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.

82.7% 91/110 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.

68.4 / 100
Cost $4.60
Tokens 200k / 144k input / output, all attempts
Duration 1h 29m
Filter:
Per-task results for run a921e213-735a-4fb3-83c4-b2989507d391
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK39.3s413 / 316
CG-AL-E002easy1100.0 / 1006/6OK3m 6s428 / 425
CG-AL-E003easy1100.0 / 1005/5OK33.7s405 / 150
CG-AL-E004easy1100.0 / 1006/6OK38.4s465 / 365
CG-AL-E005easy1100.0 / 10013/13OK37.2s486 / 589
CG-AL-E006easy1100.0 / 1007/7OK3m 26s465 / 595
CG-AL-E007easy1100.0 / 1007/7OK48.4s553 / 240
CG-AL-E008easy1100.0 / 1006/6OK48.2s465 / 484
CG-AL-E009easy1100.0 / 1005/5OK51.3s437 / 237
CG-AL-E010easy1100.0 / 1005/5OK55.5s462 / 234
CG-AL-E031easy1100.0 / 1003/3OK54.1s673 / 657
CG-AL-E032easy1100.0 / 1001/1OK52.2s372 / 238
CG-AL-E045easy1100.0 / 1004/4OK19.1s560 / 432
CG-AL-E050easy1100.0 / 10013/13OK18.3s630 / 382
CG-AL-E051easy1100.0 / 10015/15OK24.7s771 / 1.1k
CG-AL-E052easy2100.0 / 10016/16OK18.1s2.4k / 759
CG-AL-E053easy1100.0 / 1003/3OK2m 57s456 / 171
CG-AL-E054easy2100.0 / 1009/9OK17.7s1.7k / 636
CG-AL-E055easy1100.0 / 1008/8OK18.4s561 / 299
CG-AL-E056easy2100.0 / 10015/15OK18.2s2.8k / 978
CG-AL-E057easy20.0 / 1000/0FAIL10.4s2.3k / 1.1k
CG-AL-E058easy1100.0 / 1001/1OK17.0s623 / 166
CG-AL-H001hard1100.0 / 10025/25OK18.4s721 / 396
CG-AL-H002hard1100.0 / 1004/4OK21.6s742 / 862
CG-AL-H003hard1100.0 / 1005/5OK21.9s761 / 842
CG-AL-H004hard1100.0 / 10014/14OK21.7s774 / 613
CG-AL-H005hard1100.0 / 1006/6OK22.3s1.2k / 871
CG-AL-H006hard1100.0 / 1006/6OK18.3s710 / 363
CG-AL-H007hard1100.0 / 10010/10OK23.2s947 / 995
CG-AL-H008hard1100.0 / 10010/10OK18.6s881 / 584
CG-AL-H009hard1100.0 / 10011/11OK24.4s1.0k / 1.3k
CG-AL-H010hard1100.0 / 1008/8OK18.8s896 / 630
CG-AL-H011hard20.0 / 1000/0FAIL11.5s1.8k / 614
CG-AL-H013hard1100.0 / 1009/9OK24.8s602 / 444
CG-AL-H014hard20.0 / 1000/0FAIL16.3s4.1k / 2.7k
CG-AL-H015hard1100.0 / 1004/4OK17.8s658 / 447
CG-AL-H016hard1100.0 / 1004/4OK18.3s698 / 435
CG-AL-H017hard20.0 / 1000/0FAIL9.4s1.7k / 782
CG-AL-H018hard1100.0 / 1006/6OK23.6s727 / 1.1k
CG-AL-H019hard1100.0 / 1005/5OK17.3s528 / 231
CG-AL-H020hard1100.0 / 10010/10OK23.3s781 / 1.2k
CG-AL-H021hard2100.0 / 10020/20OK28.4s29k / 2.2k
CG-AL-H022hard1100.0 / 10021/21OK26.2s1.2k / 1.4k
CG-AL-H023hard20.0 / 1000/0FAIL2m 18s22k / 22k
CG-AL-H024hard1100.0 / 1009/9OK51.5s847 / 1.3k
CG-AL-H025hard1100.0 / 1007/7OK52.4s570 / 300
CG-AL-H026hard1100.0 / 1008/8OK26.9s745 / 534
CG-AL-H027hard2100.0 / 1004/4OK18.0s3.4k / 644
CG-AL-H028hard1100.0 / 1009/9OK44.1s1.0k / 769
CG-AL-H029hard2100.0 / 10018/18OK27.5s4.3k / 3.1k
CG-AL-H030hard20.0 / 1000/0FAIL15.9s3.6k / 2.2k
CG-AL-H031hard1100.0 / 10022/22OK27.6s1.6k / 1.6k
CG-AL-H032hard1100.0 / 10019/19OK31.5s1.3k / 1.4k
