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.

68.9 / 100
Cost $4.22
Tokens 198k / 129k input / output, all attempts
Duration 2h 6m
Filter:
Per-task results for run e5dcc595-a287-43b8-8191-f144e24b2a7b
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK20.8s418 / 433
CG-AL-E002easy1100.0 / 1006/6OK2m 37s433 / 378
CG-AL-E003easy1100.0 / 1005/5OK27.4s410 / 166
CG-AL-E004easy2100.0 / 1006/6OK18.6s1.3k / 758
CG-AL-E005easy2100.0 / 10013/13OK19.9s1.4k / 1.1k
CG-AL-E006easy1100.0 / 1007/7OK2m 55s470 / 596
CG-AL-E007easy1100.0 / 1007/7OK49.1s558 / 242
CG-AL-E008easy1100.0 / 1006/6OK53.8s470 / 473
CG-AL-E009easy1100.0 / 1005/5OK59.3s442 / 254
CG-AL-E010easy1100.0 / 1005/5OK1m 1s467 / 188
CG-AL-E031easy1100.0 / 1003/3OK1m 4s678 / 659
CG-AL-E032easy1100.0 / 1001/1OK10m 32s377 / 89
CG-AL-E045easy1100.0 / 1004/4OK20.3s565 / 509
CG-AL-E050easy2100.0 / 10013/13OK20.0s3.0k / 604
CG-AL-E051easy1100.0 / 10015/15OK23.2s776 / 845
CG-AL-E052easy2100.0 / 10016/16OK18.9s2.4k / 763
CG-AL-E053easy1100.0 / 1003/3OK2m 43s461 / 176
CG-AL-E054easy2100.0 / 1009/9OK20.4s1.7k / 746
CG-AL-E055easy1100.0 / 1008/8OK18.7s566 / 301
CG-AL-E056easy262.5 / 10013/15OK19.0s2.8k / 998
CG-AL-E057easy20.0 / 1000/0FAIL10.7s2.2k / 1.1k
CG-AL-E058easy1100.0 / 1001/1OK16.7s628 / 168
CG-AL-H001hard1100.0 / 10025/25OK18.8s726 / 427
CG-AL-H002hard1100.0 / 1004/4OK22.5s747 / 750
CG-AL-H003hard1100.0 / 1005/5OK24.4s766 / 898
CG-AL-H004hard1100.0 / 10014/14OK21.2s779 / 625
CG-AL-H005hard1100.0 / 1006/6OK24.2s1.2k / 948
CG-AL-H006hard1100.0 / 1006/6OK19.2s715 / 365
CG-AL-H007hard1100.0 / 10010/10OK23.6s952 / 968
CG-AL-H008hard1100.0 / 10010/10OK30.2s886 / 586
CG-AL-H009hard1100.0 / 10011/11OK26.0s1.0k / 1.3k
CG-AL-H010hard1100.0 / 1008/8OK21.3s901 / 632
CG-AL-H011hard20.0 / 1000/0FAIL8.1s1.5k / 572
CG-AL-H013hard1100.0 / 1009/9OK21.7s607 / 397
CG-AL-H014hard20.0 / 1000/0FAIL11.7s2.4k / 1.5k
CG-AL-H015hard1100.0 / 1004/4OK18.8s663 / 431
CG-AL-H016hard1100.0 / 1004/4OK19.0s703 / 402
CG-AL-H017hard20.0 / 1000/0FAIL9.3s1.6k / 708
CG-AL-H018hard1100.0 / 1006/6OK23.3s732 / 942
CG-AL-H019hard1100.0 / 1005/5OK18.1s533 / 238
CG-AL-H020hard2100.0 / 10010/10OK24.2s2.8k / 2.2k
CG-AL-H021hard2100.0 / 10020/20OK27.1s30k / 2.2k
CG-AL-H022hard1100.0 / 10021/21OK27.9s1.2k / 1.4k
CG-AL-H023hard20.0 / 1000/0FAIL2m 28s22k / 22k
CG-AL-H024hard1100.0 / 1009/9OK2m 11s852 / 1.3k
CG-AL-H025hard1100.0 / 1007/7OK21.1s575 / 453
CG-AL-H026hard1100.0 / 1008/8OK20.6s750 / 473
CG-AL-H027hard2100.0 / 1004/4OK21.8s3.4k / 849
CG-AL-H028hard1100.0 / 1009/9OK30.5s1.1k / 800
CG-AL-H029hard262.5 / 10016/18OK31.2s4.5k / 3.5k
CG-AL-H030hard262.5 / 1008/10OK29.9s4.5k / 3.1k
CG-AL-H031hard1100.0 / 10022/22OK32.3s1.6k / 1.8k
CG-AL-H032hard1100.0 / 10019/19OK31.7s1.3k / 1.4k
