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.

39.6 / 100
Cost $1.41
Tokens 78k / 575k input / output, all attempts
Duration 4h 43m
Filter:
Per-task results for run bc365892-44dd-4cd2-a55c-aa9a304403f8
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK2m 51s273 / 2.4k
CG-AL-E002easy1100.0 / 1006/6OK3m 2s286 / 3.2k
CG-AL-E003easy2100.0 / 1005/5OK4m 24s853 / 4.3k
CG-AL-E004easy1100.0 / 1006/6OK3m 0s296 / 2.9k
CG-AL-E005easy2100.0 / 10013/13OK4m 13s1.0k / 7.4k
CG-AL-E006easy20.0 / 1000/0FAIL2m 6s1.0k / 8.5k
CG-AL-E007easy1100.0 / 1007/7OK3m 38s352 / 2.5k
CG-AL-E008easy20.0 / 1000/0FAIL2m 9s1.1k / 9.1k
CG-AL-E009easy20.0 / 1000/0FAIL1m 11s875 / 6.2k
CG-AL-E010easy2100.0 / 1005/5OK3m 26s710 / 6.6k
CG-AL-E031easy1100.0 / 1003/3OK5m 4s415 / 4.5k
CG-AL-E032easy1100.0 / 1001/1OK4m 33s230 / 1.3k
CG-AL-E045easy1100.0 / 1004/4OK3m 18s378 / 4.2k
CG-AL-E050easy20.0 / 1000/0FAIL1m 54s2.0k / 12k
CG-AL-E051easy1100.0 / 10015/15OK4m 3s494 / 7.3k
CG-AL-E052easy262.5 / 10014/16OK3m 50s963 / 9.9k
CG-AL-E053easy20.0 / 1000/0FAIL43.7s882 / 6.0k
CG-AL-E054easy2100.0 / 1009/9OK2m 44s1.1k / 4.9k
CG-AL-E055easy2100.0 / 1008/8OK2m 48s929 / 5.3k
CG-AL-H001easy1100.0 / 10025/25OK3m 12s478 / 3.9k
CG-AL-H002easy1100.0 / 1004/4OK3m 6s455 / 3.6k
CG-AL-H003easy262.5 / 1004/5OK3m 54s1.5k / 11k
CG-AL-H004easy1100.0 / 10014/14OK3m 19s509 / 4.3k
CG-AL-H005easy20.0 / 1000/0FAIL1m 49s1.8k / 12k
CG-AL-H006easy1100.0 / 1006/6OK2m 50s430 / 2.4k
CG-AL-H007easy20.0 / 1000/0FAIL1m 47s1.7k / 12k
CG-AL-H008easy262.5 / 1008/10OK3m 5s1.7k / 7.4k
CG-AL-H009easy1100.0 / 10011/11OK3m 35s607 / 5.4k
CG-AL-H010easy1100.0 / 1008/8OK3m 13s517 / 3.9k
CG-AL-H011easy20.0 / 1000/0FAIL1m 12s1.0k / 7.8k
CG-AL-H013easy1100.0 / 1009/9OK3m 11s377 / 3.9k
CG-AL-H014easy20.0 / 1000/0FAIL45.4s1.4k / 7.1k
CG-AL-H015easy2100.0 / 1004/4OK3m 9s1.2k / 7.8k
CG-AL-H016easy262.5 / 1003/4OK4m 11s1.1k / 13k
CG-AL-H017easy20.0 / 1000/0FAIL1m 28s1.1k / 11k
CG-AL-H018easy2100.0 / 1006/6OK3m 26s1.6k / 11k
CG-AL-H019easy2100.0 / 1005/5OK2m 42s878 / 4.3k
CG-AL-H020easy20.0 / 1000/0FAIL1m 26s2.4k / 12k
CG-AL-H021easy20.0 / 1000/0FAIL1m 14s2.0k / 9.2k
CG-AL-H022easy20.0 / 1000/0FAIL3m 38s2.4k / 16k
CG-AL-H023easy20.0 / 1000/0FAIL5m 19s3.8k / 30k
CG-AL-H024easy2100.0 / 1009/9OK4m 49s1.8k / 11k
CG-AL-H025easy1100.0 / 1007/7OK3m 17s378 / 4.3k
CG-AL-H026easy1100.0 / 1008/8OK4m 9s475 / 3.3k
CG-AL-H205easy2100.0 / 1006/6OK3m 40s1.2k / 9.3k
CG-AL-M001easy20.0 / 1000/0FAIL52.3s1.4k / 8.7k
CG-AL-M002easy1100.0 / 10022/22OK3m 36s431 / 5.6k
CG-AL-M003easy262.5 / 1008/9OK3m 1s1.6k / 10.0k
CG-AL-M004easy20.0 / 1000/0FAIL1m 23s1.7k / 12k
CG-AL-M005easy20.0 / 1000/0FAIL2m 38s2.2k / 19k
CG-AL-M006easy20.0 / 1000/0FAIL1m 36s2.2k / 17k
CG-AL-M007easy20.0 / 1000/0FAIL1m 51s2.2k / 16k
CG-AL-M008easy20.0 / 1000/0FAIL2m 41s2.5k / 22k
CG-AL-M009easy2100.0 / 10011/11OK5m 7s2.6k / 22k
CG-AL-M010easy262.5 / 10018/21OK4m 37s2.2k / 17k
CG-AL-M020easy20.0 / 1000/0FAIL1m 19s2.1k / 12k
CG-AL-M021easy20.0 / 1000/0FAIL1m 59s1.9k / 13k
CG-AL-M022easy20.0 / 1000/0FAIL2m 11s1.9k / 15k
CG-AL-M023easy1100.0 / 10011/11OK3m 32s509 / 5.1k
CG-AL-M024easy2100.0 / 10010/10OK4m 18s1.9k / 16k
CG-AL-M025easy262.5 / 1002/7OK3m 34s1.2k / 9.1k
CG-AL-M026easy1100.0 / 1008/8OK4m 33s390 / 5.1k
CG-AL-M088easy1100.0 / 1006/6OK3m 29s416 / 5.0k
CG-AL-M112easy262.5 / 1002/4OK3m 50s1.8k / 11k