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.

56.3% 36/64 of 64 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.

44.1 / 100
Cost $0.57
Duration 2h 6m
Filter:
Per-task results for run 4438b0ca-feb4-4509-b231-3d768333cae3
TaskDifficultyAttemptScoreTestsCompileDuration
CG-AL-E001easy1100.0 / 1007/7OK2m 18s
CG-AL-E002easy1100.0 / 1006/6OK2m 25s
CG-AL-E003easy1100.0 / 1005/5OK2m 18s
CG-AL-E004easy1100.0 / 1006/6OK2m 22s
CG-AL-E005easy1100.0 / 10013/13OK2m 24s
CG-AL-E006easy2100.0 / 1007/7OK2m 23s
CG-AL-E007easy2100.0 / 1007/7OK2m 21s
CG-AL-E008easy1100.0 / 1006/6OK2m 29s
CG-AL-E009easy1100.0 / 1005/5OK2m 28s
CG-AL-E010easy1100.0 / 1005/5OK2m 27s
CG-AL-E031easy1100.0 / 1003/3OK2m 31s
CG-AL-E032easy1100.0 / 1001/1OK2m 27s
CG-AL-E045easy1100.0 / 1004/4OK2m 39s
CG-AL-E050easy20.0 / 1000/0FAIL6.6s
CG-AL-E051easy20.0 / 1000/0FAIL8.2s
CG-AL-E052easy262.5 / 10014/16OK2m 17s
CG-AL-E053easy2100.0 / 1003/3OK2m 18s
CG-AL-E054easy20.0 / 1000/0FAIL7.5s
CG-AL-E055easy1100.0 / 1008/8OK2m 18s
CG-AL-H001easy1100.0 / 10025/25OK2m 20s
CG-AL-H002easy2100.0 / 1004/4OK2m 17s
CG-AL-H003easy262.5 / 1004/5OK2m 19s
CG-AL-H004easy1100.0 / 10014/14OK2m 18s
CG-AL-H005easy20.0 / 1000/0FAIL13.1s
CG-AL-H006easy1100.0 / 1006/6OK2m 17s
CG-AL-H007easy2100.0 / 10010/10OK2m 18s
CG-AL-H008easy1100.0 / 10010/10OK2m 18s
CG-AL-H009easy1100.0 / 10011/11OK2m 19s
CG-AL-H010easy1100.0 / 1008/8OK2m 18s
CG-AL-H011easy20.0 / 1000/0FAIL6.4s
CG-AL-H013easy1100.0 / 1009/9OK2m 19s
CG-AL-H014easy20.0 / 1000/0FAIL6.3s
CG-AL-H015easy1100.0 / 1004/4OK2m 18s
CG-AL-H016easy20.0 / 1000/0FAIL6.8s
CG-AL-H017easy20.0 / 1000/0FAIL5.8s
CG-AL-H018easy20.0 / 1000/0FAIL7.1s
CG-AL-H019easy20.0 / 1000/0FAIL5.4s
CG-AL-H020easy20.0 / 1000/0FAIL9.6s
CG-AL-H021easy20.0 / 1000/0FAIL9.1s
CG-AL-H022easy262.5 / 10017/21OK2m 23s
CG-AL-H023easy20.0 / 1000/0FAIL1m 29s
CG-AL-H024easy1100.0 / 1009/9OK2m 23s
CG-AL-H025easy1100.0 / 1007/7OK2m 18s
CG-AL-H026easy1100.0 / 1008/8OK2m 21s
CG-AL-H205easy2100.0 / 1006/6OK2m 17s
CG-AL-M001easy20.0 / 1000/0FAIL7.2s
CG-AL-M002easy262.5 / 10021/22OK2m 22s
CG-AL-M003easy20.0 / 1000/0FAIL15.1s
CG-AL-M004easy1100.0 / 10012/12OK2m 30s
CG-AL-M005easy20.0 / 1000/0FAIL14.0s
CG-AL-M006easy20.0 / 1000/0FAIL9.6s
CG-AL-M007easy20.0 / 1000/0FAIL13.6s
CG-AL-M008easy20.0 / 1000/0FAIL21.7s
CG-AL-M009easy1100.0 / 10011/11OK2m 34s
CG-AL-M010easy262.5 / 10019/21OK2m 25s
CG-AL-M020easy262.5 / 10015/17OK2m 21s
CG-AL-M021easy20.0 / 1000/0FAIL6.4s
CG-AL-M022easy2100.0 / 1009/9OK2m 18s
CG-AL-M023easy1100.0 / 10011/11OK2m 17s
CG-AL-M024easy2100.0 / 10010/10OK2m 23s
CG-AL-M025easy262.5 / 1002/7OK2m 18s
CG-AL-M026easy1100.0 / 1008/8OK2m 18s
CG-AL-M088easy1100.0 / 1006/6OK2m 19s
CG-AL-M112easy262.5 / 1002/4OK2m 21s