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.

70.3% 45/64 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.

61.8 / 100
Cost $0.67
Tokens 70k / 233k input / output, all attempts
Duration 3h 32m
Filter:
Per-task results for run 8306da4a-2147-463d-ae9b-1e1b7aeb4fdd
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK2m 42s381 / 1.4k
CG-AL-E002easy2100.0 / 1006/6OK3m 19s909 / 4.8k
CG-AL-E003easy1100.0 / 1005/5OK2m 48s382 / 1.5k
CG-AL-E004easy1100.0 / 1006/6OK2m 45s402 / 1.5k
CG-AL-E005easy1100.0 / 10013/13OK2m 45s416 / 1.7k
CG-AL-E006easy2100.0 / 1007/7OK3m 12s2.0k / 5.8k
CG-AL-E007easy1100.0 / 1007/7OK3m 12s468 / 1.5k
CG-AL-E008easy2100.0 / 1006/6OK2m 51s1.2k / 3.1k
CG-AL-E009easy1100.0 / 1005/5OK3m 17s394 / 1.5k
CG-AL-E010easy2100.0 / 1005/5OK2m 50s913 / 2.2k
CG-AL-E031easy1100.0 / 1003/3OK3m 32s524 / 1.7k
CG-AL-E032easy1100.0 / 1001/1OK3m 23s343 / 910
CG-AL-E045easy1100.0 / 1004/4OK3m 10s483 / 2.0k
CG-AL-E050easy262.5 / 10011/13OK3m 3s1.9k / 6.7k
CG-AL-E051easy1100.0 / 10015/15OK3m 7s576 / 2.6k
CG-AL-E052easy20.0 / 1000/0FAIL1m 5s1.1k / 4.8k
CG-AL-E053easy1100.0 / 1003/3OK2m 47s416 / 2.2k
CG-AL-E054easy2100.0 / 1009/9OK3m 2s1.3k / 3.3k
CG-AL-E055easy1100.0 / 1008/8OK2m 29s455 / 1.0k
CG-AL-H001easy1100.0 / 10025/25OK2m 34s575 / 1.0k
CG-AL-H002easy1100.0 / 1004/4OK2m 41s546 / 1.8k
CG-AL-H003easy1100.0 / 1005/5OK2m 37s587 / 1.6k
CG-AL-H004easy1100.0 / 10014/14OK2m 37s597 / 1.4k
CG-AL-H005easy262.5 / 1002/5OK3m 12s1.9k / 6.6k
CG-AL-H006easy1100.0 / 1006/6OK2m 26s541 / 909
CG-AL-H007easy1100.0 / 10010/10OK2m 42s666 / 2.7k
CG-AL-H008easy1100.0 / 10010/10OK2m 40s627 / 2.2k
CG-AL-H009easy1100.0 / 10011/11OK2m 51s691 / 2.4k
CG-AL-H010easy1100.0 / 1008/8OK2m 39s612 / 2.1k
CG-AL-H011easy20.0 / 1000/0FAIL1m 0s1.2k / 6.3k
CG-AL-H013easy1100.0 / 1009/9OK2m 38s481 / 1.3k
CG-AL-H014easy20.0 / 1000/0FAIL28.9s1.7k / 3.8k
CG-AL-H015easy1100.0 / 1004/4OK2m 38s510 / 1.1k
CG-AL-H016easy262.5 / 1003/4OK2m 47s1.2k / 3.1k
CG-AL-H017easy20.0 / 1000/0FAIL55.6s1.3k / 6.3k
CG-AL-H018easy1100.0 / 1006/6OK2m 48s542 / 2.2k
CG-AL-H019easy2100.0 / 1005/5OK2m 25s1.1k / 1.5k
CG-AL-H020easy20.0 / 1000/0FAIL41.3s2.0k / 5.2k
CG-AL-H021easy262.5 / 1006/20OK2m 36s2.1k / 3.3k
CG-AL-H022easy2100.0 / 10021/21OK2m 39s2.7k / 4.4k
CG-AL-H023easy20.0 / 1000/0FAIL2m 20s4.4k / 13k
CG-AL-H024easy1100.0 / 1009/9OK2m 51s631 / 2.1k
CG-AL-H025easy1100.0 / 1007/7OK2m 41s479 / 1.9k
CG-AL-H026easy1100.0 / 1008/8OK2m 36s566 / 1.6k
CG-AL-H205easy1100.0 / 1006/6OK2m 38s551 / 1.7k
CG-AL-M001easy262.5 / 1005/10OK3m 17s1.4k / 5.9k
CG-AL-M002easy1100.0 / 10022/22OK2m 43s527 / 2.3k
CG-AL-M003easy262.5 / 1003/9OK2m 49s1.7k / 5.6k
CG-AL-M004easy1100.0 / 10012/12OK3m 10s571 / 3.1k
CG-AL-M005easy262.5 / 10014/22OK3m 1s2.1k / 6.7k
CG-AL-M006easy1100.0 / 10018/18OK3m 3s531 / 3.4k
CG-AL-M007easy20.0 / 1000/0FAIL48.0s2.7k / 7.5k
CG-AL-M008easy20.0 / 1000/0FAIL1m 2s2.4k / 11k
CG-AL-M009easy1100.0 / 10011/11OK3m 16s552 / 4.0k
CG-AL-M010easy262.5 / 10019/21OK2m 59s2.2k / 7.3k
CG-AL-M020easy20.0 / 1000/0FAIL45.2s2.8k / 4.6k
CG-AL-M021easy2100.0 / 10011/11OK3m 23s1.9k / 11k
CG-AL-M022easy2100.0 / 1009/9OK3m 15s2.0k / 5.9k
CG-AL-M023easy1100.0 / 10011/11OK2m 40s605 / 1.5k
CG-AL-M024easy1100.0 / 10010/10OK2m 41s599 / 1.9k
CG-AL-M025easy262.5 / 1002/7OK3m 28s1.3k / 9.7k
CG-AL-M026easy1100.0 / 1008/8OK2m 45s493 / 2.3k
CG-AL-M088easy1100.0 / 1006/6OK2m 40s513 / 1.6k
CG-AL-M112easy262.5 / 1002/4OK3m 7s1.9k / 5.7k