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.

73.4% 47/64 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.

59.8 / 100
Cost $9.25
Tokens 66k / 297k input / output, all attempts
Duration 3h 39m
Filter:
Per-task results for run 71c98551-f4a2-4c8b-9cfe-d0b168ab51e3
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK2m 29s258 / 702
CG-AL-E002easy1100.0 / 1006/6OK2m 28s272 / 715
CG-AL-E003easy1100.0 / 1005/5OK2m 25s259 / 243
CG-AL-E004easy1100.0 / 1006/6OK2m 25s279 / 411
CG-AL-E005easy1100.0 / 10013/13OK2m 56s293 / 1.9k
CG-AL-E006easy1100.0 / 1007/7OK3m 33s284 / 3.4k
CG-AL-E007easy1100.0 / 1007/7OK2m 36s345 / 684
CG-AL-E008easy20.0 / 1000/0FAIL30.9s999 / 1.9k
CG-AL-E009easy1100.0 / 1005/5OK2m 42s271 / 677
CG-AL-E010easy1100.0 / 1005/5OK2m 41s275 / 320
CG-AL-E031easy1100.0 / 1003/3OK2m 43s401 / 759
CG-AL-E032easy1100.0 / 1001/1OK2m 46s221 / 450
CG-AL-E045easy1100.0 / 1004/4OK2m 31s360 / 797
CG-AL-E050easy2100.0 / 10013/13OK2m 48s1.9k / 4.6k
CG-AL-E051easy1100.0 / 10015/15OK3m 21s455 / 3.8k
CG-AL-E052easy2100.0 / 10016/16OK2m 26s903 / 1.2k
CG-AL-E053easy1100.0 / 1003/3OK2m 28s293 / 579
CG-AL-E054easy20.0 / 1000/0FAIL17.5s975 / 1.4k
CG-AL-E055easy1100.0 / 1008/8OK2m 28s332 / 729
CG-AL-H001easy1100.0 / 10025/25OK2m 25s453 / 771
CG-AL-H002easy1100.0 / 1004/4OK2m 49s425 / 2.0k
CG-AL-H003easy1100.0 / 1005/5OK2m 31s464 / 1.0k
CG-AL-H004easy1100.0 / 10014/14OK2m 51s474 / 2.0k
CG-AL-H005easy262.5 / 1002/5OK2m 35s2.0k / 5.0k
CG-AL-H006easy1100.0 / 1006/6OK2m 28s421 / 548
CG-AL-H007easy2100.0 / 10010/10OK2m 32s2.1k / 9.0k
CG-AL-H008easy1100.0 / 10010/10OK2m 29s504 / 876
CG-AL-H009easy1100.0 / 10011/11OK2m 49s574 / 2.2k
CG-AL-H010easy1100.0 / 1008/8OK2m 28s493 / 839
CG-AL-H011easy1100.0 / 1005/5OK2m 56s352 / 2.2k
CG-AL-H013easy1100.0 / 1009/9OK2m 29s358 / 771
CG-AL-H014easy20.0 / 1000/0FAIL15.3s1.4k / 1.9k
CG-AL-H015easy1100.0 / 1004/4OK2m 28s387 / 744
CG-AL-H016easy20.0 / 1000/0FAIL14.8s1.3k / 6.5k
CG-AL-H017easy2100.0 / 1003/3OK2m 28s1.0k / 3.7k
CG-AL-H018easy1100.0 / 1006/6OK3m 49s840 / 5.6k
CG-AL-H019easy1100.0 / 1005/5OK2m 40s310 / 1.7k
CG-AL-H020easy2100.0 / 10010/10OK2m 45s1.8k / 5.9k
CG-AL-H021easy262.5 / 1006/20OK2m 29s1.9k / 2.6k
CG-AL-H022easy1100.0 / 10021/21OK4m 17s1.4k / 7.1k
CG-AL-H023easy20.0 / 1000/0FAIL3m 47s7.1k / 24k
CG-AL-H024easy1100.0 / 1009/9OK3m 16s508 / 3.8k
CG-AL-H025easy1100.0 / 1007/7OK2m 30s356 / 698
CG-AL-H026easy1100.0 / 1008/8OK2m 57s443 / 2.4k
CG-AL-H205easy1100.0 / 1006/6OK2m 26s434 / 865
CG-AL-M001easy20.0 / 1000/0FAIL38.1s1.4k / 6.3k
CG-AL-M002easy1100.0 / 10022/22OK2m 41s403 / 1.5k
CG-AL-M003easy262.5 / 1008/9OK3m 0s1.8k / 7.8k
CG-AL-M004easy1100.0 / 10012/12OK2m 49s449 / 1.7k
CG-AL-M005easy20.0 / 1000/0FAIL3m 39s3.0k / 24k
CG-AL-M006easy20.0 / 1000/0FAIL3m 26s2.4k / 24k
CG-AL-M007easy20.0 / 1000/0FAIL3m 26s2.5k / 24k
CG-AL-M008easy20.0 / 1000/0FAIL3m 54s2.9k / 24k
CG-AL-M009easy20.0 / 1000/0FAIL2m 24s1.7k / 12k
CG-AL-M010easy20.0 / 1000/0FAIL1m 16s2.3k / 16k
CG-AL-M020easy2100.0 / 10017/17OK2m 31s2.2k / 5.2k
CG-AL-M021easy1100.0 / 10011/11OK2m 29s547 / 1.0k
CG-AL-M022easy2100.0 / 1009/9OK2m 39s2.0k / 14k
CG-AL-M023easy1100.0 / 10011/11OK2m 29s482 / 935
CG-AL-M024easy1100.0 / 10010/10OK2m 34s477 / 1.3k
CG-AL-M025easy262.5 / 1002/7OK3m 25s1.2k / 5.9k
CG-AL-M026easy2100.0 / 1008/8OK2m 31s1.1k / 3.8k
CG-AL-M088easy1100.0 / 1006/6OK2m 32s391 / 865
CG-AL-M112easy262.5 / 1002/4OK2m 57s1.7k / 3.6k