
CG-AL-M033medium1100.0 / 1002/2OK19.4s
CG-AL-M034medium262.5 / 1001/2OK30.5s
CG-AL-M035medium1100.0 / 1002/2OK17.4s
CG-AL-M036medium20.0 / 1000/0FAIL46.9s
CG-AL-M037medium20.0 / 1000/0FAIL34.5s
CG-AL-M038medium1100.0 / 1002/2OK19.7s
CG-AL-M039medium1100.0 / 1002/2OK2m 24s
CG-AL-M040medium262.5 / 1001/2OK27.2s
CG-AL-M041medium1100.0 / 1003/3OK16.1s
CG-AL-M042medium1100.0 / 1008/8OK21.4s
CG-AL-M043medium1100.0 / 1005/5OK25.9s
CG-AL-M044medium1100.0 / 1006/6OK2m 22s
CG-AL-M045medium1100.0 / 1006/6OK19.5s
CG-AL-M088medium1100.0 / 1006/6OK19.9s
CG-AL-M112medium2100.0 / 1004/4OK22.5s