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.

77.8% 49/63 of 63 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.

67.2 / 100
Cost $4.09
Tokens 95k / 145k input / output, all attempts
Duration 3h 4m
Filter:
Per-task results for run 3ded2473-5f9c-410e-a28e-8298c8d76b26
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy2100.0 / 1007/7OK2m 51s927 / 571
CG-AL-E002easy1100.0 / 1006/6OK2m 27s285 / 297
CG-AL-E003easy1100.0 / 1005/5OK2m 36s273 / 129
CG-AL-E004easy1100.0 / 1006/6OK2m 34s300 / 247
CG-AL-E005easy1100.0 / 10013/13OK2m 43s315 / 586
CG-AL-E006easy1100.0 / 1007/7OK2m 47s301 / 422
CG-AL-E007easy1100.0 / 1007/7OK2m 50s371 / 165
CG-AL-E008easy1100.0 / 1006/6OK2m 51s291 / 350
CG-AL-E009easy1100.0 / 1005/5OK2m 57s285 / 234
CG-AL-E010easy1100.0 / 1005/5OK2m 56s296 / 132
CG-AL-E031easy1100.0 / 1003/3OK3m 2s428 / 404
CG-AL-E032easy1100.0 / 1001/1OK3m 5s239 / 56
CG-AL-E045easy1100.0 / 1004/4OK2m 30s385 / 339
CG-AL-E050easy1100.0 / 10013/13OK2m 37s415 / 794
CG-AL-E051easy1100.0 / 10015/15OK2m 37s520 / 777
CG-AL-E052easy2100.0 / 10016/16OK2m 32s1.0k / 493
CG-AL-E053easy1100.0 / 1003/3OK2m 32s312 / 166
CG-AL-E054easy1100.0 / 1009/9OK2m 31s426 / 316
CG-AL-E055easy1100.0 / 1008/8OK2m 29s385 / 216
CG-AL-H001hard1100.0 / 10025/25OK2m 33s491 / 394
CG-AL-H002hard1100.0 / 1004/4OK2m 34s496 / 579
CG-AL-H003hard1100.0 / 1005/5OK2m 36s524 / 673
CG-AL-H004hard1100.0 / 10014/14OK2m 32s535 / 495
CG-AL-H005hard262.5 / 1002/5OK2m 43s2.1k / 2.8k
CG-AL-H006hard1100.0 / 1006/6OK2m 28s454 / 243
CG-AL-H007hard1100.0 / 10010/10OK2m 33s625 / 689
CG-AL-H008hard1100.0 / 10010/10OK2m 30s588 / 423
CG-AL-H009hard1100.0 / 10011/11OK2m 33s688 / 841
CG-AL-H010hard1100.0 / 1008/8OK2m 31s561 / 407
CG-AL-H011hard20.0 / 1000/0FAIL11.5s1.1k / 401
CG-AL-H013hard1100.0 / 1009/9OK2m 29s392 / 323
CG-AL-H014hard2100.0 / 1007/7OK2m 31s1.8k / 1.3k
CG-AL-H015hard1100.0 / 1004/4OK2m 30s443 / 325
CG-AL-H016hard262.5 / 1001/6OK2m 32s1.5k / 1.1k
CG-AL-H017hard2100.0 / 1003/3OK2m 25s1.1k / 581
CG-AL-H018hard1100.0 / 1006/6OK2m 35s462 / 537
CG-AL-H019hard1100.0 / 1005/5OK2m 28s349 / 169
CG-AL-H020hard2100.0 / 10010/10OK2m 30s2.4k / 1.6k
CG-AL-H021hard20.0 / 1000/0FAIL16.0s2.6k / 1.5k
CG-AL-H023hard20.0 / 1000/0FAIL2m 49s15k / 22k
CG-AL-H024hard1100.0 / 1009/9OK2m 33s573 / 937
CG-AL-H025hard1100.0 / 1007/7OK2m 27s388 / 207
CG-AL-H026hard20.0 / 1000/0FAIL15.0s2.4k / 864
CG-AL-H205hard1100.0 / 1006/6OK2m 28s535 / 477
CG-AL-M001medium262.5 / 1003/10OK2m 39s1.9k / 2.9k
CG-AL-M002medium1100.0 / 10022/22OK2m 37s471 / 506
CG-AL-M003medium262.5 / 1008/9OK2m 31s1.8k / 3.7k
CG-AL-M004medium1100.0 / 10012/12OK2m 45s496 / 1.3k
CG-AL-M005medium262.5 / 10017/22OK2m 45s2.4k / 5.6k
CG-AL-M006medium2100.0 / 10018/18OK2m 39s2.0k / 3.4k
CG-AL-M007medium20.0 / 1000/0FAIL2m 51s8.7k / 24k
CG-AL-M008medium20.0 / 1000/0FAIL2m 49s10k / 22k
CG-AL-M009medium20.0 / 1000/0FAIL2m 5s8.0k / 18k
CG-AL-M010medium262.5 / 10019/21OK2m 53s2.6k / 5.9k
CG-AL-M020medium2100.0 / 10017/17OK2m 34s2.1k / 1.6k
CG-AL-M021medium2100.0 / 10014/14OK2m 50s2.9k / 4.1k
CG-AL-M022medium1100.0 / 1009/9OK2m 32s554 / 664
CG-AL-M023medium1100.0 / 10011/11OK2m 29s536 / 526
CG-AL-M024medium1100.0 / 10010/10OK2m 35s518 / 1.2k
CG-AL-M025medium1100.0 / 1007/7OK2m 27s457 / 365
CG-AL-M026medium1100.0 / 1008/8OK2m 30s426 / 421
CG-AL-M088medium1100.0 / 1006/6OK2m 26s451 / 476
CG-AL-M112medium262.5 / 1002/4OK2m 23s2.0k / 1.5k