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.

91.8% 101/110 of 110 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.

79.4 / 100
Cost $13.15
Tokens 209k / 221k input / output, all attempts
Duration 2h 3m
Filter:
Per-task results for run 9ab3a769-5213-4a2a-8525-c1257524d4c3
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy2100.0 / 1007/7OK28.1s1.4k / 942
CG-AL-E002easy1100.0 / 1006/6OK2m 59s428 / 486
CG-AL-E003easy1100.0 / 1005/5OK28.8s405 / 177
CG-AL-E004easy1100.0 / 1006/6OK34.9s465 / 418
CG-AL-E005easy1100.0 / 10013/13OK37.4s486 / 566
CG-AL-E006easy1100.0 / 1007/7OK2m 47s465 / 802
CG-AL-E007easy1100.0 / 1007/7OK38.2s553 / 240
CG-AL-E008easy1100.0 / 1006/6OK44.1s465 / 907
CG-AL-E009easy1100.0 / 1005/5OK40.4s437 / 316
CG-AL-E010easy1100.0 / 1005/5OK35.3s462 / 317
CG-AL-E031easy1100.0 / 1003/3OK39.6s673 / 638
CG-AL-E032easy1100.0 / 1001/1OK45.4s372 / 244
CG-AL-E045easy1100.0 / 1004/4OK19.8s560 / 570
CG-AL-E050easy2100.0 / 10013/13OK30.1s2.9k / 2.0k
CG-AL-E051easy1100.0 / 10015/15OK33.3s771 / 2.1k
CG-AL-E052easy2100.0 / 10016/16OK27.3s2.4k / 900
CG-AL-E053easy1100.0 / 1003/3OK3m 6s456 / 237
CG-AL-E054easy2100.0 / 1009/9OK30.6s1.7k / 1.5k
CG-AL-E055easy1100.0 / 1008/8OK21.2s561 / 374
CG-AL-E056easy2100.0 / 10015/15OK22.5s2.8k / 1.1k
CG-AL-E057easy2100.0 / 1008/8OK1m 17s3.3k / 5.5k
CG-AL-E058easy1100.0 / 1001/1OK28.2s623 / 292
CG-AL-H001hard1100.0 / 10025/25OK19.9s721 / 409
CG-AL-H002hard1100.0 / 1004/4OK23.2s742 / 909
CG-AL-H003hard1100.0 / 1005/5OK22.4s761 / 886
CG-AL-H004hard1100.0 / 10014/14OK22.0s774 / 577
CG-AL-H005hard1100.0 / 1006/6OK27.5s1.2k / 907
CG-AL-H006hard1100.0 / 1006/6OK17.3s710 / 373
CG-AL-H007hard2100.0 / 10010/10OK31.1s2.9k / 2.5k
CG-AL-H008hard1100.0 / 10010/10OK20.6s881 / 667
CG-AL-H009hard1100.0 / 10011/11OK32.8s1.0k / 1.3k
CG-AL-H010hard1100.0 / 1008/8OK25.4s896 / 687
CG-AL-H011hard1100.0 / 1005/5OK23.5s574 / 353
CG-AL-H013hard1100.0 / 1009/9OK30.3s602 / 670
CG-AL-H014hard2100.0 / 1007/7OK24.0s2.2k / 1.7k
CG-AL-H015hard1100.0 / 1004/4OK18.4s658 / 453
CG-AL-H016hard1100.0 / 1004/4OK20.5s698 / 573
CG-AL-H017hard1100.0 / 1003/3OK25.1s610 / 1.2k
CG-AL-H018hard1100.0 / 1006/6OK30.0s727 / 1.6k
CG-AL-H019hard1100.0 / 1005/5OK23.8s528 / 342
CG-AL-H020hard1100.0 / 10010/10OK27.2s781 / 1.4k
CG-AL-H021hard2100.0 / 10020/20OK34.1s30k / 2.6k
CG-AL-H022hard1100.0 / 10021/21OK46.0s1.2k / 3.1k
CG-AL-H023hard20.0 / 1000/0FAIL2m 57s25k / 28k
CG-AL-H024hard1100.0 / 1009/9OK26.1s847 / 1.2k
CG-AL-H025hard1100.0 / 1007/7OK27.7s570 / 318
CG-AL-H026hard1100.0 / 1008/8OK27.1s745 / 529
CG-AL-H027hard1100.0 / 1004/4OK29.7s1.1k / 1.3k
CG-AL-H028hard1100.0 / 1009/9OK22.4s1.0k / 887
CG-AL-H029hard1100.0 / 10018/18OK47.3s1.3k / 3.1k
CG-AL-H030hard1100.0 / 10010/10OK34.8s1.1k / 1.7k
CG-AL-H031hard1100.0 / 10022/22OK33.9s1.6k / 2.1k
