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.

73.0% 46/63 of 63 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.

63.6 / 100
Cost $4.05
Tokens 130k / 136k input / output, all attempts
Duration 2h 55m
Filter:
Per-task results for run 16e667f8-6a0b-469c-a8bb-11022eb4ce53
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK2m 35s418 / 433
CG-AL-E002easy1100.0 / 1006/6OK2m 23s433 / 377
CG-AL-E003easy1100.0 / 1005/5OK2m 36s410 / 166
CG-AL-E004easy1100.0 / 1006/6OK2m 36s470 / 367
CG-AL-E005easy2100.0 / 10013/13OK2m 41s1.6k / 1.1k
CG-AL-E006easy1100.0 / 1007/7OK2m 46s470 / 594
CG-AL-E007easy1100.0 / 1007/7OK2m 48s558 / 242
CG-AL-E008easy1100.0 / 1006/6OK2m 53s470 / 490
CG-AL-E009easy1100.0 / 1005/5OK2m 51s442 / 254
CG-AL-E010easy1100.0 / 1005/5OK2m 56s467 / 198
CG-AL-E031easy1100.0 / 1003/3OK3m 5s678 / 659
CG-AL-E032easy1100.0 / 1001/1OK3m 2s377 / 89
CG-AL-E045easy1100.0 / 1004/4OK2m 32s565 / 440
CG-AL-E050easy2100.0 / 10013/13OK2m 28s3.0k / 604
CG-AL-E051easy1100.0 / 10015/15OK2m 34s776 / 812
CG-AL-E052easy2100.0 / 10016/16OK2m 28s1.6k / 763
CG-AL-E053easy1100.0 / 1003/3OK2m 31s461 / 171
CG-AL-E054easy2100.0 / 1009/9OK2m 30s1.7k / 632
CG-AL-E055easy1100.0 / 1008/8OK2m 30s566 / 306
CG-AL-H001hard1100.0 / 10025/25OK2m 31s726 / 427
CG-AL-H002hard1100.0 / 1004/4OK2m 35s747 / 777
CG-AL-H003hard262.5 / 1004/5OK2m 31s2.4k / 1.8k
CG-AL-H004hard1100.0 / 10014/14OK2m 32s779 / 601
CG-AL-H005hard262.5 / 1002/5OK2m 34s3.0k / 2.6k
CG-AL-H006hard1100.0 / 1006/6OK2m 28s715 / 365
CG-AL-H007hard1100.0 / 10010/10OK2m 33s952 / 969
CG-AL-H008hard1100.0 / 10010/10OK2m 31s886 / 586
CG-AL-H009hard1100.0 / 10011/11OK2m 35s1.0k / 1.3k
CG-AL-H010hard1100.0 / 1008/8OK2m 30s901 / 632
CG-AL-H011hard20.0 / 1000/0FAIL12.7s1.6k / 559
CG-AL-H013hard1100.0 / 1009/9OK2m 31s607 / 464
CG-AL-H014hard20.0 / 1000/0FAIL14.4s2.4k / 1.4k
CG-AL-H015hard1100.0 / 1004/4OK2m 33s663 / 449
CG-AL-H016hard20.0 / 1000/0FAIL13.2s2.0k / 945
CG-AL-H017hard20.0 / 1000/0FAIL12.7s1.6k / 708
CG-AL-H018hard1100.0 / 1006/6OK2m 31s732 / 808
CG-AL-H019hard1100.0 / 1005/5OK2m 27s533 / 233
CG-AL-H020hard2100.0 / 10010/10OK2m 32s2.8k / 2.1k
CG-AL-H021hard262.5 / 1006/20OK2m 33s3.3k / 2.1k
CG-AL-H022hard1100.0 / 10021/21OK2m 30s1.2k / 1.5k
CG-AL-H023hard20.0 / 1000/0FAIL2m 14s21k / 22k
CG-AL-H025hard1100.0 / 1007/7OK2m 29s575 / 453
CG-AL-H026hard20.0 / 1000/0FAIL15.5s3.3k / 1.1k
CG-AL-H205hard1100.0 / 1006/6OK2m 33s784 / 664
CG-AL-M001medium262.5 / 1004/10OK2m 34s2.8k / 3.3k
CG-AL-M002medium1100.0 / 10022/22OK2m 34s730 / 940
CG-AL-M003medium262.5 / 1008/9OK2m 31s2.4k / 2.2k
CG-AL-M004medium1100.0 / 10012/12OK2m 48s778 / 1.5k
CG-AL-M005medium262.5 / 10012/22OK2m 44s3.7k / 6.3k
CG-AL-M006medium2100.0 / 10018/18OK2m 39s3.0k / 3.6k
CG-AL-M007medium20.0 / 1000/0FAIL2m 26s12k / 20k
CG-AL-M008medium20.0 / 1000/0FAIL2m 17s15k / 20k
CG-AL-M009medium1100.0 / 10011/11OK2m 47s751 / 2.5k
CG-AL-M010medium262.5 / 10019/21OK3m 5s5.3k / 7.9k
CG-AL-M020medium2100.0 / 10017/17OK2m 34s3.0k / 2.0k
CG-AL-M021medium1100.0 / 10014/14OK2m 50s802 / 2.5k
CG-AL-M022medium1100.0 / 1009/9OK2m 34s815 / 1.1k
CG-AL-M023medium1100.0 / 10011/11OK2m 30s808 / 741
CG-AL-M024medium1100.0 / 10010/10OK2m 37s762 / 1.7k
CG-AL-M025medium1100.0 / 1007/7OK2m 25s660 / 507
CG-AL-M026medium20.0 / 1000/0FAIL14.6s2.3k / 1.3k
CG-AL-M088medium1100.0 / 1006/6OK2m 29s678 / 643
CG-AL-M112medium262.5 / 1002/4OK2m 27s2.9k / 2.2k