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.

73.4% 47/64 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.

69.8 / 100
Cost $3.42
Tokens 118k / 113k input / output, all attempts
Duration 3h 6m
Filter:
Per-task results for run f1d66f25-1f83-4e93-a9d4-e8078ef34342
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK2m 21s418 / 433
CG-AL-E002easy1100.0 / 1006/6OK2m 28s433 / 378
CG-AL-E003easy1100.0 / 1005/5OK2m 31s410 / 166
CG-AL-E004easy1100.0 / 1006/6OK2m 35s470 / 367
CG-AL-E005easy1100.0 / 10013/13OK2m 39s491 / 547
CG-AL-E006easy1100.0 / 1007/7OK2m 48s470 / 595
CG-AL-E007easy1100.0 / 1007/7OK2m 48s558 / 242
CG-AL-E008easy1100.0 / 1006/6OK2m 53s470 / 461
CG-AL-E009easy1100.0 / 1005/5OK2m 57s442 / 229
CG-AL-E010easy1100.0 / 1005/5OK3m 2s467 / 188
CG-AL-E031easy1100.0 / 1003/3OK3m 4s678 / 659
CG-AL-E032easy1100.0 / 1001/1OK3m 9s377 / 89
CG-AL-E045easy1100.0 / 1004/4OK2m 21s565 / 434
CG-AL-E050easy262.5 / 10011/13OK2m 27s3.1k / 712
CG-AL-E051easy1100.0 / 10015/15OK2m 27s776 / 838
CG-AL-E052easy2100.0 / 10016/16OK2m 26s1.6k / 763
CG-AL-E053easy1100.0 / 1003/3OK2m 25s461 / 167
CG-AL-E054easy2100.0 / 1009/9OK2m 20s1.7k / 632
CG-AL-E055easy1100.0 / 1008/8OK2m 19s566 / 301
CG-AL-H001easy1100.0 / 10025/25OK2m 23s726 / 436
CG-AL-H002easy1100.0 / 1004/4OK2m 25s747 / 771
CG-AL-H003easy262.5 / 1004/5OK2m 29s2.4k / 1.8k
CG-AL-H004easy1100.0 / 10014/14OK2m 28s779 / 625
CG-AL-H005easy262.5 / 1002/5OK2m 30s3.0k / 2.5k
CG-AL-H006easy1100.0 / 1006/6OK2m 20s715 / 365
CG-AL-H007easy1100.0 / 10010/10OK2m 25s952 / 972
CG-AL-H008easy1100.0 / 10010/10OK2m 21s886 / 586
CG-AL-H009easy1100.0 / 10011/11OK2m 32s1.0k / 1.3k
CG-AL-H010easy1100.0 / 1008/8OK2m 33s901 / 632
CG-AL-H011easy20.0 / 1000/0FAIL7.6s1.6k / 549
CG-AL-H013easy1100.0 / 1009/9OK2m 29s607 / 453
CG-AL-H014easy20.0 / 1000/0FAIL9.7s2.4k / 1.4k
CG-AL-H015easy1100.0 / 1004/4OK2m 27s663 / 431
CG-AL-H016easy262.5 / 1003/4OK2m 22s1.7k / 762
CG-AL-H017easy20.0 / 1000/0FAIL7.7s1.6k / 708
CG-AL-H018easy1100.0 / 1006/6OK2m 29s732 / 808
CG-AL-H019easy1100.0 / 1005/5OK2m 24s533 / 233
CG-AL-H020easy2100.0 / 10010/10OK2m 29s2.8k / 2.1k
CG-AL-H021easy262.5 / 1006/20OK2m 35s3.3k / 2.2k
CG-AL-H022easy1100.0 / 10021/21OK2m 36s1.2k / 1.5k
CG-AL-H023easy20.0 / 1000/0FAIL2m 11s21k / 22k
CG-AL-H024easy1100.0 / 1009/9OK2m 35s852 / 1.3k
CG-AL-H025easy1100.0 / 1007/7OK2m 29s575 / 302
CG-AL-H026easy1100.0 / 1008/8OK2m 29s750 / 470
CG-AL-H205easy1100.0 / 1006/6OK2m 27s784 / 664
CG-AL-M001easy262.5 / 1005/10OK2m 26s2.2k / 1.9k
CG-AL-M002easy1100.0 / 10022/22OK2m 27s730 / 854
CG-AL-M003easy262.5 / 1008/9OK2m 29s2.4k / 2.1k
CG-AL-M004easy2100.0 / 10012/12OK2m 41s2.8k / 3.1k
CG-AL-M005easy262.5 / 10012/22OK2m 47s3.7k / 6.6k
CG-AL-M006easy1100.0 / 10018/18OK2m 40s710 / 1.9k
CG-AL-M007easy262.5 / 10013/15OK3m 20s3.9k / 5.4k
CG-AL-M008easy20.0 / 1000/0FAIL2m 35s15k / 17k
CG-AL-M009easy1100.0 / 10011/11OK2m 39s751 / 2.2k
CG-AL-M010easy262.5 / 10019/21OK2m 40s3.4k / 5.8k
CG-AL-M020easy2100.0 / 10017/17OK2m 30s3.2k / 2.4k
CG-AL-M021easy2100.0 / 10011/11OK2m 26s2.8k / 1.5k
CG-AL-M022easy1100.0 / 1009/9OK2m 31s815 / 1.1k
CG-AL-M023easy1100.0 / 10011/11OK2m 24s808 / 730
CG-AL-M024easy1100.0 / 10010/10OK2m 29s762 / 1.3k
CG-AL-M025easy1100.0 / 1007/7OK2m 22s660 / 508
CG-AL-M026easy20.0 / 1000/0FAIL9.3s2.3k / 1.3k
CG-AL-M088easy1100.0 / 1006/6OK2m 23s678 / 623
CG-AL-M112easy262.5 / 1002/4OK2m 13s2.9k / 2.2k