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.

79.7% 51/64 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.

71.9 / 100
Cost $3.49
Tokens 85k / 123k input / output, all attempts
Duration 3h 6m
Filter:
Per-task results for run 48be80fd-566b-492d-b7fd-58a1d7ff2850
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy2100.0 / 1007/7OK3m 2s927 / 571
CG-AL-E002easy1100.0 / 1006/6OK2m 27s285 / 297
CG-AL-E003easy1100.0 / 1005/5OK2m 30s273 / 129
CG-AL-E004easy1100.0 / 1006/6OK2m 30s300 / 247
CG-AL-E005easy1100.0 / 10013/13OK2m 42s315 / 600
CG-AL-E006easy1100.0 / 1007/7OK2m 48s301 / 422
CG-AL-E007easy1100.0 / 1007/7OK2m 51s371 / 165
CG-AL-E008easy1100.0 / 1006/6OK2m 55s291 / 346
CG-AL-E009easy1100.0 / 1005/5OK2m 57s285 / 223
CG-AL-E010easy1100.0 / 1005/5OK3m 0s296 / 132
CG-AL-E031easy1100.0 / 1003/3OK3m 7s428 / 404
CG-AL-E032easy1100.0 / 1001/1OK3m 10s239 / 56
CG-AL-E045easy1100.0 / 1004/4OK2m 23s385 / 339
CG-AL-E050easy2100.0 / 10013/13OK2m 23s1.1k / 669
CG-AL-E051easy1100.0 / 10015/15OK2m 29s520 / 765
CG-AL-E052easy2100.0 / 10016/16OK2m 20s1.0k / 522
CG-AL-E053easy1100.0 / 1003/3OK2m 23s312 / 166
CG-AL-E054easy1100.0 / 1009/9OK2m 19s426 / 316
CG-AL-E055easy1100.0 / 1008/8OK2m 17s385 / 216
CG-AL-H001easy1100.0 / 10025/25OK2m 22s491 / 394
CG-AL-H002easy1100.0 / 1004/4OK2m 23s496 / 579
CG-AL-H003easy1100.0 / 1005/5OK2m 25s524 / 669
CG-AL-H004easy1100.0 / 10014/14OK2m 24s535 / 495
CG-AL-H005easy262.5 / 1002/5OK2m 36s2.2k / 2.8k
CG-AL-H006easy1100.0 / 1006/6OK2m 21s454 / 243
CG-AL-H007easy1100.0 / 10010/10OK2m 25s625 / 732
CG-AL-H008easy1100.0 / 10010/10OK2m 23s588 / 423
CG-AL-H009easy1100.0 / 10011/11OK2m 27s688 / 806
CG-AL-H010easy1100.0 / 1008/8OK2m 19s561 / 407
CG-AL-H011easy20.0 / 1000/0FAIL7.3s1.1k / 401
CG-AL-H013easy1100.0 / 1009/9OK2m 23s392 / 323
CG-AL-H014easy2100.0 / 1007/7OK2m 25s1.8k / 1.3k
CG-AL-H015easy1100.0 / 1004/4OK2m 22s443 / 325
CG-AL-H016easy262.5 / 1003/4OK2m 22s1.2k / 683
CG-AL-H017easy2100.0 / 1003/3OK2m 22s1.1k / 581
CG-AL-H018easy1100.0 / 1006/6OK2m 25s462 / 519
CG-AL-H019easy1100.0 / 1005/5OK2m 21s349 / 169
CG-AL-H020easy2100.0 / 10010/10OK2m 26s2.4k / 1.6k
CG-AL-H021easy262.5 / 1006/20OK2m 32s2.2k / 1.8k
CG-AL-H022easy1100.0 / 10021/21OK2m 29s826 / 1.1k
CG-AL-H023easy20.0 / 1000/0FAIL2m 42s14k / 22k
CG-AL-H024easy1100.0 / 1009/9OK2m 37s573 / 937
CG-AL-H025easy1100.0 / 1007/7OK2m 45s388 / 223
CG-AL-H026easy1100.0 / 1008/8OK2m 23s509 / 368
CG-AL-H205easy1100.0 / 1006/6OK2m 25s535 / 477
CG-AL-M001easy20.0 / 1000/0FAIL28.6s1.6k / 3.3k
CG-AL-M002easy1100.0 / 10022/22OK2m 25s471 / 506
CG-AL-M003easy262.5 / 1008/9OK2m 25s1.8k / 1.7k
CG-AL-M004easy1100.0 / 10012/12OK2m 38s496 / 1.3k
CG-AL-M005easy262.5 / 10012/22OK2m 51s2.4k / 6.7k
CG-AL-M006easy1100.0 / 10018/18OK2m 41s445 / 1.9k
CG-AL-M007easy20.0 / 1000/0FAIL42.5s3.8k / 8.1k
CG-AL-M008easy20.0 / 1000/0FAIL2m 57s12k / 23k
CG-AL-M009easy20.0 / 1000/0FAIL3m 36s7.9k / 17k
CG-AL-M010easy262.5 / 10019/21OK2m 38s2.4k / 5.0k
CG-AL-M020easy2100.0 / 10017/17OK2m 26s2.1k / 1.5k
CG-AL-M021easy1100.0 / 10011/11OK2m 29s595 / 593
CG-AL-M022easy1100.0 / 1009/9OK2m 26s554 / 664
CG-AL-M023easy1100.0 / 10011/11OK2m 24s536 / 532
CG-AL-M024easy1100.0 / 10010/10OK2m 28s518 / 1.2k
CG-AL-M025easy1100.0 / 1007/7OK2m 21s457 / 386
CG-AL-M026easy1100.0 / 1008/8OK2m 22s426 / 408
CG-AL-M088easy1100.0 / 1006/6OK2m 22s451 / 486
CG-AL-M112easy262.5 / 1002/4OK2m 14s2.0k / 1.5k