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.

75.0% 48/64 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.

71.1 / 100
Cost $3.47
Tokens 121k / 115k input / output, all attempts
Duration 3h 14m
Filter:
Per-task results for run dffb867d-3c90-44c2-ac80-e06dea8b631e
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK2m 47s418 / 433
CG-AL-E002easy1100.0 / 1006/6OK2m 48s433 / 377
CG-AL-E003easy1100.0 / 1005/5OK2m 59s410 / 166
CG-AL-E004easy1100.0 / 1006/6OK2m 58s470 / 367
CG-AL-E005easy1100.0 / 10013/13OK2m 58s491 / 614
CG-AL-E006easy1100.0 / 1007/7OK3m 7s470 / 595
CG-AL-E007easy1100.0 / 1007/7OK3m 9s558 / 242
CG-AL-E008easy1100.0 / 1006/6OK3m 14s470 / 506
CG-AL-E009easy1100.0 / 1005/5OK3m 15s442 / 239
CG-AL-E010easy1100.0 / 1005/5OK3m 20s467 / 188
CG-AL-E031easy1100.0 / 1003/3OK3m 27s678 / 659
CG-AL-E032easy1100.0 / 1001/1OK3m 28s377 / 89
CG-AL-E045easy1100.0 / 1004/4OK2m 39s565 / 604
CG-AL-E050easy262.5 / 10011/13OK2m 37s3.0k / 708
CG-AL-E051easy1100.0 / 10015/15OK2m 39s776 / 941
CG-AL-E052easy2100.0 / 10016/16OK2m 33s1.6k / 763
CG-AL-E053easy1100.0 / 1003/3OK2m 38s461 / 176
CG-AL-E054easy2100.0 / 1009/9OK2m 38s1.7k / 694
CG-AL-E055easy1100.0 / 1008/8OK2m 37s566 / 306
CG-AL-H001easy1100.0 / 10025/25OK2m 35s726 / 428
CG-AL-H002easy1100.0 / 1004/4OK2m 39s747 / 767
CG-AL-H003easy262.5 / 1004/5OK2m 34s2.4k / 1.8k
CG-AL-H004easy1100.0 / 10014/14OK2m 37s779 / 625
CG-AL-H005easy262.5 / 1002/5OK2m 38s3.1k / 2.6k
CG-AL-H006easy1100.0 / 1006/6OK2m 35s715 / 365
CG-AL-H007easy1100.0 / 10010/10OK2m 40s952 / 926
CG-AL-H008easy1100.0 / 10010/10OK2m 34s886 / 586
CG-AL-H009easy1100.0 / 10011/11OK2m 38s1.0k / 1.3k
CG-AL-H010easy1100.0 / 1008/8OK2m 37s901 / 632
CG-AL-H011easy20.0 / 1000/0FAIL8.6s1.6k / 571
CG-AL-H013easy1100.0 / 1009/9OK2m 36s607 / 464
CG-AL-H014easy20.0 / 1000/0FAIL10.7s2.4k / 1.4k
CG-AL-H015easy1100.0 / 1004/4OK2m 37s663 / 449
CG-AL-H016easy262.5 / 1003/4OK2m 26s1.7k / 830
CG-AL-H017easy20.0 / 1000/0FAIL8.6s1.6k / 708
CG-AL-H018easy1100.0 / 1006/6OK2m 29s732 / 829
CG-AL-H019easy1100.0 / 1005/5OK2m 25s533 / 233
CG-AL-H020easy262.5 / 1009/10OK2m 33s2.8k / 2.2k
CG-AL-H021easy2100.0 / 10020/20OK2m 30s3.3k / 2.2k
CG-AL-H022easy1100.0 / 10021/21OK2m 36s1.2k / 1.5k
CG-AL-H023easy20.0 / 1000/0FAIL2m 30s26k / 22k
CG-AL-H024easy1100.0 / 1009/9OK2m 32s852 / 1.3k
CG-AL-H025easy1100.0 / 1007/7OK2m 26s575 / 302
CG-AL-H026easy1100.0 / 1008/8OK2m 27s750 / 467
CG-AL-H205easy1100.0 / 1006/6OK2m 27s784 / 664
CG-AL-M001easy262.5 / 1005/10OK2m 29s2.1k / 1.8k
CG-AL-M002easy1100.0 / 10022/22OK2m 29s730 / 850
CG-AL-M003easy262.5 / 1008/9OK2m 29s2.4k / 2.2k
CG-AL-M004easy1100.0 / 10012/12OK2m 40s778 / 1.5k
CG-AL-M005easy262.5 / 10012/22OK2m 40s3.7k / 6.2k
CG-AL-M006easy1100.0 / 10018/18OK2m 38s710 / 1.9k
CG-AL-M007easy262.5 / 10013/15OK2m 41s3.7k / 5.3k
CG-AL-M008easy20.0 / 1000/0FAIL2m 14s16k / 21k
CG-AL-M009easy1100.0 / 10011/11OK2m 42s751 / 2.3k
CG-AL-M010easy262.5 / 10019/21OK2m 38s3.4k / 5.5k
CG-AL-M020easy2100.0 / 10017/17OK2m 23s3.0k / 2.1k
CG-AL-M021easy2100.0 / 10011/11OK2m 28s2.8k / 1.6k
CG-AL-M022easy1100.0 / 1009/9OK2m 36s815 / 1.1k
CG-AL-M023easy1100.0 / 10011/11OK2m 28s808 / 738
CG-AL-M024easy1100.0 / 10010/10OK2m 32s762 / 1.4k
CG-AL-M025easy1100.0 / 1007/7OK2m 28s660 / 508
CG-AL-M026easy2100.0 / 1008/8OK2m 27s2.3k / 1.2k
CG-AL-M088easy1100.0 / 1006/6OK2m 32s678 / 643
CG-AL-M112easy262.5 / 1002/4OK2m 24s2.8k / 1.9k