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.

51.6% 33/64 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.

37.7 / 100
Cost $1.61
Tokens 86k / 657k input / output, all attempts
Duration 5h 13m
Filter:
Per-task results for run 2e16b76a-74d2-4f6e-9edf-776aa2fc9e8c
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK3m 8s273 / 2.8k
CG-AL-E002easy1100.0 / 1006/6OK3m 11s286 / 3.3k
CG-AL-E003easy2100.0 / 1005/5OK3m 43s847 / 4.2k
CG-AL-E004easy2100.0 / 1006/6OK4m 31s1.9k / 7.5k
CG-AL-E005easy1100.0 / 10013/13OK3m 21s303 / 3.5k
CG-AL-E006easy2100.0 / 1007/7OK3m 53s926 / 8.1k
CG-AL-E007easy1100.0 / 1007/7OK3m 50s352 / 2.4k
CG-AL-E008easy2100.0 / 1006/6OK3m 51s1.1k / 5.3k
CG-AL-E009easy2100.0 / 1005/5OK3m 12s762 / 4.9k
CG-AL-E010easy1100.0 / 1005/5OK4m 32s286 / 2.9k
CG-AL-E031easy1100.0 / 1003/3OK5m 4s415 / 3.8k
CG-AL-E032easy2100.0 / 1001/1OK2m 54s594 / 3.3k
CG-AL-E045easy1100.0 / 1004/4OK3m 26s378 / 4.2k
CG-AL-E050easy20.0 / 1000/0FAIL1m 33s2.1k / 11k
CG-AL-E051easy2100.0 / 10015/15OK4m 41s1.7k / 18k
CG-AL-E052easy262.5 / 10014/16OK4m 9s963 / 9.8k
CG-AL-E053easy1100.0 / 1003/3OK3m 24s311 / 4.0k
CG-AL-E054easy2100.0 / 1009/9OK2m 52s1.1k / 5.8k
CG-AL-E055easy1100.0 / 1008/8OK3m 0s349 / 2.7k
CG-AL-H001easy1100.0 / 10025/25OK3m 18s478 / 3.9k
CG-AL-H002easy1100.0 / 1004/4OK3m 22s455 / 4.2k
CG-AL-H003easy262.5 / 1004/5OK3m 11s1.6k / 8.3k
CG-AL-H004easy2100.0 / 10014/14OK3m 5s1.7k / 7.1k
CG-AL-H005easy262.5 / 1002/5OK4m 16s2.3k / 17k
CG-AL-H006easy1100.0 / 1006/6OK2m 47s430 / 1.9k
CG-AL-H007easy20.0 / 1000/0FAIL20m 41s1.7k / 88k
CG-AL-H008easy1100.0 / 10010/10OK3m 7s523 / 3.2k
CG-AL-H009easy1100.0 / 10011/11OK3m 36s607 / 5.1k
CG-AL-H010easy1100.0 / 1008/8OK3m 9s517 / 3.3k
CG-AL-H011easy20.0 / 1000/0FAIL1m 16s1.0k / 8.1k
CG-AL-H013easy1100.0 / 1009/9OK3m 12s377 / 3.5k
CG-AL-H014easy20.0 / 1000/0FAIL54.1s1.4k / 8.2k
CG-AL-H015easy20.0 / 1000/0FAIL1m 4s1.4k / 7.8k
CG-AL-H016easy20.0 / 1000/0FAIL2m 6s1.3k / 12k
CG-AL-H017easy20.0 / 1000/0FAIL1m 19s1.1k / 9.6k
CG-AL-H018easy20.0 / 1000/0FAIL2m 9s2.5k / 15k
CG-AL-H019easy2100.0 / 1005/5OK2m 51s880 / 5.1k
CG-AL-H020easy2100.0 / 10010/10OK3m 8s2.4k / 13k
CG-AL-H021easy20.0 / 1000/0FAIL1m 6s2.0k / 8.2k
CG-AL-H022easy20.0 / 1000/0FAIL2m 43s2.3k / 15k
CG-AL-H023easy20.0 / 1000/0FAIL5m 17s4.5k / 36k
CG-AL-H024easy20.0 / 1000/0FAIL2m 0s1.8k / 13k
CG-AL-H025easy20.0 / 1000/0FAIL1m 21s1.1k / 6.1k
CG-AL-H026easy1100.0 / 1008/8OK3m 54s475 / 4.3k
CG-AL-H205easy2100.0 / 1006/6OK3m 34s1.2k / 8.2k
CG-AL-M001easy20.0 / 1000/0FAIL52.4s1.7k / 7.7k
CG-AL-M002easy20.0 / 1000/0FAIL1m 58s1.4k / 11k
CG-AL-M003easy20.0 / 1000/0FAIL1m 34s2.5k / 14k
CG-AL-M004easy20.0 / 1000/0FAIL1m 19s2.4k / 12k
CG-AL-M005easy20.0 / 1000/0FAIL2m 10s2.9k / 16k
CG-AL-M006easy262.5 / 10015/18OK4m 1s2.4k / 14k
CG-AL-M007easy20.0 / 1000/0FAIL2m 42s2.6k / 18k
CG-AL-M008easy20.0 / 1000/0FAIL3m 15s2.0k / 17k
CG-AL-M009easy2100.0 / 10011/11OK6m 14s2.0k / 18k
CG-AL-M010easy262.5 / 10019/21OK6m 8s2.3k / 19k
CG-AL-M020easy20.0 / 1000/0FAIL2m 14s1.9k / 12k
CG-AL-M021easy20.0 / 1000/0FAIL3m 8s1.9k / 13k
CG-AL-M022easy20.0 / 1000/0FAIL1m 51s1.9k / 11k
CG-AL-M023easy1100.0 / 10011/11OK5m 52s509 / 5.6k
CG-AL-M024easy2100.0 / 10010/10OK4m 33s2.2k / 12k
CG-AL-M025easy262.5 / 1002/7OK3m 53s1.3k / 11k
CG-AL-M026easy20.0 / 1000/0FAIL1m 2s1.2k / 8.3k
CG-AL-M088easy1100.0 / 1006/6OK3m 29s416 / 4.8k
CG-AL-M112easy262.5 / 1002/4OK3m 44s1.8k / 11k