CG-AL-H033hard1100.0 / 1005/5OK2m 45s1.2k / 2.2k
CG-AL-H034hard2100.0 / 1003/3OK16.0s2.1k / 461
CG-AL-H035hard1100.0 / 1003/3OK17.2s495 / 198
CG-AL-H036hard20.0 / 1000/0FAIL8.9s1.8k / 508
CG-AL-H037hard20.0 / 1000/0FAIL8.3s1.9k / 795
CG-AL-H038hard1100.0 / 1003/3OK17.1s887 / 335
CG-AL-H039hard1100.0 / 1004/4OK17.6s773 / 338
CG-AL-H040hard1100.0 / 1002/2OK16.1s645 / 255
CG-AL-H041hard1100.0 / 1003/3OK19.5s923 / 562
CG-AL-H042hard1100.0 / 1003/3OK15.5s658 / 179
CG-AL-H043hard1100.0 / 1005/5OK15.6s650 / 168
CG-AL-H050hard262.5 / 1002/3OK17.2s2.4k / 665
CG-AL-H051hard1100.0 / 1004/4OK15.6s989 / 194
CG-AL-H052hard1100.0 / 1005/5OK14.9s1.1k / 155
CG-AL-H053hard1100.0 / 1004/4OK16.9s847 / 339
CG-AL-H054hard20.0 / 1000/0FAIL10.0s3.0k / 1.0k
CG-AL-H056hard20.0 / 1000/0FAIL7.9s2.4k / 449
CG-AL-H057hard1100.0 / 1004/4OK2m 22s1.1k / 475
CG-AL-H058hard1100.0 / 1005/5OK18.1s929 / 457
CG-AL-H205hard1100.0 / 1006/6OK18.8s779 / 662
CG-AL-M001medium20.0 / 1000/0FAIL12.6s2.3k / 1.6k
CG-AL-M002medium1100.0 / 10022/22OK20.3s725 / 800
CG-AL-M003medium1100.0 / 1009/9OK25.3s687 / 1.2k
CG-AL-M004medium1100.0 / 10012/12OK2m 59s773 / 2.0k
CG-AL-M005medium1100.0 / 10022/22OK41.6s943 / 3.2k
CG-AL-M006medium1100.0 / 10018/18OK31.4s705 / 1.9k
CG-AL-M007medium2100.0 / 10015/15OK33.8s4.0k / 5.0k
CG-AL-M008medium20.0 / 1000/0FAIL2m 44s9.3k / 21k
CG-AL-M009medium1100.0 / 10011/11OK52.7s746 / 2.4k
CG-AL-M010medium2100.0 / 10021/21OK3m 5s3.4k / 6.2k
CG-AL-M020medium2100.0 / 10017/17OK48.1s2.9k / 1.9k
CG-AL-M021medium1100.0 / 10011/11OK43.6s908 / 816
CG-AL-M022medium1100.0 / 1009/9OK24.0s810 / 1.1k
CG-AL-M023medium262.5 / 10010/11OK21.9s2.7k / 1.6k
CG-AL-M024medium1100.0 / 10010/10OK33.9s757 / 1.7k
CG-AL-M025medium1100.0 / 1007/7OK25.1s655 / 505
CG-AL-M026medium20.0 / 1000/0FAIL11.2s2.2k / 1.3k
CG-AL-M027medium2100.0 / 10018/18OK30.3s5.9k / 4.4k
CG-AL-M028medium2100.0 / 1003/3OK2m 23s1.7k / 898
CG-AL-M029medium2100.0 / 1003/3OK2m 31s1.4k / 299
CG-AL-M031medium20.0 / 1000/0FAIL14.6s4.3k / 2.4k
CG-AL-M032medium2100.0 / 1003/3OK15.7s2.6k / 670
CG-AL-M033medium1100.0 / 1002/2OK19.8s735 / 393
CG-AL-M034medium262.5 / 1000/2OK18.0s2.7k / 912
CG-AL-M035medium1100.0 / 1002/2OK16.5s544 / 157
CG-AL-M036medium1100.0 / 1002/2OK18.7s910 / 515
CG-AL-M037medium20.0 / 1000/0FAIL8.4s2.1k / 708
CG-AL-M038medium1100.0 / 1002/2OK16.0s638 / 266
CG-AL-M039medium1100.0 / 1002/2OK2m 21s710 / 614
CG-AL-M040medium20.0 / 1000/0FAIL7.2s1.3k / 472
CG-AL-M041medium1100.0 / 1003/3OK14.9s501 / 157
CG-AL-M042medium1100.0 / 1008/8OK17.3s753 / 376
CG-AL-M043medium1100.0 / 1005/5OK21.2s677 / 409
CG-AL-M044medium1100.0 / 1006/6OK2m 16s985 / 846
CG-AL-M045medium1100.0 / 1006/6OK15.3s1.0k / 242
CG-AL-M088medium1100.0 / 1006/6OK20.0s673 / 671
CG-AL-M112medium1100.0 / 1004/4OK21.0s908 / 969