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.

80.9% 89/110 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.

67.9 / 100
Cost $3.92
Tokens 175k / 122k input / output, all attempts
Duration 1h 6m
Filter:
Per-task results for run 7fb765a9-3404-4c1b-a330-70825dcaf708
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK27.0s413 / 386
CG-AL-E002easy1100.0 / 1006/6OK2m 50s428 / 373
CG-AL-E003easy1100.0 / 1005/5OK38.7s405 / 150
CG-AL-E004easy1100.0 / 1006/6OK35.5s465 / 365
CG-AL-E005easy1100.0 / 10013/13OK37.4s486 / 495
CG-AL-E006easy1100.0 / 1007/7OK2m 53s465 / 599
CG-AL-E007easy1100.0 / 1007/7OK38.8s553 / 240
CG-AL-E008easy1100.0 / 1006/6OK42.9s465 / 467
CG-AL-E009easy1100.0 / 1005/5OK50.7s437 / 237
CG-AL-E010easy1100.0 / 1005/5OK46.8s462 / 234
CG-AL-E031easy1100.0 / 1003/3OK46.2s673 / 657
CG-AL-E032easy1100.0 / 1001/1OK43.3s372 / 245
CG-AL-E045easy1100.0 / 1004/4OK16.3s560 / 437
CG-AL-E050easy1100.0 / 10013/13OK16.0s630 / 315
CG-AL-E051easy1100.0 / 10015/15OK25.4s771 / 1.3k
CG-AL-E052easy2100.0 / 10016/16OK17.0s2.4k / 759
CG-AL-E053easy1100.0 / 1003/3OK2m 32s456 / 170
CG-AL-E054easy2100.0 / 1009/9OK14.6s1.7k / 640
CG-AL-E055easy1100.0 / 1008/8OK15.7s561 / 299
CG-AL-E056easy262.5 / 10013/15OK16.8s3.8k / 1.0k
CG-AL-E057easy20.0 / 1000/0FAIL10.6s2.3k / 1.1k
CG-AL-E058easy1100.0 / 1001/1OK13.9s623 / 166
CG-AL-H001hard1100.0 / 10025/25OK16.5s721 / 426
CG-AL-H002hard1100.0 / 1004/4OK20.1s742 / 862
CG-AL-H003hard1100.0 / 1005/5OK20.6s761 / 832
CG-AL-H004hard1100.0 / 10014/14OK18.2s774 / 663
CG-AL-H005hard1100.0 / 1006/6OK20.3s1.2k / 873
CG-AL-H006hard1100.0 / 1006/6OK15.8s710 / 363
CG-AL-H007hard1100.0 / 10010/10OK21.3s947 / 970
CG-AL-H008hard1100.0 / 10010/10OK17.9s881 / 584
CG-AL-H009hard1100.0 / 10011/11OK23.3s1.0k / 1.3k
CG-AL-H010hard1100.0 / 1008/8OK18.2s896 / 630
CG-AL-H011hard20.0 / 1000/0FAIL8.0s1.6k / 610
CG-AL-H013hard1100.0 / 1009/9OK16.8s602 / 473
CG-AL-H014hard2100.0 / 1007/7OK23.3s4.1k / 2.7k
CG-AL-H015hard1100.0 / 1004/4OK16.0s658 / 447
CG-AL-H016hard1100.0 / 1004/4OK16.2s698 / 435
CG-AL-H017hard20.0 / 1000/0FAIL11.5s1.7k / 778
CG-AL-H018hard1100.0 / 1006/6OK20.7s727 / 1.0k
CG-AL-H019hard1100.0 / 1005/5OK14.0s528 / 231
CG-AL-H020hard1100.0 / 10010/10OK23.2s781 / 1.1k
CG-AL-H021hard2100.0 / 10020/20OK24.6s30k / 2.2k
CG-AL-H022hard1100.0 / 10021/21OK24.9s1.2k / 1.5k
CG-AL-H023hard20.0 / 1000/0FAIL59.1s6.0k / 13k
CG-AL-H024hard1100.0 / 1009/9OK23.4s847 / 1.3k
CG-AL-H025hard1100.0 / 1007/7OK15.6s570 / 300
CG-AL-H026hard1100.0 / 1008/8OK17.0s745 / 534
CG-AL-H027hard2100.0 / 1004/4OK16.5s3.4k / 623
CG-AL-H028hard1100.0 / 1009/9OK18.7s1.0k / 769
CG-AL-H029hard1100.0 / 10018/18OK26.4s1.3k / 1.6k
CG-AL-H030hard1100.0 / 10010/10OK29.1s1.1k / 1.4k
CG-AL-H031hard1100.0 / 10022/22OK26.0s1.6k / 1.7k
CG-AL-H032hard1100.0 / 10019/19OK25.0s1.3k / 1.4k
