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.

65.7 / 100
Cost $4.64
Tokens 204k / 145k input / output, all attempts
Duration 1h 25m
Filter:
Per-task results for run ef4e640a-646e-4ec1-8044-34f9e25a3fb4
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.1s413 / 316
CG-AL-E002easy1100.0 / 1006/6OK2m 25s428 / 425
CG-AL-E003easy1100.0 / 1005/5OK24.5s405 / 150
CG-AL-E004easy1100.0 / 1006/6OK28.4s465 / 365
CG-AL-E005easy1100.0 / 10013/13OK35.0s486 / 770
CG-AL-E006easy1100.0 / 1007/7OK2m 44s465 / 594
CG-AL-E007easy1100.0 / 1007/7OK42.1s553 / 240
CG-AL-E008easy1100.0 / 1006/6OK47.3s465 / 487
CG-AL-E009easy1100.0 / 1005/5OK50.9s437 / 237
CG-AL-E010easy2100.0 / 1005/5OK18.1s1.2k / 421
CG-AL-E031easy1100.0 / 1003/3OK53.1s673 / 567
CG-AL-E032easy1100.0 / 1001/1OK54.4s372 / 239
CG-AL-E045easy1100.0 / 1004/4OK18.5s560 / 430
CG-AL-E050easy1100.0 / 10013/13OK18.6s630 / 315
CG-AL-E051easy1100.0 / 10015/15OK26.0s771 / 996
CG-AL-E052easy2100.0 / 10016/16OK17.6s2.4k / 759
CG-AL-E053easy1100.0 / 1003/3OK2m 21s456 / 170
CG-AL-E054easy2100.0 / 1009/9OK16.8s1.7k / 670
CG-AL-E055easy1100.0 / 1008/8OK17.0s561 / 299
CG-AL-E056easy2100.0 / 10015/15OK18.6s2.8k / 1.0k
CG-AL-E057easy20.0 / 1000/0FAIL10.0s2.3k / 1.1k
CG-AL-E058easy2100.0 / 1001/1OK15.3s1.4k / 328
CG-AL-H001hard1100.0 / 10025/25OK17.3s721 / 426
CG-AL-H002hard1100.0 / 1004/4OK23.2s742 / 873
CG-AL-H003hard1100.0 / 1005/5OK26.5s761 / 848
CG-AL-H004hard1100.0 / 10014/14OK19.8s774 / 663
CG-AL-H005hard1100.0 / 1006/6OK22.0s1.2k / 824
CG-AL-H006hard1100.0 / 1006/6OK17.5s710 / 363
CG-AL-H007hard1100.0 / 10010/10OK22.5s947 / 995
CG-AL-H008hard1100.0 / 10010/10OK19.9s881 / 584
CG-AL-H009hard1100.0 / 10011/11OK27.7s1.0k / 1.3k
CG-AL-H010hard1100.0 / 1008/8OK18.9s896 / 630
CG-AL-H011hard20.0 / 1000/0FAIL8.5s1.6k / 659
CG-AL-H013hard1100.0 / 1009/9OK18.8s602 / 464
CG-AL-H014hard20.0 / 1000/0FAIL18.0s4.4k / 3.1k
CG-AL-H015hard1100.0 / 1004/4OK19.2s658 / 444
CG-AL-H016hard1100.0 / 1004/4OK18.1s698 / 435
CG-AL-H017hard20.0 / 1000/0FAIL9.0s1.6k / 776
CG-AL-H018hard1100.0 / 1006/6OK24.2s727 / 1.1k
CG-AL-H019hard1100.0 / 1005/5OK17.6s528 / 231
CG-AL-H020hard1100.0 / 10010/10OK22.7s781 / 1.1k
CG-AL-H021hard2100.0 / 10020/20OK25.1s30k / 2.2k
CG-AL-H022hard1100.0 / 10021/21OK26.5s1.2k / 1.5k
CG-AL-H023hard20.0 / 1000/0FAIL2m 19s22k / 22k
CG-AL-H024hard1100.0 / 1009/9OK49.1s847 / 1.3k
CG-AL-H025hard1100.0 / 1007/7OK22.0s570 / 300
CG-AL-H026hard1100.0 / 1008/8OK25.5s745 / 532
CG-AL-H027hard2100.0 / 1004/4OK17.4s3.4k / 624
CG-AL-H028hard1100.0 / 1009/9OK39.3s1.0k / 754
CG-AL-H029hard20.0 / 1000/0FAIL18.8s4.5k / 3.2k
CG-AL-H030hard2100.0 / 10010/10OK22.1s3.4k / 2.1k
CG-AL-H031hard1100.0 / 10022/22OK28.5s1.6k / 1.6k
CG-AL-H032hard1100.0 / 10019/19OK27.8s1.3k / 1.6k
