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.

87.3% 96/110 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.

72.3 / 100
Cost $3.87
Duration 1h 56m
Filter:
Per-task results for run c611fa66-e0e0-4274-9f5e-a7f1f9704262
TaskDifficultyAttemptScoreTestsCompileDuration
CG-AL-E001easy2100.0 / 1007/7OK1m 0s
CG-AL-E002easy1100.0 / 1006/6OK2m 47s
CG-AL-E003easy1100.0 / 1005/5OK26.3s
CG-AL-E004easy1100.0 / 1006/6OK30.0s
CG-AL-E005easy1100.0 / 10013/13OK37.6s
CG-AL-E006easy1100.0 / 1007/7OK2m 56s
CG-AL-E007easy2100.0 / 1007/7OK19.6s
CG-AL-E008easy1100.0 / 1006/6OK51.8s
CG-AL-E009easy1100.0 / 1005/5OK57.1s
CG-AL-E010easy2100.0 / 1005/5OK18.9s
CG-AL-E031easy1100.0 / 1003/3OK1m 0s
CG-AL-E032easy1100.0 / 1001/1OK58.8s
CG-AL-E045easy1100.0 / 1004/4OK19.8s
CG-AL-E050easy1100.0 / 10013/13OK24.9s
CG-AL-E051easy1100.0 / 10015/15OK25.7s
CG-AL-E052easy2100.0 / 10016/16OK18.1s
CG-AL-E053easy1100.0 / 1003/3OK2m 28s
CG-AL-E054easy1100.0 / 1009/9OK19.7s
CG-AL-E055easy1100.0 / 1008/8OK17.9s
CG-AL-E056easy262.5 / 10013/15OK17.7s
CG-AL-E057easy20.0 / 1000/0FAIL10.7s
CG-AL-E058easy1100.0 / 1001/1OK16.4s
CG-AL-H001easy1100.0 / 10025/25OK19.8s
CG-AL-H002easy1100.0 / 1004/4OK20.8s
CG-AL-H003easy1100.0 / 1005/5OK21.7s
CG-AL-H004easy1100.0 / 10014/14OK20.1s
CG-AL-H005easy1100.0 / 1006/6OK23.2s
CG-AL-H006easy1100.0 / 1006/6OK18.4s
CG-AL-H007easy1100.0 / 10010/10OK22.2s
CG-AL-H008easy1100.0 / 10010/10OK26.7s
CG-AL-H009easy1100.0 / 10011/11OK23.4s
CG-AL-H010easy1100.0 / 1008/8OK19.5s
CG-AL-H011easy20.0 / 1000/0FAIL7.7s
CG-AL-H013easy1100.0 / 1009/9OK19.8s
CG-AL-H014easy2100.0 / 1007/7OK19.8s
CG-AL-H015easy1100.0 / 1004/4OK17.6s
CG-AL-H016easy1100.0 / 1004/4OK18.8s
CG-AL-H017easy2100.0 / 1003/3OK17.1s
CG-AL-H018easy1100.0 / 1006/6OK21.2s
CG-AL-H019easy1100.0 / 1005/5OK17.2s
CG-AL-H020easy2100.0 / 10010/10OK21.1s
CG-AL-H021easy20.0 / 1000/0FAIL11.9s
CG-AL-H022easy1100.0 / 10021/21OK29.5s
CG-AL-H023easy20.0 / 1000/0FAIL2m 45s
CG-AL-H024easy1100.0 / 1009/9OK2m 5s
CG-AL-H025easy1100.0 / 1007/7OK19.0s
CG-AL-H026easy1100.0 / 1008/8OK20.6s
CG-AL-H027easy1100.0 / 1004/4OK20.7s
CG-AL-H028easy2100.0 / 1009/9OK22.8s
CG-AL-H029easy20.0 / 1000/0FAIL16.6s
CG-AL-H030easy1100.0 / 10010/10OK23.4s
