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.

68.6 / 100
Cost $4.17
Tokens 194k / 128k input / output, all attempts
Duration 2h 12m
Filter:
Per-task results for run 7d67b00d-60e0-480c-b96c-2ae513ca1a01
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK20.4s418 / 433
CG-AL-E002easy1100.0 / 1006/6OK2m 39s433 / 376
CG-AL-E003easy1100.0 / 1005/5OK30.0s410 / 166
CG-AL-E004easy1100.0 / 1006/6OK34.3s470 / 367
CG-AL-E005easy1100.0 / 10013/13OK40.0s491 / 515
CG-AL-E006easy1100.0 / 1007/7OK26m 32s470 / 594
CG-AL-E007easy1100.0 / 1007/7OK49.9s558 / 242
CG-AL-E008easy1100.0 / 1006/6OK53.4s470 / 493
CG-AL-E009easy1100.0 / 1005/5OK1m 9s442 / 229
CG-AL-E010easy1100.0 / 1005/5OK1m 1s467 / 188
CG-AL-E031easy1100.0 / 1003/3OK1m 3s678 / 659
CG-AL-E032easy1100.0 / 1001/1OK59.7s377 / 89
CG-AL-E045easy1100.0 / 1004/4OK20.0s565 / 432
CG-AL-E050easy2100.0 / 10013/13OK19.8s3.0k / 874
CG-AL-E051easy1100.0 / 10015/15OK27.7s776 / 1.3k
CG-AL-E052easy2100.0 / 10016/16OK19.3s2.4k / 763
CG-AL-E053easy1100.0 / 1003/3OK2m 35s461 / 195
CG-AL-E054easy2100.0 / 1009/9OK17.7s1.7k / 694
CG-AL-E055easy1100.0 / 1008/8OK18.8s566 / 301
CG-AL-E056easy262.5 / 10013/15OK19.9s3.8k / 992
CG-AL-E057easy20.0 / 1000/0FAIL10.5s2.2k / 1.1k
CG-AL-E058easy1100.0 / 1001/1OK16.9s628 / 168
CG-AL-H001hard1100.0 / 10025/25OK19.7s726 / 439
CG-AL-H002hard1100.0 / 1004/4OK24.4s747 / 770
CG-AL-H003hard1100.0 / 1005/5OK24.1s766 / 898
CG-AL-H004hard1100.0 / 10014/14OK21.9s779 / 625
CG-AL-H005hard1100.0 / 1006/6OK26.0s1.2k / 903
CG-AL-H006hard1100.0 / 1006/6OK19.3s715 / 365
CG-AL-H007hard1100.0 / 10010/10OK24.6s952 / 1.0k
CG-AL-H008hard1100.0 / 10010/10OK20.7s886 / 586
CG-AL-H009hard1100.0 / 10011/11OK27.3s1.0k / 1.3k
CG-AL-H010hard1100.0 / 1008/8OK21.2s901 / 632
CG-AL-H011hard20.0 / 1000/0FAIL8.6s1.5k / 586
CG-AL-H013hard1100.0 / 1009/9OK19.8s607 / 453
CG-AL-H014hard20.0 / 1000/0FAIL11.5s2.3k / 1.4k
CG-AL-H015hard1100.0 / 1004/4OK19.9s663 / 449
CG-AL-H016hard1100.0 / 1004/4OK27.3s703 / 436
CG-AL-H017hard20.0 / 1000/0FAIL9.0s1.6k / 708
CG-AL-H018hard1100.0 / 1006/6OK24.6s732 / 1.0k
CG-AL-H019hard2100.0 / 1005/5OK26.1s1.4k / 473
CG-AL-H020hard2100.0 / 10010/10OK25.0s2.9k / 2.2k
CG-AL-H021hard2100.0 / 10020/20OK26.9s30k / 2.2k
CG-AL-H022hard1100.0 / 10021/21OK30.2s1.2k / 1.5k
CG-AL-H023hard20.0 / 1000/0FAIL2m 28s22k / 22k
CG-AL-H024hard1100.0 / 1009/9OK44.8s852 / 1.3k
CG-AL-H025hard1100.0 / 1007/7OK1m 33s575 / 302
CG-AL-H026hard1100.0 / 1008/8OK1m 26s750 / 473
CG-AL-H027hard20.0 / 1000/0FAIL11.2s3.4k / 729
CG-AL-H028hard1100.0 / 1009/9OK26.1s1.1k / 1.2k
CG-AL-H029hard20.0 / 1000/0FAIL19.8s4.5k / 3.2k
CG-AL-H030hard2100.0 / 10010/10OK29.6s4.3k / 3.0k
CG-AL-H031hard1100.0 / 10022/22OK34.1s1.6k / 1.8k
CG-AL-H032hard1100.0 / 10019/19OK28.2s1.3k / 1.4k