CG-AL-H033hard1100.0 / 1005/5OK2m 39s1.2k / 2.2k
CG-AL-H034hard2100.0 / 1003/3OK15.9s2.1k / 461
CG-AL-H035hard1100.0 / 1003/3OK17.6s495 / 198
CG-AL-H036hard20.0 / 1000/0FAIL8.2s1.7k / 508
CG-AL-H037hard10.0 / 1000/0FAIL0ms0 / 0
CG-AL-H038hard1100.0 / 1003/3OK17.0s887 / 395
CG-AL-H039hard1100.0 / 1004/4OK18.0s773 / 424
CG-AL-H040hard1100.0 / 1002/2OK16.2s645 / 250
CG-AL-H041hard1100.0 / 1003/3OK19.4s923 / 606
CG-AL-H042hard1100.0 / 1003/3OK17.3s658 / 179
CG-AL-H043hard1100.0 / 1005/5OK15.3s650 / 168
CG-AL-H050hard20.0 / 1000/0FAIL12.7s2.4k / 688
CG-AL-H051hard1100.0 / 1004/4OK17.6s989 / 197
CG-AL-H052hard1100.0 / 1005/5OK15.2s1.1k / 155
CG-AL-H053hard1100.0 / 1004/4OK17.9s847 / 339
CG-AL-H054hard20.0 / 1000/0FAIL15.1s3.0k / 1.0k
CG-AL-H056hard20.0 / 1000/0FAIL7.8s2.4k / 449
CG-AL-H057hard1100.0 / 1004/4OK2m 26s1.1k / 488
CG-AL-H058hard1100.0 / 1005/5OK18.0s929 / 453
CG-AL-H205hard1100.0 / 1006/6OK19.5s779 / 662
CG-AL-M001medium20.0 / 1000/0FAIL11.9s2.2k / 1.4k
CG-AL-M002medium1100.0 / 10022/22OK22.2s725 / 869
CG-AL-M003medium1100.0 / 1009/9OK26.1s687 / 1.2k
CG-AL-M004medium1100.0 / 10012/12OK2m 42s773 / 1.9k
CG-AL-M005medium1100.0 / 10022/22OK40.6s943 / 3.0k
CG-AL-M006medium1100.0 / 10018/18OK33.2s705 / 2.1k
CG-AL-M007medium20.0 / 1000/0FAIL30.0s3.4k / 6.0k
CG-AL-M008medium20.0 / 1000/0FAIL3m 14s15k / 21k
CG-AL-M009medium1100.0 / 10011/11OK1m 42s746 / 3.2k
CG-AL-M010medium1100.0 / 10021/21OK5m 10s958 / 3.2k
CG-AL-M020medium2100.0 / 10017/17OK48.6s2.9k / 1.9k
CG-AL-M021medium1100.0 / 10011/11OK2m 9s908 / 803
CG-AL-M022medium1100.0 / 1009/9OK28.0s810 / 1.1k
CG-AL-M023medium262.5 / 10010/11OK21.9s2.7k / 1.6k
CG-AL-M024medium1100.0 / 10010/10OK47.3s757 / 1.5k
CG-AL-M025medium1100.0 / 1007/7OK19.2s655 / 533
CG-AL-M026medium20.0 / 1000/0FAIL12.2s1.9k / 1.2k
CG-AL-M027medium2100.0 / 10018/18OK31.0s5.9k / 4.4k
CG-AL-M028medium2100.0 / 1003/3OK2m 22s1.7k / 898
CG-AL-M029medium2100.0 / 1003/3OK2m 19s1.4k / 284
CG-AL-M031medium20.0 / 1000/0FAIL13.5s2.9k / 2.2k
CG-AL-M032medium2100.0 / 1003/3OK16.1s2.6k / 670
CG-AL-M033medium1100.0 / 1002/2OK17.3s735 / 389
CG-AL-M034medium262.5 / 1001/2OK17.2s2.6k / 698
CG-AL-M035medium1100.0 / 1002/2OK16.0s544 / 157
CG-AL-M036medium2100.0 / 1002/2OK17.5s2.5k / 988
CG-AL-M037medium20.0 / 1000/0FAIL12.6s2.1k / 708
CG-AL-M038medium1100.0 / 1002/2OK16.8s638 / 266
CG-AL-M039medium20.0 / 1000/0FAIL12.6s2.1k / 1.2k
CG-AL-M040medium20.0 / 1000/0FAIL8.6s1.3k / 465
CG-AL-M041medium1100.0 / 1003/3OK16.0s501 / 157
CG-AL-M042medium1100.0 / 1008/8OK17.2s753 / 365
CG-AL-M043medium1100.0 / 1005/5OK17.8s677 / 410
CG-AL-M044medium1100.0 / 1006/6OK2m 39s985 / 867
CG-AL-M045medium1100.0 / 1006/6OK18.5s1.0k / 242
CG-AL-M088medium1100.0 / 1006/6OK19.5s673 / 680
CG-AL-M112medium1100.0 / 1004/4OK22.2s908 / 1.1k