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.

81.4 / 100
Cost $12.37
Tokens 190k / 209k input / output, all attempts
Duration 1h 18m
Filter:
Per-task results for run 021a60c0-85d1-4ce5-ab68-16f1fa1dd475
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK37.8s413 / 463
CG-AL-E002easy1100.0 / 1006/6OK33.7s428 / 454
CG-AL-E003easy1100.0 / 1005/5OK41.5s405 / 184
CG-AL-E004easy1100.0 / 1006/6OK43.8s465 / 446
CG-AL-E005easy1100.0 / 10013/13OK48.2s486 / 650
CG-AL-E006easy1100.0 / 1007/7OK1m 5s465 / 751
CG-AL-E007easy1100.0 / 1007/7OK38.7s553 / 240
CG-AL-E008easy1100.0 / 1006/6OK24.3s465 / 923
CG-AL-E009easy1100.0 / 1005/5OK20.7s437 / 380
CG-AL-E010easy1100.0 / 1005/5OK18.4s462 / 353
CG-AL-E031easy1100.0 / 1003/3OK19.3s673 / 638
CG-AL-E032easy1100.0 / 1001/1OK21.3s372 / 251
CG-AL-E045easy1100.0 / 1004/4OK19.1s560 / 546
CG-AL-E050easy1100.0 / 10013/13OK28.2s630 / 1.2k
CG-AL-E051easy1100.0 / 10015/15OK36.2s771 / 2.1k
CG-AL-E052easy2100.0 / 10016/16OK19.8s2.5k / 987
CG-AL-E053easy1100.0 / 1003/3OK53.4s456 / 250
CG-AL-E054easy2100.0 / 1009/9OK21.8s1.7k / 1.2k
CG-AL-E055easy1100.0 / 1008/8OK19.2s561 / 385
CG-AL-E056easy2100.0 / 10015/15OK22.8s2.8k / 1.1k
CG-AL-E057easy2100.0 / 1008/8OK37.3s2.1k / 2.7k
CG-AL-E058easy1100.0 / 1001/1OK17.3s623 / 290
CG-AL-H001hard1100.0 / 10025/25OK18.4s721 / 406
CG-AL-H002hard1100.0 / 1004/4OK21.4s742 / 902
CG-AL-H003hard1100.0 / 1005/5OK23.3s761 / 899
CG-AL-H004hard1100.0 / 10014/14OK19.2s774 / 598
CG-AL-H005hard1100.0 / 1006/6OK22.8s1.2k / 889
CG-AL-H006hard1100.0 / 1006/6OK17.7s710 / 363
CG-AL-H007hard1100.0 / 10010/10OK27.7s947 / 1.4k
CG-AL-H008hard1100.0 / 10010/10OK19.8s881 / 705
CG-AL-H009hard1100.0 / 10011/11OK21.9s1.0k / 1.0k
CG-AL-H010hard1100.0 / 1008/8OK19.2s896 / 690
CG-AL-H011hard1100.0 / 1005/5OK19.2s574 / 552
CG-AL-H013hard1100.0 / 1009/9OK25.7s602 / 937
CG-AL-H014hard2100.0 / 1007/7OK22.9s2.2k / 1.9k
CG-AL-H015hard1100.0 / 1004/4OK17.9s658 / 438
CG-AL-H016hard1100.0 / 1004/4OK22.0s698 / 671
CG-AL-H017hard1100.0 / 1003/3OK27.9s610 / 1.3k
CG-AL-H018hard1100.0 / 1006/6OK30.5s727 / 1.8k
CG-AL-H019hard1100.0 / 1005/5OK20.4s528 / 524
CG-AL-H020hard1100.0 / 10010/10OK24.4s781 / 1.3k
CG-AL-H021hard2100.0 / 10020/20OK29.0s29k / 2.6k
CG-AL-H022hard1100.0 / 10021/21OK30.4s1.2k / 1.6k
CG-AL-H023hard20.0 / 1000/0FAIL2m 45s17k / 32k
CG-AL-H024hard1100.0 / 1009/9OK23.9s847 / 1.2k
CG-AL-H025hard1100.0 / 1007/7OK19.0s570 / 318
CG-AL-H026hard1100.0 / 1008/8OK19.8s745 / 557
CG-AL-H027hard1100.0 / 1004/4OK24.6s1.1k / 993
CG-AL-H028hard1100.0 / 1009/9OK21.0s1.0k / 859
CG-AL-H029hard1100.0 / 10018/18OK44.4s1.3k / 3.1k
CG-AL-H030hard1100.0 / 10010/10OK28.6s1.1k / 1.5k
CG-AL-H031hard1100.0 / 10022/22OK37.5s1.6k / 1.9k
CG-AL-H032hard1100.0 / 10019/19OK36.1s1.3k / 1.6k
