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.

64.2 / 100
Cost $2.35
Tokens 97k / 138k input / output, all attempts
Duration 2h 59m
Filter:
Per-task results for run b9ca725e-7be3-4b1b-9a7e-5940440ad41b
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK2m 19s272 / 272
CG-AL-E002easy1100.0 / 1006/6OK2m 29s285 / 334
CG-AL-E003easy1100.0 / 1005/5OK2m 24s273 / 120
CG-AL-E004easy1100.0 / 1006/6OK2m 39s300 / 250
CG-AL-E005easy1100.0 / 10013/13OK2m 36s315 / 437
CG-AL-E006easy1100.0 / 1007/7OK2m 50s301 / 419
CG-AL-E007easy1100.0 / 1007/7OK2m 50s371 / 154
CG-AL-E008easy1100.0 / 1006/6OK2m 52s291 / 361
CG-AL-E009easy1100.0 / 1005/5OK3m 0s285 / 254
CG-AL-E010easy20.0 / 1000/0FAIL10.8s763 / 277
CG-AL-E031easy1100.0 / 1003/3OK3m 6s428 / 401
CG-AL-E032easy1100.0 / 1001/1OK3m 10s239 / 55
CG-AL-E045easy1100.0 / 1004/4OK2m 20s385 / 369
CG-AL-E050easy2100.0 / 10013/13OK2m 28s1.9k / 845
CG-AL-E051easy1100.0 / 10015/15OK2m 27s520 / 751
CG-AL-E052easy2100.0 / 10016/16OK2m 24s1.0k / 788
CG-AL-E053easy1100.0 / 1003/3OK2m 20s312 / 128
CG-AL-E054easy20.0 / 1000/0FAIL10.0s1.2k / 612
CG-AL-E055easy1100.0 / 1008/8OK2m 20s385 / 215
CG-AL-H001easy1100.0 / 10025/25OK2m 19s491 / 335
CG-AL-H002easy1100.0 / 1004/4OK2m 24s496 / 626
CG-AL-H003easy1100.0 / 1005/5OK2m 24s524 / 721
CG-AL-H004easy1100.0 / 10014/14OK2m 20s535 / 501
CG-AL-H005easy20.0 / 1000/0FAIL29.3s2.3k / 3.5k
CG-AL-H006easy1100.0 / 1006/6OK2m 23s454 / 243
CG-AL-H007easy1100.0 / 10010/10OK2m 24s625 / 705
CG-AL-H008easy1100.0 / 10010/10OK2m 19s588 / 416
CG-AL-H009easy1100.0 / 10011/11OK2m 26s688 / 849
CG-AL-H010easy1100.0 / 1008/8OK2m 21s561 / 406
CG-AL-H011easy2100.0 / 1005/5OK2m 18s1.0k / 438
CG-AL-H013easy1100.0 / 1009/9OK2m 22s392 / 322
CG-AL-H014easy2100.0 / 1007/7OK2m 23s2.9k / 1.7k
CG-AL-H015easy1100.0 / 1004/4OK2m 23s443 / 286
CG-AL-H016easy262.5 / 1003/4OK2m 17s1.2k / 614
CG-AL-H017easy20.0 / 1000/0FAIL10.3s1.2k / 739
CG-AL-H018easy1100.0 / 1006/6OK2m 25s462 / 580
CG-AL-H019easy1100.0 / 1005/5OK2m 18s349 / 168
CG-AL-H020easy2100.0 / 10010/10OK2m 27s2.5k / 1.7k
CG-AL-H021easy262.5 / 1006/20OK2m 27s2.3k / 1.7k
CG-AL-H022easy2100.0 / 10021/21OK2m 27s2.8k / 2.1k
CG-AL-H023easy20.0 / 1000/0FAIL3m 6s18k / 22k
CG-AL-H024easy1100.0 / 1009/9OK2m 48s573 / 780
CG-AL-H025easy1100.0 / 1007/7OK2m 44s388 / 210
CG-AL-H026easy1100.0 / 1008/8OK2m 28s509 / 365
CG-AL-H205easy1100.0 / 1006/6OK2m 22s535 / 476
CG-AL-M001easy20.0 / 1000/0FAIL18.0s1.6k / 2.0k
CG-AL-M002easy1100.0 / 10022/22OK2m 22s471 / 522
CG-AL-M003easy262.5 / 1008/9OK2m 23s1.6k / 1.6k
CG-AL-M004easy1100.0 / 10012/12OK2m 45s496 / 1.5k
CG-AL-M005easy20.0 / 1000/0FAIL27.7s2.2k / 5.6k
CG-AL-M006easy2100.0 / 10018/18OK2m 37s1.9k / 4.1k
CG-AL-M007easy20.0 / 1000/0FAIL45.1s3.4k / 8.2k
CG-AL-M008easy20.0 / 1000/0FAIL2m 52s14k / 32k
CG-AL-M009easy2100.0 / 10011/11OK2m 50s5.2k / 19k
CG-AL-M010easy262.5 / 10019/21OK3m 4s2.4k / 4.5k
CG-AL-M020easy2100.0 / 10017/17OK2m 24s2.2k / 1.8k
CG-AL-M021easy2100.0 / 10011/11OK2m 21s1.9k / 1.1k
CG-AL-M022easy1100.0 / 1009/9OK2m 23s554 / 728
CG-AL-M023easy1100.0 / 10011/11OK2m 26s536 / 535
CG-AL-M024easy1100.0 / 10010/10OK2m 27s518 / 1.2k
CG-AL-M025easy20.0 / 1000/0FAIL10.6s1.4k / 911
CG-AL-M026easy1100.0 / 1008/8OK2m 23s426 / 384
CG-AL-M088easy1100.0 / 1006/6OK2m 20s451 / 450
CG-AL-M112easy262.5 / 1002/4OK2m 27s2.0k / 1.8k