CG-AL-H031easy1100.0 / 10022/22OK27.6s
CG-AL-H032easy1100.0 / 10019/19OK28.3s
CG-AL-H033easy1100.0 / 1005/5OK2m 52s
CG-AL-H034easy2100.0 / 1003/3OK16.9s
CG-AL-H035easy1100.0 / 1003/3OK18.6s
CG-AL-H036easy1100.0 / 1005/5OK18.6s
CG-AL-H037easy1100.0 / 1003/3OK20.9s
CG-AL-H038easy1100.0 / 1003/3OK18.9s
CG-AL-H039easy1100.0 / 1004/4OK21.6s
CG-AL-H040easy1100.0 / 1002/2OK18.0s
CG-AL-H041easy1100.0 / 1003/3OK20.5s
CG-AL-H042easy1100.0 / 1003/3OK17.7s
CG-AL-H043easy1100.0 / 1005/5OK16.4s
CG-AL-H050easy262.5 / 1002/3OK28.1s
CG-AL-H051easy1100.0 / 1004/4OK18.9s
CG-AL-H052easy1100.0 / 1005/5OK19.6s
CG-AL-H053easy1100.0 / 1004/4OK18.6s
CG-AL-H054easy2100.0 / 1005/5OK21.2s
CG-AL-H056easy2100.0 / 1004/4OK17.2s
CG-AL-H057easy1100.0 / 1004/4OK2m 35s
CG-AL-H058easy1100.0 / 1005/5OK18.8s
CG-AL-H205easy1100.0 / 1006/6OK21.3s
CG-AL-M001easy20.0 / 1000/0FAIL9.5s
CG-AL-M002easy1100.0 / 10022/22OK27.2s
CG-AL-M003easy2100.0 / 1009/9OK27.1s
CG-AL-M004easy1100.0 / 10012/12OK2m 51s
CG-AL-M005easy2100.0 / 10022/22OK43.6s
CG-AL-M006easy1100.0 / 10018/18OK38.2s
CG-AL-M007easy2100.0 / 10015/15OK1m 36s
CG-AL-M008easy2100.0 / 10012/12OK2m 30s
CG-AL-M009easy2100.0 / 10011/11OK1m 59s
CG-AL-M010easy1100.0 / 10021/21OK5m 0s
CG-AL-M020easy2100.0 / 10017/17OK41.6s
CG-AL-M021easy1100.0 / 10011/11OK49.2s
CG-AL-M022easy1100.0 / 1009/9OK22.9s
CG-AL-M023easy262.5 / 10010/11OK26.5s
CG-AL-M024easy1100.0 / 10010/10OK27.1s
CG-AL-M025easy1100.0 / 1007/7OK21.4s
CG-AL-M026easy1100.0 / 1008/8OK21.2s
CG-AL-M027easy2100.0 / 10018/18OK26.3s
CG-AL-M028easy2100.0 / 1003/3OK2m 40s
CG-AL-M029easy2100.0 / 1003/3OK2m 29s
CG-AL-M031easy20.0 / 1000/0FAIL14.7s
CG-AL-M032easy1100.0 / 1003/3OK18.5s
CG-AL-M033easy1100.0 / 1002/2OK19.0s
CG-AL-M034easy262.5 / 1001/2OK19.2s
CG-AL-M035easy1100.0 / 1002/2OK17.6s
CG-AL-M036easy20.0 / 1000/0FAIL9.7s
CG-AL-M037easy20.0 / 1000/0FAIL8.2s
CG-AL-M038easy1100.0 / 1002/2OK18.9s
CG-AL-M039easy1100.0 / 1002/2OK2m 36s
CG-AL-M040easy20.0 / 1000/0FAIL7.7s
CG-AL-M041easy1100.0 / 1003/3OK18.2s
CG-AL-M042easy1100.0 / 1008/8OK18.3s
CG-AL-M043easy1100.0 / 1005/5OK19.6s
CG-AL-M044easy1100.0 / 1006/6OK2m 38s
CG-AL-M045easy1100.0 / 1006/6OK17.6s
CG-AL-M088easy1100.0 / 1006/6OK20.7s
CG-AL-M112easy1100.0 / 1004/4OK22.4s