CG-AL-H033hard1100.0 / 1005/5OK3m 15s1.2k / 2.2k
CG-AL-H034hard2100.0 / 1003/3OK18.4s2.1k / 465
CG-AL-H035hard1100.0 / 1003/3OK17.7s500 / 162
CG-AL-H036hard20.0 / 1000/0FAIL9.2s1.6k / 450
CG-AL-H037hard1100.0 / 1003/3OK19.1s810 / 274
CG-AL-H038hard1100.0 / 1003/3OK19.0s892 / 346
CG-AL-H039hard1100.0 / 1004/4OK21.2s778 / 551
CG-AL-H040hard1100.0 / 1002/2OK19.7s650 / 252
CG-AL-H041hard1100.0 / 1003/3OK21.3s928 / 581
CG-AL-H042hard1100.0 / 1003/3OK18.7s663 / 181
CG-AL-H043hard1100.0 / 1005/5OK17.0s655 / 150
CG-AL-H050hard2100.0 / 1003/3OK18.9s2.3k / 503
CG-AL-H051hard1100.0 / 1004/4OK19.3s994 / 196
CG-AL-H052hard1100.0 / 1005/5OK17.9s1.1k / 157
CG-AL-H053hard1100.0 / 1004/4OK19.0s852 / 341
CG-AL-H054hard20.0 / 1000/0FAIL10.5s3.0k / 1.1k
CG-AL-H056hard20.0 / 1000/0FAIL7.8s2.4k / 454
CG-AL-H057hard1100.0 / 1004/4OK2m 34s1.1k / 403
CG-AL-H058hard1100.0 / 1005/5OK20.6s934 / 459
CG-AL-H205hard1100.0 / 1006/6OK29.0s784 / 664
CG-AL-M001medium20.0 / 1000/0FAIL11.9s2.3k / 1.4k
CG-AL-M002medium1100.0 / 10022/22OK28.5s730 / 854
CG-AL-M003medium1100.0 / 1009/9OK27.4s692 / 1.1k
CG-AL-M004medium2100.0 / 10012/12OK2m 58s2.8k / 3.1k
CG-AL-M005medium1100.0 / 10022/22OK40.8s948 / 2.6k
CG-AL-M006medium1100.0 / 10018/18OK35.0s710 / 1.8k
CG-AL-M007medium20.0 / 1000/0FAIL27.1s3.8k / 4.8k
CG-AL-M008medium2100.0 / 10012/12OK1m 4s5.0k / 8.0k
CG-AL-M009medium1100.0 / 10011/11OK2m 9s751 / 2.4k
CG-AL-M010medium1100.0 / 10021/21OK5m 5s963 / 2.8k
CG-AL-M020medium2100.0 / 10017/17OK43.0s3.0k / 2.0k
CG-AL-M021medium2100.0 / 10011/11OK28.4s2.8k / 1.6k
CG-AL-M022medium1100.0 / 1009/9OK33.6s815 / 1.1k
CG-AL-M023medium262.5 / 10010/11OK24.0s2.7k / 1.5k
CG-AL-M024medium1100.0 / 10010/10OK27.4s762 / 1.4k
CG-AL-M025medium1100.0 / 1007/7OK20.5s660 / 529
CG-AL-M026medium20.0 / 1000/0FAIL20.6s2.2k / 1.1k
CG-AL-M027medium2100.0 / 10018/18OK33.5s6.0k / 4.1k
CG-AL-M028medium20.0 / 1000/0FAIL11.7s1.7k / 817
CG-AL-M029medium2100.0 / 1003/3OK2m 32s1.4k / 318
CG-AL-M031medium20.0 / 1000/0FAIL15.1s3.0k / 2.4k
CG-AL-M032medium1100.0 / 1003/3OK18.2s798 / 320
CG-AL-M033medium1100.0 / 1002/2OK20.8s740 / 390
CG-AL-M034medium262.5 / 1000/2OK17.1s2.6k / 621
CG-AL-M035medium1100.0 / 1002/2OK17.9s549 / 159
CG-AL-M036medium1100.0 / 1002/2OK19.9s915 / 502
CG-AL-M037medium20.0 / 1000/0FAIL9.5s2.1k / 712
CG-AL-M038medium1100.0 / 1002/2OK19.2s643 / 268
CG-AL-M039medium1100.0 / 1002/2OK2m 34s715 / 499
CG-AL-M040medium20.0 / 1000/0FAIL9.8s1.3k / 474
CG-AL-M041medium1100.0 / 1003/3OK17.5s506 / 159
CG-AL-M042medium1100.0 / 1008/8OK20.4s758 / 405
CG-AL-M043medium1100.0 / 1005/5OK20.7s682 / 386
CG-AL-M044medium1100.0 / 1006/6OK2m 43s990 / 827
CG-AL-M045medium1100.0 / 1006/6OK17.7s1.0k / 262
CG-AL-M088medium1100.0 / 1006/6OK21.6s678 / 620
CG-AL-M112medium1100.0 / 1004/4OK26.0s913 / 1.1k