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.

81.8% 90/110 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.

67.7 / 100
Cost $3.95
Tokens 177k / 123k input / output, all attempts
Duration 1h 8m
Filter:
Per-task results for run 84ba3ab3-c78f-49cb-b772-b32b5a048d75
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK16.6s413 / 316
CG-AL-E002easy1100.0 / 1006/6OK2m 40s428 / 423
CG-AL-E003easy1100.0 / 1005/5OK20.1s405 / 164
CG-AL-E004easy1100.0 / 1006/6OK25.5s465 / 365
CG-AL-E005easy1100.0 / 10013/13OK28.5s486 / 670
CG-AL-E006easy1100.0 / 1007/7OK2m 41s465 / 605
CG-AL-E007easy1100.0 / 1007/7OK35.3s553 / 240
CG-AL-E008easy1100.0 / 1006/6OK40.2s465 / 466
CG-AL-E009easy1100.0 / 1005/5OK39.7s437 / 237
CG-AL-E010easy2100.0 / 1005/5OK15.5s1.2k / 425
CG-AL-E031easy1100.0 / 1003/3OK44.8s673 / 657
CG-AL-E032easy1100.0 / 1001/1OK39.6s372 / 239
CG-AL-E045easy1100.0 / 1004/4OK17.3s560 / 430
CG-AL-E050easy1100.0 / 10013/13OK16.1s630 / 315
CG-AL-E051easy1100.0 / 10015/15OK21.8s771 / 1.0k
CG-AL-E052easy2100.0 / 10016/16OK15.4s2.4k / 765
CG-AL-E053easy1100.0 / 1003/3OK2m 27s456 / 175
CG-AL-E054easy2100.0 / 1009/9OK14.5s1.7k / 632
CG-AL-E055easy1100.0 / 1008/8OK15.2s561 / 299
CG-AL-E056easy2100.0 / 10015/15OK16.6s2.8k / 978
CG-AL-E057easy20.0 / 1000/0FAIL10.3s2.3k / 1.1k
CG-AL-E058easy2100.0 / 1001/1OK13.7s1.4k / 328
CG-AL-H001hard1100.0 / 10025/25OK16.9s721 / 396
CG-AL-H002hard1100.0 / 1004/4OK20.1s742 / 858
CG-AL-H003hard1100.0 / 1005/5OK20.4s761 / 832
CG-AL-H004hard1100.0 / 10014/14OK18.3s774 / 663
CG-AL-H005hard1100.0 / 1006/6OK21.4s1.2k / 957
CG-AL-H006hard1100.0 / 1006/6OK16.3s710 / 363
CG-AL-H007hard1100.0 / 10010/10OK21.2s947 / 993
CG-AL-H008hard1100.0 / 10010/10OK17.7s881 / 584
CG-AL-H009hard1100.0 / 10011/11OK23.8s1.0k / 1.3k
CG-AL-H010hard1100.0 / 1008/8OK17.9s896 / 630
CG-AL-H011hard20.0 / 1000/0FAIL8.5s1.8k / 630
CG-AL-H013hard1100.0 / 1009/9OK19.7s602 / 486
CG-AL-H014hard2100.0 / 1007/7OK24.6s4.2k / 2.8k
CG-AL-H015hard1100.0 / 1004/4OK16.5s658 / 451
CG-AL-H016hard1100.0 / 1004/4OK16.5s698 / 435
CG-AL-H017hard20.0 / 1000/0FAIL9.8s1.7k / 938
CG-AL-H018hard1100.0 / 1006/6OK19.5s727 / 823
CG-AL-H019hard1100.0 / 1005/5OK14.6s528 / 231
CG-AL-H020hard1100.0 / 10010/10OK22.5s781 / 1.2k
CG-AL-H021hard2100.0 / 10020/20OK26.6s30k / 2.4k
CG-AL-H022hard1100.0 / 10021/21OK24.6s1.2k / 1.5k
CG-AL-H023hard20.0 / 1000/0FAIL57.9s5.8k / 13k
CG-AL-H024hard1100.0 / 1009/9OK23.8s847 / 1.3k
CG-AL-H025hard1100.0 / 1007/7OK16.0s570 / 300
CG-AL-H026hard1100.0 / 1008/8OK17.6s745 / 543
CG-AL-H027hard2100.0 / 1004/4OK15.4s3.4k / 616
CG-AL-H028hard1100.0 / 1009/9OK20.1s1.0k / 772
CG-AL-H029hard1100.0 / 10018/18OK25.4s1.3k / 1.6k
CG-AL-H030hard1100.0 / 10010/10OK23.0s1.1k / 1.1k
CG-AL-H031hard1100.0 / 10022/22OK26.0s1.6k / 1.6k
CG-AL-H032hard1100.0 / 10019/19OK25.3s1.3k / 1.5k
