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.

82.7% 91/110 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.

71.1 / 100
Cost $3.83
Tokens 183k / 117k input / output, all attempts
Duration 1h 11m
Filter:
Per-task results for run eae41fb1-f1a9-488d-85f9-d31f8bd7c6ea
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.2s418 / 433
CG-AL-E002easy1100.0 / 1006/6OK2m 50s433 / 377
CG-AL-E003easy1100.0 / 1005/5OK20.2s410 / 166
CG-AL-E004easy1100.0 / 1006/6OK25.2s470 / 367
CG-AL-E005easy1100.0 / 10013/13OK31.0s491 / 515
CG-AL-E006easy1100.0 / 1007/7OK2m 46s470 / 596
CG-AL-E007easy1100.0 / 1007/7OK38.1s558 / 242
CG-AL-E008easy1100.0 / 1006/6OK39.8s470 / 467
CG-AL-E009easy1100.0 / 1005/5OK43.3s442 / 239
CG-AL-E010easy1100.0 / 1005/5OK43.3s467 / 188
CG-AL-E031easy1100.0 / 1003/3OK45.6s678 / 659
CG-AL-E032easy1100.0 / 1001/1OK39.8s377 / 88
CG-AL-E045easy1100.0 / 1004/4OK18.5s565 / 605
CG-AL-E050easy1100.0 / 10013/13OK15.8s635 / 349
CG-AL-E051easy1100.0 / 10015/15OK23.4s776 / 1.2k
CG-AL-E052easy2100.0 / 10016/16OK16.2s2.4k / 763
CG-AL-E053easy1100.0 / 1003/3OK2m 28s461 / 176
CG-AL-E054easy2100.0 / 1009/9OK15.5s1.7k / 714
CG-AL-E055easy1100.0 / 1008/8OK16.8s566 / 301
CG-AL-E056easy262.5 / 10013/15OK16.6s3.8k / 992
CG-AL-E057easy20.0 / 1000/0FAIL10.5s2.2k / 1.1k
CG-AL-E058easy1100.0 / 1001/1OK14.0s628 / 168
CG-AL-H001hard1100.0 / 10025/25OK17.0s726 / 428
CG-AL-H002hard1100.0 / 1004/4OK21.9s747 / 765
CG-AL-H003hard1100.0 / 1005/5OK24.3s766 / 945
CG-AL-H004hard1100.0 / 10014/14OK25.9s779 / 572
CG-AL-H005hard1100.0 / 1006/6OK21.0s1.2k / 892
CG-AL-H006hard1100.0 / 1006/6OK15.7s715 / 365
CG-AL-H007hard1100.0 / 10010/10OK21.8s952 / 968
CG-AL-H008hard1100.0 / 10010/10OK17.4s886 / 586
CG-AL-H009hard1100.0 / 10011/11OK22.8s1.0k / 1.3k
CG-AL-H010hard1100.0 / 1008/8OK21.9s901 / 632
CG-AL-H011hard20.0 / 1000/0FAIL8.8s1.8k / 594
CG-AL-H013hard1100.0 / 1009/9OK16.6s607 / 453
CG-AL-H014hard20.0 / 1000/0FAIL11.8s2.4k / 1.5k
CG-AL-H015hard1100.0 / 1004/4OK16.2s663 / 431
CG-AL-H016hard1100.0 / 1004/4OK16.2s703 / 402
CG-AL-H017hard20.0 / 1000/0FAIL8.9s1.6k / 708
CG-AL-H018hard1100.0 / 1006/6OK20.0s732 / 809
CG-AL-H019hard1100.0 / 1005/5OK14.6s533 / 238
CG-AL-H020hard2100.0 / 10010/10OK21.6s2.8k / 2.2k
CG-AL-H021hard2100.0 / 10020/20OK24.4s30k / 2.2k
CG-AL-H022hard1100.0 / 10021/21OK30.0s1.2k / 1.5k
CG-AL-H023hard2100.0 / 10025/25OK1m 6s5.9k / 12k
CG-AL-H024hard1100.0 / 1009/9OK34.8s852 / 1.2k
CG-AL-H025hard1100.0 / 1007/7OK16.1s575 / 453
CG-AL-H026hard1100.0 / 1008/8OK16.7s750 / 471
CG-AL-H027hard2100.0 / 1004/4OK20.1s3.4k / 878
CG-AL-H028hard1100.0 / 1009/9OK18.4s1.1k / 755
CG-AL-H029hard20.0 / 1000/0FAIL21.4s4.6k / 3.6k
CG-AL-H030hard2100.0 / 10010/10OK29.2s4.3k / 3.0k
CG-AL-H031hard1100.0 / 10022/22OK27.8s1.6k / 1.8k
CG-AL-H032hard1100.0 / 10019/19OK28.9s1.3k / 1.4k