CG-AL-H033hard1100.0 / 1005/5OK2m 38s1.2k / 2.1k
CG-AL-H034hard2100.0 / 1003/3OK14.3s2.1k / 461
CG-AL-H035hard1100.0 / 1003/3OK14.7s495 / 198
CG-AL-H036hard20.0 / 1000/0FAIL9.2s1.7k / 452
CG-AL-H037hard2100.0 / 1003/3OK14.6s1.9k / 782
CG-AL-H038hard1100.0 / 1003/3OK15.3s887 / 334
CG-AL-H039hard1100.0 / 1004/4OK15.9s773 / 373
CG-AL-H040hard1100.0 / 1002/2OK15.7s645 / 255
CG-AL-H041hard1100.0 / 1003/3OK18.1s923 / 595
CG-AL-H042hard1100.0 / 1003/3OK14.4s658 / 179
CG-AL-H043hard1100.0 / 1005/5OK15.6s650 / 168
CG-AL-H050hard20.0 / 1000/0FAIL11.8s2.4k / 798
CG-AL-H051hard1100.0 / 1004/4OK14.7s989 / 194
CG-AL-H052hard1100.0 / 1005/5OK13.9s1.1k / 155
CG-AL-H053hard1100.0 / 1004/4OK16.2s847 / 333
CG-AL-H054hard20.0 / 1000/0FAIL11.1s3.0k / 1.1k
CG-AL-H056hard20.0 / 1000/0FAIL7.7s2.4k / 449
CG-AL-H057hard1100.0 / 1004/4OK2m 27s1.1k / 488
CG-AL-H058hard1100.0 / 1005/5OK17.0s929 / 457
CG-AL-H205hard1100.0 / 1006/6OK18.1s779 / 662
CG-AL-M001medium20.0 / 1000/0FAIL13.5s2.3k / 1.6k
CG-AL-M002medium1100.0 / 10022/22OK19.3s725 / 779
CG-AL-M003medium1100.0 / 1009/9OK21.4s687 / 974
CG-AL-M004medium20.0 / 1000/0FAIL21.4s2.9k / 3.8k
CG-AL-M005medium1100.0 / 10022/22OK41.1s943 / 3.2k
CG-AL-M006medium1100.0 / 10018/18OK31.2s705 / 2.0k
CG-AL-M007medium20.0 / 1000/0FAIL29.7s3.6k / 5.5k
CG-AL-M008medium262.5 / 10011/12OK43.9s3.8k / 8.2k
CG-AL-M009medium1100.0 / 10011/11OK40.2s746 / 3.2k
CG-AL-M010medium1100.0 / 10021/21OK3m 7s958 / 3.3k
CG-AL-M020medium2100.0 / 10017/17OK21.9s2.9k / 2.0k
CG-AL-M021medium1100.0 / 10011/11OK19.5s908 / 816
CG-AL-M022medium1100.0 / 1009/9OK21.6s810 / 1.1k
CG-AL-M023medium262.5 / 10010/11OK20.2s2.7k / 1.6k
CG-AL-M024medium1100.0 / 10010/10OK25.2s757 / 1.5k
CG-AL-M025medium1100.0 / 1007/7OK17.7s655 / 533
CG-AL-M026medium20.0 / 1000/0FAIL11.6s2.2k / 1.4k
CG-AL-M027medium2100.0 / 10018/18OK29.9s5.9k / 4.4k
CG-AL-M028medium20.0 / 1000/0FAIL9.6s1.7k / 891
CG-AL-M029medium20.0 / 1000/0FAIL7.5s1.4k / 310
CG-AL-M031medium20.0 / 1000/0FAIL13.9s3.0k / 2.2k
CG-AL-M032medium2100.0 / 1003/3OK14.7s2.6k / 657
CG-AL-M033medium1100.0 / 1002/2OK17.4s735 / 393
CG-AL-M034medium262.5 / 1001/2OK17.2s2.7k / 818
CG-AL-M035medium1100.0 / 1002/2OK13.8s544 / 157
CG-AL-M036medium2100.0 / 1002/2OK16.9s2.5k / 1.0k
CG-AL-M037medium20.0 / 1000/0FAIL8.8s2.1k / 722
CG-AL-M038medium1100.0 / 1002/2OK15.0s638 / 266
CG-AL-M039medium2100.0 / 1002/2OK2m 43s2.2k / 1.3k
CG-AL-M040medium20.0 / 1000/0FAIL8.7s1.3k / 466
CG-AL-M041medium1100.0 / 1003/3OK13.8s501 / 157
CG-AL-M042medium1100.0 / 1008/8OK16.3s753 / 410
CG-AL-M043medium1100.0 / 1005/5OK17.2s677 / 410
CG-AL-M044medium1100.0 / 1006/6OK2m 30s985 / 873
CG-AL-M045medium1100.0 / 1006/6OK15.0s1.0k / 242
CG-AL-M088medium1100.0 / 1006/6OK17.8s673 / 660
CG-AL-M112medium1100.0 / 1004/4OK21.0s908 / 969