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.

57.8% 37/64 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.

45.3 / 100
Cost $0.51
Tokens 88k / 85k input / output, all attempts
Duration 2h 16m
Filter:
Per-task results for run 81f8056f-69e4-4948-b39c-e71d887397fa
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy2100.0 / 1007/7OK2m 22s937 / 566
CG-AL-E002easy1100.0 / 1006/6OK2m 26s285 / 302
CG-AL-E003easy1100.0 / 1005/5OK3m 3s273 / 120
CG-AL-E004easy1100.0 / 1006/6OK3m 11s300 / 336
CG-AL-E005easy1100.0 / 10013/13OK3m 9s315 / 436
CG-AL-E006easy2100.0 / 1007/7OK2m 25s1.1k / 896
CG-AL-E007easy2100.0 / 1007/7OK2m 33s1.1k / 397
CG-AL-E008easy1100.0 / 1006/6OK3m 11s291 / 304
CG-AL-E009easy1100.0 / 1005/5OK2m 42s285 / 164
CG-AL-E010easy1100.0 / 1005/5OK2m 29s296 / 116
CG-AL-E031easy1100.0 / 1003/3OK2m 29s428 / 401
CG-AL-E032easy1100.0 / 1001/1OK2m 29s239 / 55
CG-AL-E045easy1100.0 / 1004/4OK2m 21s385 / 336
CG-AL-E050easy20.0 / 1000/0FAIL8.2s2.2k / 451
CG-AL-E051easy20.0 / 1000/0FAIL12.5s1.8k / 1.4k
CG-AL-E052easy262.5 / 10014/16OK2m 21s1.1k / 564
CG-AL-E053easy20.0 / 1000/0FAIL5.9s854 / 353
CG-AL-E054easy20.0 / 1000/0FAIL6.0s1.2k / 490
CG-AL-E055easy1100.0 / 1008/8OK2m 20s385 / 218
CG-AL-H001easy1100.0 / 10025/25OK2m 22s491 / 447
CG-AL-H002easy2100.0 / 1004/4OK2m 22s1.7k / 1.0k
CG-AL-H003easy262.5 / 1004/5OK2m 22s1.7k / 1.3k
CG-AL-H004easy1100.0 / 10014/14OK2m 30s535 / 445
CG-AL-H005easy20.0 / 1000/0FAIL12.1s2.3k / 3.0k
CG-AL-H006easy1100.0 / 1006/6OK2m 19s454 / 247
CG-AL-H007easy2100.0 / 10010/10OK2m 22s2.0k / 1.3k
CG-AL-H008easy1100.0 / 10010/10OK2m 20s588 / 431
CG-AL-H009easy1100.0 / 10011/11OK2m 22s688 / 811
CG-AL-H010easy1100.0 / 1008/8OK2m 19s561 / 406
CG-AL-H011easy20.0 / 1000/0FAIL5.9s1.3k / 451
CG-AL-H013easy1100.0 / 1009/9OK2m 18s392 / 339
CG-AL-H014easy20.0 / 1000/0FAIL7.0s1.6k / 916
CG-AL-H015easy1100.0 / 1004/4OK2m 18s443 / 312
CG-AL-H016easy262.5 / 1003/4OK2m 19s1.1k / 536
CG-AL-H017easy20.0 / 1000/0FAIL5.8s1.2k / 562
CG-AL-H018easy20.0 / 1000/0FAIL6.8s1.7k / 987
CG-AL-H019easy2100.0 / 1005/5OK2m 17s956 / 343
CG-AL-H020easy2100.0 / 10010/10OK2m 19s2.5k / 1.6k
CG-AL-H021easy20.0 / 1000/0FAIL8.9s3.1k / 1.7k
CG-AL-H022easy262.5 / 10017/21OK2m 22s2.8k / 1.9k
CG-AL-H023easy20.0 / 1000/0FAIL47.1s11k / 14k
CG-AL-H024easy1100.0 / 1009/9OK2m 24s573 / 1.0k
CG-AL-H025easy1100.0 / 1007/7OK2m 20s388 / 272
CG-AL-H026easy1100.0 / 1008/8OK2m 19s509 / 364
CG-AL-H205easy2100.0 / 1006/6OK2m 29s1.6k / 1.1k
CG-AL-M001easy20.0 / 1000/0FAIL6.4s1.6k / 1.2k
CG-AL-M002easy262.5 / 10021/22OK2m 28s2.0k / 2.0k
CG-AL-M003easy20.0 / 1000/0FAIL7.9s1.9k / 1.7k
CG-AL-M004easy1100.0 / 10012/12OK2m 36s496 / 1.1k
CG-AL-M005easy20.0 / 1000/0FAIL14.5s2.4k / 4.1k
CG-AL-M006easy20.0 / 1000/0FAIL10.6s2.1k / 2.5k
CG-AL-M007easy20.0 / 1000/0FAIL15.4s2.5k / 4.2k
CG-AL-M008easy20.0 / 1000/0FAIL20.6s3.4k / 6.6k
CG-AL-M009easy1100.0 / 10011/11OK2m 41s475 / 3.1k
CG-AL-M010easy262.5 / 10019/21OK2m 34s2.5k / 3.9k
CG-AL-M020easy20.0 / 1000/0FAIL8.1s2.2k / 1.3k
CG-AL-M021easy20.0 / 1000/0FAIL7.3s2.1k / 1.1k
CG-AL-M022easy2100.0 / 1009/9OK2m 26s1.9k / 1.5k
CG-AL-M023easy1100.0 / 10011/11OK2m 26s536 / 541
CG-AL-M024easy2100.0 / 10010/10OK2m 27s2.4k / 2.5k
CG-AL-M025easy262.5 / 1002/7OK2m 26s1.4k / 780
CG-AL-M026easy1100.0 / 1008/8OK2m 24s426 / 347
CG-AL-M088easy1100.0 / 1006/6OK2m 23s451 / 429
CG-AL-M112easy262.5 / 1002/4OK2m 24s2.2k / 1.5k