CG-AL-H033hard1100.0 / 1005/5OK2m 45s1.2k / 2.3k
CG-AL-H034hard2100.0 / 1003/3OK14.3s2.1k / 465
CG-AL-H035hard1100.0 / 1003/3OK13.7s500 / 162
CG-AL-H036hard2100.0 / 1005/5OK14.6s1.5k / 447
CG-AL-H037hard1100.0 / 1003/3OK15.7s810 / 270
CG-AL-H038hard1100.0 / 1003/3OK15.2s892 / 346
CG-AL-H039hard1100.0 / 1004/4OK15.4s778 / 322
CG-AL-H040hard1100.0 / 1002/2OK15.0s650 / 252
CG-AL-H041hard1100.0 / 1003/3OK18.1s928 / 588
CG-AL-H042hard1100.0 / 1003/3OK14.3s663 / 181
CG-AL-H043hard1100.0 / 1005/5OK15.6s655 / 169
CG-AL-H050hard262.5 / 1002/3OK14.4s2.3k / 607
CG-AL-H051hard1100.0 / 1004/4OK14.4s994 / 196
CG-AL-H052hard1100.0 / 1005/5OK13.6s1.1k / 157
CG-AL-H053hard1100.0 / 1004/4OK15.9s852 / 341
CG-AL-H054hard20.0 / 1000/0FAIL10.8s3.0k / 1.0k
CG-AL-H056hard20.0 / 1000/0FAIL8.3s2.4k / 454
CG-AL-H057hard1100.0 / 1004/4OK2m 27s1.1k / 420
CG-AL-H058hard1100.0 / 1005/5OK16.7s934 / 457
CG-AL-H205hard1100.0 / 1006/6OK17.7s784 / 664
CG-AL-M001medium20.0 / 1000/0FAIL11.9s2.3k / 1.4k
CG-AL-M002medium1100.0 / 10022/22OK20.7s730 / 889
CG-AL-M003medium2100.0 / 1009/9OK22.2s5.2k / 1.9k
CG-AL-M004medium1100.0 / 10012/12OK2m 45s778 / 1.5k
CG-AL-M005medium1100.0 / 10022/22OK42.0s948 / 3.2k
CG-AL-M006medium1100.0 / 10018/18OK31.2s710 / 1.8k
CG-AL-M007medium2100.0 / 10015/15OK33.6s3.7k / 4.3k
CG-AL-M008medium262.5 / 10011/12OK45.5s6.8k / 7.2k
CG-AL-M009medium1100.0 / 10011/11OK39.7s751 / 2.8k
CG-AL-M010medium1100.0 / 10021/21OK3m 9s963 / 2.9k
CG-AL-M020medium262.5 / 10016/17OK26.5s3.0k / 2.1k
CG-AL-M021medium1100.0 / 10011/11OK18.7s913 / 781
CG-AL-M022medium1100.0 / 1009/9OK24.3s815 / 1.1k
CG-AL-M023medium262.5 / 10010/11OK22.3s2.7k / 1.5k
CG-AL-M024medium1100.0 / 10010/10OK25.4s762 / 1.4k
CG-AL-M025medium1100.0 / 1007/7OK17.6s660 / 525
CG-AL-M026medium2100.0 / 1008/8OK17.3s2.0k / 1.1k
CG-AL-M027medium2100.0 / 10018/18OK29.0s6.0k / 3.7k
CG-AL-M028medium20.0 / 1000/0FAIL9.8s1.7k / 909
CG-AL-M029medium2100.0 / 1003/3OK2m 22s1.4k / 318
CG-AL-M031medium20.0 / 1000/0FAIL15.4s3.0k / 2.3k
CG-AL-M032medium1100.0 / 1003/3OK14.9s798 / 320
CG-AL-M033medium1100.0 / 1002/2OK16.5s740 / 390
CG-AL-M034medium262.5 / 1000/2OK15.4s2.6k / 596
CG-AL-M035medium1100.0 / 1002/2OK14.2s549 / 159
CG-AL-M036medium20.0 / 1000/0FAIL9.9s2.6k / 1.1k
CG-AL-M037medium20.0 / 1000/0FAIL8.5s2.1k / 712
CG-AL-M038medium1100.0 / 1002/2OK15.1s643 / 268
CG-AL-M039medium1100.0 / 1002/2OK2m 27s715 / 493
CG-AL-M040medium20.0 / 1000/0FAIL7.7s1.3k / 476
CG-AL-M041medium1100.0 / 1003/3OK13.8s506 / 159
CG-AL-M042medium1100.0 / 1008/8OK17.7s758 / 446
CG-AL-M043medium1100.0 / 1005/5OK17.9s682 / 421
CG-AL-M044medium1100.0 / 1006/6OK2m 32s990 / 828
CG-AL-M045medium1100.0 / 1006/6OK14.5s1.0k / 248
CG-AL-M088medium1100.0 / 1006/6OK18.6s678 / 643
CG-AL-M112medium1100.0 / 1004/4OK25.3s913 / 971