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.

76.6% 49/64 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.

66.3 / 100
Cost $2.28
Tokens 95k / 133k input / output, all attempts
Duration 3h 12m
Filter:
Per-task results for run 75466b2c-00f2-4ba5-b7f9-e48607416da8
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK2m 45s272 / 272
CG-AL-E002easy1100.0 / 1006/6OK2m 45s285 / 334
CG-AL-E003easy1100.0 / 1005/5OK3m 2s273 / 120
CG-AL-E004easy1100.0 / 1006/6OK2m 50s300 / 250
CG-AL-E005easy1100.0 / 10013/13OK2m 55s315 / 437
CG-AL-E006easy1100.0 / 1007/7OK3m 12s301 / 419
CG-AL-E007easy1100.0 / 1007/7OK3m 7s371 / 154
CG-AL-E008easy1100.0 / 1006/6OK3m 9s291 / 354
CG-AL-E009easy1100.0 / 1005/5OK3m 15s285 / 250
CG-AL-E010easy20.0 / 1000/0FAIL9.5s766 / 270
CG-AL-E031easy1100.0 / 1003/3OK3m 26s428 / 401
CG-AL-E032easy1100.0 / 1001/1OK3m 30s239 / 55
CG-AL-E045easy1100.0 / 1004/4OK2m 34s385 / 369
CG-AL-E050easy2100.0 / 10013/13OK2m 42s2.0k / 950
CG-AL-E051easy1100.0 / 10015/15OK2m 43s520 / 751
CG-AL-E052easy2100.0 / 10016/16OK2m 35s1.0k / 708
CG-AL-E053easy1100.0 / 1003/3OK2m 35s312 / 128
CG-AL-E054easy20.0 / 1000/0FAIL15.6s1.2k / 812
CG-AL-E055easy1100.0 / 1008/8OK2m 39s385 / 215
CG-AL-H001easy1100.0 / 10025/25OK2m 35s491 / 335
CG-AL-H002easy1100.0 / 1004/4OK2m 37s496 / 626
CG-AL-H003easy1100.0 / 1005/5OK2m 39s524 / 721
CG-AL-H004easy1100.0 / 10014/14OK2m 36s535 / 452
CG-AL-H005easy20.0 / 1000/0FAIL24.9s2.3k / 3.4k
CG-AL-H006easy1100.0 / 1006/6OK2m 32s454 / 243
CG-AL-H007easy1100.0 / 10010/10OK2m 35s625 / 705
CG-AL-H008easy1100.0 / 10010/10OK2m 33s588 / 416
CG-AL-H009easy1100.0 / 10011/11OK2m 38s688 / 849
CG-AL-H010easy1100.0 / 1008/8OK2m 34s561 / 406
CG-AL-H011easy2100.0 / 1005/5OK2m 35s1.0k / 438
CG-AL-H013easy1100.0 / 1009/9OK2m 34s392 / 322
CG-AL-H014easy2100.0 / 1007/7OK2m 44s2.9k / 1.7k
CG-AL-H015easy1100.0 / 1004/4OK2m 32s443 / 286
CG-AL-H016easy262.5 / 1003/4OK2m 27s1.2k / 638
CG-AL-H017easy2100.0 / 1003/3OK2m 27s1.2k / 803
CG-AL-H018easy1100.0 / 1006/6OK2m 31s462 / 552
CG-AL-H019easy1100.0 / 1005/5OK2m 24s349 / 168
CG-AL-H020easy2100.0 / 10010/10OK2m 31s2.5k / 1.8k
CG-AL-H021easy262.5 / 1006/20OK2m 30s2.3k / 1.7k
CG-AL-H022easy2100.0 / 10021/21OK2m 36s2.8k / 2.0k
CG-AL-H023easy20.0 / 1000/0FAIL2m 32s15k / 22k
CG-AL-H024easy1100.0 / 1009/9OK2m 41s573 / 825
CG-AL-H025easy1100.0 / 1007/7OK2m 35s388 / 210
CG-AL-H026easy1100.0 / 1008/8OK2m 38s509 / 360
CG-AL-H205easy1100.0 / 1006/6OK2m 25s535 / 476
CG-AL-M001easy262.5 / 1005/10OK2m 31s1.3k / 1.4k
CG-AL-M002easy1100.0 / 10022/22OK2m 28s471 / 587
CG-AL-M003easy262.5 / 1008/9OK2m 32s1.7k / 1.9k
CG-AL-M004easy1100.0 / 10012/12OK2m 42s496 / 1.5k
CG-AL-M005easy20.0 / 1000/0FAIL29.0s2.3k / 6.1k
CG-AL-M006easy262.5 / 10017/18OK2m 36s1.9k / 4.2k
CG-AL-M007easy20.0 / 1000/0FAIL1m 9s5.9k / 11k
CG-AL-M008easy20.0 / 1000/0FAIL2m 58s13k / 24k
CG-AL-M009easy2100.0 / 10011/11OK2m 50s5.4k / 20k
CG-AL-M010easy262.5 / 10019/21OK2m 51s2.4k / 4.4k
CG-AL-M020easy2100.0 / 10017/17OK2m 42s2.2k / 1.6k
CG-AL-M021easy2100.0 / 10011/11OK2m 28s1.9k / 1.2k
CG-AL-M022easy1100.0 / 1009/9OK2m 33s554 / 733
CG-AL-M023easy1100.0 / 10011/11OK2m 25s536 / 535
CG-AL-M024easy1100.0 / 10010/10OK2m 31s518 / 1.2k
CG-AL-M025easy262.5 / 1000/0OK2m 22s1.4k / 914
CG-AL-M026easy1100.0 / 1008/8OK2m 27s426 / 366
CG-AL-M088easy1100.0 / 1006/6OK2m 28s451 / 450
CG-AL-M112easy262.5 / 1002/4OK2m 21s2.0k / 1.7k