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.

83.6% 92/110 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.

70.0 / 100
Cost $3.85
Tokens 171k / 120k input / output, all attempts
Duration 1h 10m
Filter:
Per-task results for run df0b62ba-cc34-48d6-9662-20217d799363
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.5s413 / 383
CG-AL-E002easy1100.0 / 1006/6OK2m 44s428 / 425
CG-AL-E003easy1100.0 / 1005/5OK20.3s405 / 150
CG-AL-E004easy1100.0 / 1006/6OK25.0s465 / 361
CG-AL-E005easy1100.0 / 10013/13OK29.5s486 / 568
CG-AL-E006easy1100.0 / 1007/7OK2m 44s465 / 594
CG-AL-E007easy1100.0 / 1007/7OK37.1s553 / 240
CG-AL-E008easy1100.0 / 1006/6OK40.0s465 / 506
CG-AL-E009easy1100.0 / 1005/5OK41.0s437 / 237
CG-AL-E010easy2100.0 / 1005/5OK14.8s1.2k / 461
CG-AL-E031easy1100.0 / 1003/3OK43.7s673 / 567
CG-AL-E032easy1100.0 / 1001/1OK39.0s372 / 239
CG-AL-E045easy1100.0 / 1004/4OK17.9s560 / 463
CG-AL-E050easy1100.0 / 10013/13OK16.8s630 / 382
CG-AL-E051easy1100.0 / 10015/15OK21.5s771 / 1.0k
CG-AL-E052easy2100.0 / 10016/16OK16.8s2.4k / 759
CG-AL-E053easy1100.0 / 1003/3OK2m 29s456 / 176
CG-AL-E054easy2100.0 / 1009/9OK15.4s1.7k / 670
CG-AL-E055easy1100.0 / 1008/8OK15.3s561 / 299
CG-AL-E056easy2100.0 / 10015/15OK17.1s2.8k / 978
CG-AL-E057easy20.0 / 1000/0FAIL10.5s2.2k / 1.1k
CG-AL-E058easy2100.0 / 1001/1OK13.7s1.5k / 328
CG-AL-H001hard1100.0 / 10025/25OK16.3s721 / 396
CG-AL-H002hard1100.0 / 1004/4OK20.1s742 / 862
CG-AL-H003hard1100.0 / 1005/5OK20.1s761 / 854
CG-AL-H004hard1100.0 / 10014/14OK17.9s774 / 663
CG-AL-H005hard1100.0 / 1006/6OK21.1s1.2k / 897
CG-AL-H006hard1100.0 / 1006/6OK16.1s710 / 363
CG-AL-H007hard1100.0 / 10010/10OK20.8s947 / 951
CG-AL-H008hard1100.0 / 10010/10OK17.9s881 / 584
CG-AL-H009hard1100.0 / 10011/11OK24.0s1.0k / 1.3k
CG-AL-H010hard1100.0 / 1008/8OK17.4s896 / 630
CG-AL-H011hard20.0 / 1000/0FAIL8.4s1.8k / 640
CG-AL-H013hard1100.0 / 1009/9OK16.8s602 / 480
CG-AL-H014hard2100.0 / 1007/7OK24.7s4.1k / 2.7k
CG-AL-H015hard1100.0 / 1004/4OK16.3s658 / 447
CG-AL-H016hard1100.0 / 1004/4OK17.4s698 / 424
CG-AL-H017hard20.0 / 1000/0FAIL12.1s1.7k / 942
CG-AL-H018hard1100.0 / 1006/6OK22.1s727 / 1.1k
CG-AL-H019hard1100.0 / 1005/5OK15.4s528 / 231
CG-AL-H020hard1100.0 / 10010/10OK22.3s781 / 1.2k
CG-AL-H021hard2100.0 / 10020/20OK24.3s29k / 2.1k
CG-AL-H022hard1100.0 / 10021/21OK26.5s1.2k / 1.5k
CG-AL-H023hard262.5 / 10024/25OK1m 4s5.6k / 12k
CG-AL-H024hard1100.0 / 1009/9OK23.7s847 / 1.3k
CG-AL-H025hard1100.0 / 1007/7OK14.8s570 / 304
CG-AL-H026hard1100.0 / 1008/8OK19.6s745 / 534
CG-AL-H027hard2100.0 / 1004/4OK16.0s3.4k / 632
CG-AL-H028hard1100.0 / 1009/9OK19.3s1.0k / 769
CG-AL-H029hard2100.0 / 10018/18OK25.4s4.4k / 3.3k
CG-AL-H030hard1100.0 / 10010/10OK23.1s1.1k / 1.2k
CG-AL-H031hard1100.0 / 10022/22OK27.9s1.6k / 1.6k
