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.

50.0% 32/64 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.

37.8 / 100
Cost $1.65
Tokens 85k / 673k input / output, all attempts
Duration 5h 18m
Filter:
Per-task results for run 9a9a4d0e-ca69-4c5d-9755-d9bf674abcfe
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK3m 8s273 / 3.1k
CG-AL-E002easy20.0 / 1000/0FAIL21m 32s986 / 85k
CG-AL-E003easy1100.0 / 1005/5OK2m 50s271 / 2.1k
CG-AL-E004easy2100.0 / 1006/6OK3m 48s1.1k / 5.5k
CG-AL-E005easy2100.0 / 10013/13OK4m 10s971 / 9.8k
CG-AL-E006easy20.0 / 1000/0FAIL1m 45s1.1k / 8.1k
CG-AL-E007easy1100.0 / 1007/7OK3m 55s352 / 2.8k
CG-AL-E008easy20.0 / 1000/0FAIL1m 47s1.1k / 5.5k
CG-AL-E009easy20.0 / 1000/0FAIL1m 40s829 / 9.2k
CG-AL-E010easy2100.0 / 1005/5OK3m 7s712 / 4.1k
CG-AL-E031easy1100.0 / 1003/3OK4m 57s415 / 4.1k
CG-AL-E032easy1100.0 / 1001/1OK4m 36s230 / 1.7k
CG-AL-E045easy1100.0 / 1004/4OK3m 13s378 / 3.6k
CG-AL-E050easy20.0 / 1000/0FAIL1m 21s2.0k / 9.6k
CG-AL-E051easy262.5 / 1003/15OK4m 47s1.7k / 20k
CG-AL-E052easy2100.0 / 10016/16OK3m 47s949 / 8.6k
CG-AL-E053easy1100.0 / 1003/3OK3m 15s311 / 3.0k
CG-AL-E054easy2100.0 / 1009/9OK3m 21s1.2k / 7.0k
CG-AL-E055easy1100.0 / 1008/8OK3m 7s349 / 2.5k
CG-AL-H001easy1100.0 / 10025/25OK3m 22s478 / 3.6k
CG-AL-H002easy1100.0 / 1004/4OK3m 36s455 / 4.2k
CG-AL-H003easy2100.0 / 1005/5OK3m 47s1.5k / 9.1k
CG-AL-H004easy2100.0 / 10014/14OK3m 20s1.7k / 7.3k
CG-AL-H005easy262.5 / 1002/5OK4m 51s1.9k / 15k
CG-AL-H006easy2100.0 / 1006/6OK2m 58s1.2k / 5.2k
CG-AL-H007easy20.0 / 1000/0FAIL1m 56s1.7k / 13k
CG-AL-H008easy1100.0 / 10010/10OK3m 29s523 / 4.0k
CG-AL-H009easy1100.0 / 10011/11OK3m 46s607 / 5.3k
CG-AL-H010easy1100.0 / 1008/8OK3m 29s517 / 3.8k
CG-AL-H011easy20.0 / 1000/0FAIL58.8s1.0k / 5.7k
CG-AL-H013easy1100.0 / 1009/9OK3m 47s377 / 5.3k
CG-AL-H014easy20.0 / 1000/0FAIL56.4s1.5k / 7.8k
CG-AL-H015easy2100.0 / 1004/4OK3m 12s1.2k / 6.4k
CG-AL-H016easy20.0 / 1000/0FAIL47.2s1.3k / 7.0k
CG-AL-H017easy20.0 / 1000/0FAIL1m 33s1.1k / 11k
CG-AL-H018easy20.0 / 1000/0FAIL1m 18s2.1k / 11k
CG-AL-H019easy2100.0 / 1005/5OK3m 27s876 / 4.0k
CG-AL-H020easy20.0 / 1000/0FAIL1m 58s2.5k / 15k
CG-AL-H021easy262.5 / 1006/20OK3m 48s2.0k / 7.8k
CG-AL-H022easy20.0 / 1000/0FAIL2m 10s2.4k / 16k
CG-AL-H023easy20.0 / 1000/0FAIL4m 0s3.7k / 29k
CG-AL-H024easy262.5 / 1008/9OK4m 29s1.8k / 12k
CG-AL-H025easy2100.0 / 1007/7OK4m 1s1.6k / 6.1k
CG-AL-H026easy2100.0 / 1008/8OK3m 14s1.3k / 7.9k
CG-AL-H205easy2100.0 / 1006/6OK3m 45s1.2k / 9.1k
CG-AL-M001easy20.0 / 1000/0FAIL1m 45s1.6k / 10k
CG-AL-M002easy2100.0 / 10022/22OK3m 47s1.7k / 10k
CG-AL-M003easy262.5 / 1008/9OK3m 52s1.7k / 14k
CG-AL-M004easy20.0 / 1000/0FAIL1m 11s1.9k / 12k
CG-AL-M005easy20.0 / 1000/0FAIL2m 25s3.5k / 20k
CG-AL-M006easy262.5 / 10015/18OK4m 5s2.0k / 16k
CG-AL-M007easy20.0 / 1000/0FAIL2m 28s2.1k / 18k
CG-AL-M008easy20.0 / 1000/0FAIL2m 44s2.2k / 26k
CG-AL-M009easy20.0 / 1000/0FAIL2m 25s2.2k / 18k
CG-AL-M010easy262.5 / 10019/21OK6m 32s2.4k / 17k
CG-AL-M020easy20.0 / 1000/0FAIL2m 45s2.1k / 10k
CG-AL-M021easy20.0 / 1000/0FAIL3m 1s1.7k / 12k
CG-AL-M022easy20.0 / 1000/0FAIL1m 39s1.7k / 12k
CG-AL-M023easy1100.0 / 10011/11OK4m 25s509 / 5.2k
CG-AL-M024easy2100.0 / 10010/10OK3m 49s2.4k / 14k
CG-AL-M025easy262.5 / 1002/7OK4m 4s1.3k / 10k
CG-AL-M026easy1100.0 / 1008/8OK4m 6s390 / 4.2k
CG-AL-M088easy1100.0 / 1006/6OK3m 38s416 / 4.7k
CG-AL-M112easy262.5 / 1002/4OK4m 15s1.8k / 12k