CG-AL-H032hard1100.0 / 10019/19OK28.2s1.3k / 1.5k
CG-AL-H033hard1100.0 / 1005/5OK2m 48s1.2k / 2.4k
CG-AL-H034hard1100.0 / 1003/3OK29.1s720 / 1.1k
CG-AL-H035hard1100.0 / 1003/3OK17.3s495 / 230
CG-AL-H036hard1100.0 / 1005/5OK32.8s638 / 1.4k
CG-AL-H037hard1100.0 / 1003/3OK18.7s805 / 373
CG-AL-H038hard1100.0 / 1003/3OK20.7s887 / 467
CG-AL-H039hard1100.0 / 1004/4OK18.3s773 / 458
CG-AL-H040hard1100.0 / 1002/2OK17.9s645 / 310
CG-AL-H041hard2100.0 / 1003/3OK46.1s3.6k / 3.0k
CG-AL-H042hard1100.0 / 1003/3OK17.8s658 / 248
CG-AL-H043hard1100.0 / 1005/5OK18.1s650 / 241
CG-AL-H050hard1100.0 / 1003/3OK24.1s813 / 892
CG-AL-H051hard1100.0 / 1004/4OK18.5s989 / 292
CG-AL-H052hard1100.0 / 1005/5OK17.2s1.1k / 197
CG-AL-H053hard1100.0 / 1004/4OK18.2s847 / 353
CG-AL-H054hard2100.0 / 1005/5OK20.6s3.1k / 1.3k
CG-AL-H056hard2100.0 / 1004/4OK28.0s2.4k / 1.3k
CG-AL-H057hard1100.0 / 1004/4OK3m 12s1.1k / 488
CG-AL-H058hard1100.0 / 1005/5OK21.3s929 / 714
CG-AL-H205hard1100.0 / 1006/6OK21.5s779 / 764
CG-AL-M001medium20.0 / 1000/0FAIL19.3s2.5k / 2.1k
CG-AL-M002medium1100.0 / 10022/22OK21.4s725 / 808
CG-AL-M003medium1100.0 / 1009/9OK27.1s687 / 1.3k
CG-AL-M004medium1100.0 / 10012/12OK2m 53s773 / 2.2k
CG-AL-M005medium1100.0 / 10022/22OK41.3s943 / 3.3k
CG-AL-M006medium1100.0 / 10018/18OK43.8s705 / 3.1k
CG-AL-M007medium20.0 / 1000/0FAIL2m 50s9.7k / 27k
CG-AL-M008medium20.0 / 1000/0FAIL3m 56s17k / 32k
CG-AL-M009medium20.0 / 1000/0FAIL2m 55s12k / 16k
CG-AL-M010medium1100.0 / 10021/21OK4m 9s958 / 3.3k
CG-AL-M020medium1100.0 / 10017/17OK1m 9s883 / 1.0k
CG-AL-M021medium1100.0 / 10011/11OK1m 12s908 / 915
CG-AL-M022medium1100.0 / 1009/9OK1m 22s810 / 1.0k
CG-AL-M023medium262.5 / 10010/11OK2m 52s2.7k / 3.8k
CG-AL-M024medium1100.0 / 10010/10OK1m 29s757 / 1.6k
CG-AL-M025medium2100.0 / 1007/7OK30.8s4.2k / 1.5k
CG-AL-M026medium1100.0 / 1008/8OK1m 21s624 / 567
CG-AL-M027medium1100.0 / 10018/18OK2m 43s1.4k / 2.6k
CG-AL-M028medium2100.0 / 1003/3OK2m 55s1.7k / 1.1k
CG-AL-M029medium2100.0 / 1003/3OK2m 56s1.4k / 648
CG-AL-M031medium2100.0 / 1002/2OK33.9s2.9k / 2.3k
CG-AL-M032medium1100.0 / 1003/3OK1m 35s793 / 339
CG-AL-M033medium1100.0 / 1002/2OK22.4s735 / 385
CG-AL-M034medium262.5 / 1001/2OK23.1s2.6k / 1.5k
CG-AL-M035medium1100.0 / 1002/2OK23.1s544 / 167
CG-AL-M036medium1100.0 / 1002/2OK26.8s910 / 578
CG-AL-M037medium20.0 / 1000/0FAIL29.4s2.1k / 1.8k
CG-AL-M038medium1100.0 / 1002/2OK22.3s638 / 344
CG-AL-M039medium1100.0 / 1002/2OK2m 39s710 / 1.1k
CG-AL-M040medium262.5 / 1001/2OK19.9s1.3k / 857
CG-AL-M041medium1100.0 / 1003/3OK16.5s501 / 167
CG-AL-M042medium1100.0 / 1008/8OK20.2s753 / 537
CG-AL-M043medium1100.0 / 1005/5OK21.9s677 / 697
CG-AL-M044medium1100.0 / 1006/6OK2m 28s985 / 1.0k
CG-AL-M045medium1100.0 / 1006/6OK20.3s1.0k / 535
CG-AL-M088medium1100.0 / 1006/6OK22.5s673 / 804
CG-AL-M112medium1100.0 / 1004/4OK21.0s908 / 969