CG-AL-H033hard1100.0 / 1005/5OK2m 59s1.2k / 2.5k
CG-AL-H034hard2100.0 / 1003/3OK16.8s2.1k / 465
CG-AL-H035hard1100.0 / 1003/3OK20.9s500 / 204
CG-AL-H036hard20.0 / 1000/0FAIL12.4s1.6k / 506
CG-AL-H037hard1100.0 / 1003/3OK19.4s810 / 298
CG-AL-H038hard1100.0 / 1003/3OK18.8s892 / 346
CG-AL-H039hard1100.0 / 1004/4OK19.3s778 / 345
CG-AL-H040hard1100.0 / 1002/2OK24.0s650 / 252
CG-AL-H041hard1100.0 / 1003/3OK21.4s928 / 644
CG-AL-H042hard1100.0 / 1003/3OK17.3s663 / 183
CG-AL-H043hard1100.0 / 1005/5OK18.9s655 / 150
CG-AL-H050hard2100.0 / 1003/3OK19.2s2.3k / 692
CG-AL-H051hard1100.0 / 1004/4OK17.3s994 / 196
CG-AL-H052hard1100.0 / 1005/5OK19.4s1.1k / 157
CG-AL-H053hard1100.0 / 1004/4OK18.5s852 / 341
CG-AL-H054hard20.0 / 1000/0FAIL10.9s3.0k / 1.2k
CG-AL-H056hard20.0 / 1000/0FAIL7.9s2.4k / 454
CG-AL-H057hard1100.0 / 1004/4OK2m 32s1.1k / 411
CG-AL-H058hard1100.0 / 1005/5OK20.0s934 / 459
CG-AL-H205hard1100.0 / 1006/6OK21.0s784 / 664
CG-AL-M001medium20.0 / 1000/0FAIL11.8s2.3k / 1.3k
CG-AL-M002medium1100.0 / 10022/22OK22.8s730 / 842
CG-AL-M003medium1100.0 / 1009/9OK28.1s692 / 1.1k
CG-AL-M004medium1100.0 / 10012/12OK2m 51s778 / 1.5k
CG-AL-M005medium1100.0 / 10022/22OK44.0s948 / 3.0k
CG-AL-M006medium1100.0 / 10018/18OK48.7s710 / 1.9k
CG-AL-M007medium2100.0 / 10015/15OK1m 48s3.7k / 5.3k
CG-AL-M008medium20.0 / 1000/0FAIL1m 41s5.6k / 7.4k
CG-AL-M009medium1100.0 / 10011/11OK2m 41s751 / 2.3k
CG-AL-M010medium1100.0 / 10021/21OK3m 28s963 / 3.0k
CG-AL-M020medium2100.0 / 10017/17OK27.5s3.0k / 2.1k
CG-AL-M021medium1100.0 / 10011/11OK26.4s913 / 793
CG-AL-M022medium1100.0 / 1009/9OK25.2s815 / 1.1k
CG-AL-M023medium262.5 / 10010/11OK21.3s2.3k / 1.4k
CG-AL-M024medium1100.0 / 10010/10OK26.5s762 / 1.4k
CG-AL-M025medium1100.0 / 1007/7OK20.0s660 / 530
CG-AL-M026medium20.0 / 1000/0FAIL11.7s2.4k / 1.7k
CG-AL-M027medium2100.0 / 10018/18OK30.2s6.0k / 3.7k
CG-AL-M028medium262.5 / 1000/0OK7m 55s1.7k / 902
CG-AL-M029medium2100.0 / 1003/3OK2m 27s1.4k / 318
CG-AL-M031medium20.0 / 1000/0FAIL17.1s3.0k / 2.4k
CG-AL-M032medium1100.0 / 1003/3OK21.1s798 / 320
CG-AL-M033medium1100.0 / 1002/2OK18.6s740 / 369
CG-AL-M034medium262.5 / 1001/2OK19.4s2.6k / 777
CG-AL-M035medium1100.0 / 1002/2OK16.5s549 / 147
CG-AL-M036medium1100.0 / 1002/2OK21.1s915 / 517
CG-AL-M037medium20.0 / 1000/0FAIL10.3s2.1k / 712
CG-AL-M038medium1100.0 / 1002/2OK17.5s643 / 262
CG-AL-M039medium1100.0 / 1002/2OK2m 50s715 / 499
CG-AL-M040medium20.0 / 1000/0FAIL10.8s1.3k / 469
CG-AL-M041medium1100.0 / 1003/3OK17.6s506 / 159
CG-AL-M042medium1100.0 / 1008/8OK20.2s758 / 424
CG-AL-M043medium1100.0 / 1005/5OK19.9s682 / 408
CG-AL-M044medium1100.0 / 1006/6OK2m 34s990 / 846
CG-AL-M045medium1100.0 / 1006/6OK18.7s1.0k / 248
CG-AL-M088medium1100.0 / 1006/6OK21.4s678 / 643
CG-AL-M112medium1100.0 / 1004/4OK24.9s913 / 1.1k