CG-AL-H033hard1100.0 / 1005/5OK2m 46s1.2k / 2.2k
CG-AL-H034hard2100.0 / 1003/3OK13.3s2.1k / 461
CG-AL-H035hard1100.0 / 1003/3OK14.5s495 / 198
CG-AL-H036hard20.0 / 1000/0FAIL9.3s1.7k / 449
CG-AL-H037hard20.0 / 1000/0FAIL8.0s2.1k / 528
CG-AL-H038hard1100.0 / 1003/3OK15.2s887 / 334
CG-AL-H039hard1100.0 / 1004/4OK15.6s773 / 382
CG-AL-H040hard1100.0 / 1002/2OK15.2s645 / 265
CG-AL-H041hard262.5 / 1001/3OK16.4s2.5k / 1.2k
CG-AL-H042hard1100.0 / 1003/3OK14.3s658 / 179
CG-AL-H043hard1100.0 / 1005/5OK14.3s650 / 168
CG-AL-H050hard262.5 / 1002/3OK14.4s1.9k / 540
CG-AL-H051hard1100.0 / 1004/4OK13.8s989 / 197
CG-AL-H052hard1100.0 / 1005/5OK13.6s1.1k / 155
CG-AL-H053hard1100.0 / 1004/4OK15.3s847 / 339
CG-AL-H054hard20.0 / 1000/0FAIL10.6s3.0k / 1.1k
CG-AL-H056hard20.0 / 1000/0FAIL7.3s2.4k / 449
CG-AL-H057hard1100.0 / 1004/4OK2m 35s1.1k / 487
CG-AL-H058hard1100.0 / 1005/5OK16.1s929 / 457
CG-AL-H205hard1100.0 / 1006/6OK17.6s779 / 662
CG-AL-M001medium20.0 / 1000/0FAIL12.8s2.3k / 1.6k
CG-AL-M002medium1100.0 / 10022/22OK20.0s725 / 877
CG-AL-M003medium1100.0 / 1009/9OK23.7s687 / 1.2k
CG-AL-M004medium1100.0 / 10012/12OK2m 41s773 / 2.0k
CG-AL-M005medium1100.0 / 10022/22OK38.8s943 / 3.0k
CG-AL-M006medium2100.0 / 10018/18OK27.3s3.1k / 3.9k
CG-AL-M007medium20.0 / 1000/0FAIL31.3s3.6k / 6.0k
CG-AL-M008medium2100.0 / 10012/12OK39.6s7.5k / 8.7k
CG-AL-M009medium1100.0 / 10011/11OK44.3s746 / 3.6k
CG-AL-M010medium1100.0 / 10021/21OK2m 43s958 / 3.1k
CG-AL-M020medium20.0 / 1000/0FAIL13.0s2.9k / 2.0k
CG-AL-M021medium1100.0 / 10011/11OK19.2s908 / 816
CG-AL-M022medium1100.0 / 1009/9OK20.8s810 / 1.1k
CG-AL-M023medium262.5 / 10010/11OK21.3s2.7k / 1.6k
CG-AL-M024medium1100.0 / 10010/10OK25.7s757 / 1.7k
CG-AL-M025medium1100.0 / 1007/7OK16.9s655 / 533
CG-AL-M026medium20.0 / 1000/0FAIL10.3s2.1k / 1.2k
CG-AL-M027medium2100.0 / 10018/18OK28.9s5.9k / 4.4k
CG-AL-M028medium20.0 / 1000/0FAIL9.9s1.7k / 898
CG-AL-M029medium2100.0 / 1003/3OK2m 17s1.4k / 299
CG-AL-M031medium20.0 / 1000/0FAIL14.9s3.0k / 2.3k
CG-AL-M032medium1100.0 / 1003/3OK15.1s793 / 363
CG-AL-M033medium1100.0 / 1002/2OK16.3s735 / 388
CG-AL-M034medium262.5 / 1001/2OK15.6s2.3k / 972
CG-AL-M035medium1100.0 / 1002/2OK13.6s544 / 157
CG-AL-M036medium1100.0 / 1002/2OK17.0s910 / 515
CG-AL-M037medium20.0 / 1000/0FAIL9.4s2.1k / 708
CG-AL-M038medium1100.0 / 1002/2OK15.8s638 / 266
CG-AL-M039medium2100.0 / 1002/2OK2m 19s2.2k / 1.3k
CG-AL-M040medium20.0 / 1000/0FAIL14.3s1.3k / 465
CG-AL-M041medium1100.0 / 1003/3OK13.1s501 / 157
CG-AL-M042medium1100.0 / 1008/8OK17.6s753 / 365
CG-AL-M043medium1100.0 / 1005/5OK16.1s677 / 406
CG-AL-M044medium1100.0 / 1006/6OK2m 37s985 / 867
CG-AL-M045medium1100.0 / 1006/6OK14.5s1.0k / 242
CG-AL-M088medium1100.0 / 1006/6OK17.9s673 / 671
CG-AL-M112medium1100.0 / 1004/4OK21.4s908 / 1.1k