CG-AL-H032hard1100.0 / 10019/19OK27.6s1.3k / 1.6k
CG-AL-H033hard1100.0 / 1005/5OK3m 2s1.2k / 2.1k
CG-AL-H034hard2100.0 / 1003/3OK14.2s2.1k / 461
CG-AL-H035hard1100.0 / 1003/3OK15.5s495 / 198
CG-AL-H036hard2100.0 / 1005/5OK14.0s1.6k / 499
CG-AL-H037hard262.5 / 1002/3OK14.5s2.2k / 523
CG-AL-H038hard1100.0 / 1003/3OK16.1s887 / 334
CG-AL-H039hard1100.0 / 1004/4OK15.6s773 / 323
CG-AL-H040hard1100.0 / 1002/2OK15.1s645 / 255
CG-AL-H041hard20.0 / 1000/0FAIL11.0s2.5k / 1.2k
CG-AL-H042hard1100.0 / 1003/3OK14.4s658 / 179
CG-AL-H043hard1100.0 / 1005/5OK14.1s650 / 168
CG-AL-H050hard262.5 / 1002/3OK14.7s2.0k / 475
CG-AL-H051hard1100.0 / 1004/4OK14.2s989 / 197
CG-AL-H052hard1100.0 / 1005/5OK13.8s1.1k / 155
CG-AL-H053hard1100.0 / 1004/4OK15.3s847 / 339
CG-AL-H054hard20.0 / 1000/0FAIL10.2s3.0k / 1.1k
CG-AL-H056hard20.0 / 1000/0FAIL8.0s2.4k / 449
CG-AL-H057hard1100.0 / 1004/4OK2m 29s1.1k / 484
CG-AL-H058hard1100.0 / 1005/5OK16.6s929 / 453
CG-AL-H205hard1100.0 / 1006/6OK19.6s779 / 662
CG-AL-M001medium20.0 / 1000/0FAIL12.4s2.3k / 1.6k
CG-AL-M002medium1100.0 / 10022/22OK19.4s725 / 861
CG-AL-M003medium1100.0 / 1009/9OK25.2s687 / 1.3k
CG-AL-M004medium1100.0 / 10012/12OK3m 4s773 / 2.0k
CG-AL-M005medium1100.0 / 10022/22OK43.4s943 / 2.9k
CG-AL-M006medium1100.0 / 10018/18OK31.8s705 / 2.1k
CG-AL-M007medium20.0 / 1000/0FAIL24.2s3.1k / 4.8k
CG-AL-M008medium262.5 / 1003/12OK44.6s3.5k / 9.4k
CG-AL-M009medium1100.0 / 10011/11OK39.0s746 / 2.8k
CG-AL-M010medium1100.0 / 10021/21OK2m 51s958 / 3.1k
CG-AL-M020medium2100.0 / 10017/17OK21.5s3.2k / 2.1k
CG-AL-M021medium1100.0 / 10011/11OK18.9s908 / 792
CG-AL-M022medium1100.0 / 1009/9OK22.6s810 / 1.1k
CG-AL-M023medium262.5 / 10010/11OK21.1s2.7k / 1.6k
CG-AL-M024medium1100.0 / 10010/10OK25.0s757 / 1.5k
CG-AL-M025medium1100.0 / 1007/7OK17.9s655 / 505
CG-AL-M026medium1100.0 / 1008/8OK20.3s624 / 714
CG-AL-M027medium2100.0 / 10018/18OK29.4s5.8k / 4.4k
CG-AL-M028medium20.0 / 1000/0FAIL9.2s1.7k / 895
CG-AL-M029medium2100.0 / 1003/3OK2m 24s1.4k / 300
CG-AL-M031medium20.0 / 1000/0FAIL14.6s3.0k / 2.3k
CG-AL-M032medium1100.0 / 1003/3OK14.9s793 / 321
CG-AL-M033medium1100.0 / 1002/2OK16.6s735 / 386
CG-AL-M034medium262.5 / 1001/2OK17.2s2.6k / 800
CG-AL-M035medium1100.0 / 1002/2OK14.3s544 / 157
CG-AL-M036medium2100.0 / 1002/2OK16.6s2.5k / 972
CG-AL-M037medium20.0 / 1000/0FAIL9.1s2.1k / 708
CG-AL-M038medium1100.0 / 1002/2OK15.9s638 / 266
CG-AL-M039medium1100.0 / 1002/2OK2m 40s710 / 600
CG-AL-M040medium20.0 / 1000/0FAIL8.0s1.3k / 470
CG-AL-M041medium1100.0 / 1003/3OK13.9s501 / 157
CG-AL-M042medium1100.0 / 1008/8OK17.9s753 / 384
CG-AL-M043medium1100.0 / 1005/5OK16.3s677 / 406
CG-AL-M044medium1100.0 / 1006/6OK2m 31s985 / 865
CG-AL-M045medium1100.0 / 1006/6OK14.3s1.0k / 242
CG-AL-M088medium1100.0 / 1006/6OK18.3s673 / 650
CG-AL-M112medium1100.0 / 1004/4OK21.0s908 / 969