CG-AL-H033hard1100.0 / 1005/5OK49.7s1.2k / 2.2k
CG-AL-H034hard1100.0 / 1003/3OK23.2s720 / 734
CG-AL-H035hard1100.0 / 1003/3OK23.6s495 / 262
CG-AL-H036hard1100.0 / 1005/5OK35.9s638 / 1.4k
CG-AL-H037hard1100.0 / 1003/3OK22.0s805 / 360
CG-AL-H038hard1100.0 / 1003/3OK22.2s887 / 615
CG-AL-H039hard1100.0 / 1004/4OK18.3s773 / 402
CG-AL-H040hard1100.0 / 1002/2OK18.5s645 / 339
CG-AL-H041hard1100.0 / 1003/3OK25.9s923 / 996
CG-AL-H042hard1100.0 / 1003/3OK20.6s658 / 456
CG-AL-H043hard1100.0 / 1005/5OK23.7s650 / 259
CG-AL-H050hard1100.0 / 1003/3OK27.3s813 / 994
CG-AL-H051hard1100.0 / 1004/4OK18.1s989 / 285
CG-AL-H052hard1100.0 / 1005/5OK16.6s1.1k / 203
CG-AL-H053hard1100.0 / 1004/4OK18.8s847 / 370
CG-AL-H054hard2100.0 / 1005/5OK20.1s3.0k / 1.2k
CG-AL-H056hard2100.0 / 1004/4OK22.8s2.4k / 964
CG-AL-H057hard1100.0 / 1004/4OK31.3s1.1k / 489
CG-AL-H058hard1100.0 / 1005/5OK25.1s929 / 609
CG-AL-H205hard1100.0 / 1006/6OK21.3s779 / 770
CG-AL-M001medium20.0 / 1000/0FAIL25.4s2.4k / 2.1k
CG-AL-M002medium1100.0 / 10022/22OK22.8s725 / 1.0k
CG-AL-M003medium1100.0 / 1009/9OK29.5s687 / 1.4k
CG-AL-M004medium1100.0 / 10012/12OK1m 13s773 / 2.3k
CG-AL-M005medium1100.0 / 10022/22OK56.0s943 / 3.3k
CG-AL-M006medium2100.0 / 10018/18OK32.7s3.9k / 4.8k
CG-AL-M007medium20.0 / 1000/0FAIL2m 28s13k / 29k
CG-AL-M008medium20.0 / 1000/0FAIL2m 53s17k / 32k
CG-AL-M009medium20.0 / 1000/0FAIL1m 30s7.5k / 9.4k
CG-AL-M010medium1100.0 / 10021/21OK2m 6s958 / 3.4k
CG-AL-M020medium1100.0 / 10017/17OK1m 40s883 / 1.1k
CG-AL-M021medium1100.0 / 10011/11OK52.7s908 / 887
CG-AL-M022medium1100.0 / 1009/9OK52.5s810 / 1.0k
CG-AL-M023medium262.5 / 10010/11OK44.3s2.8k / 2.6k
CG-AL-M024medium1100.0 / 10010/10OK26.3s757 / 1.5k
CG-AL-M025medium1100.0 / 1007/7OK35.4s655 / 635
CG-AL-M026medium1100.0 / 1008/8OK36.7s624 / 545
CG-AL-M027medium1100.0 / 10018/18OK32.4s1.4k / 1.9k
CG-AL-M028medium2100.0 / 1003/3OK30.9s1.7k / 909
CG-AL-M029medium2100.0 / 1003/3OK40.7s1.4k / 548
CG-AL-M031medium2100.0 / 1002/2OK25.2s2.9k / 2.4k
CG-AL-M032medium1100.0 / 1003/3OK26.0s793 / 339
CG-AL-M033medium1100.0 / 1002/2OK18.1s735 / 371
CG-AL-M034medium262.5 / 1001/2OK21.1s2.6k / 1.2k
CG-AL-M035medium1100.0 / 1002/2OK16.9s544 / 192
CG-AL-M036medium1100.0 / 1002/2OK19.0s910 / 573
CG-AL-M037medium20.0 / 1000/0FAIL24.9s2.1k / 2.0k
CG-AL-M038medium1100.0 / 1002/2OK16.5s638 / 345
CG-AL-M039medium1100.0 / 1002/2OK56.4s710 / 690
CG-AL-M040medium262.5 / 1001/2OK17.8s1.3k / 848
CG-AL-M041medium1100.0 / 1003/3OK17.4s501 / 167
CG-AL-M042medium1100.0 / 1008/8OK19.7s753 / 437
CG-AL-M043medium1100.0 / 1005/5OK18.1s677 / 406
CG-AL-M044medium1100.0 / 1006/6OK33.7s985 / 984
CG-AL-M045medium1100.0 / 1006/6OK23.6s1.0k / 648
CG-AL-M088medium1100.0 / 1006/6OK25.2s673 / 758
CG-AL-M112medium1100.0 / 1004/4OK22.0s908 / 981