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.

69.8 / 100
Cost $3.65
Tokens 173k / 112k input / output, all attempts
Duration 1h 9m
Filter:
Per-task results for run 68e1635c-6be8-43aa-93e9-52e908bdf3b9
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK16.9s418 / 433
CG-AL-E002easy1100.0 / 1006/6OK2m 31s433 / 378
CG-AL-E003easy1100.0 / 1005/5OK19.9s410 / 166
CG-AL-E004easy1100.0 / 1006/6OK26.3s470 / 367
CG-AL-E005easy1100.0 / 10013/13OK31.0s491 / 584
CG-AL-E006easy1100.0 / 1007/7OK2m 43s470 / 594
CG-AL-E007easy1100.0 / 1007/7OK36.0s558 / 242
CG-AL-E008easy1100.0 / 1006/6OK40.3s470 / 468
CG-AL-E009easy1100.0 / 1005/5OK43.1s442 / 229
CG-AL-E010easy1100.0 / 1005/5OK44.9s467 / 188
CG-AL-E031easy1100.0 / 1003/3OK45.3s678 / 659
CG-AL-E032easy1100.0 / 1001/1OK40.8s377 / 89
CG-AL-E045easy1100.0 / 1004/4OK19.3s565 / 468
CG-AL-E050easy1100.0 / 10013/13OK17.9s635 / 369
CG-AL-E051easy1100.0 / 10015/15OK23.9s776 / 984
CG-AL-E052easy2100.0 / 10016/16OK16.5s2.4k / 763
CG-AL-E053easy1100.0 / 1003/3OK2m 29s461 / 176
CG-AL-E054easy2100.0 / 1009/9OK19.8s1.7k / 708
CG-AL-E055easy1100.0 / 1008/8OK16.1s566 / 301
CG-AL-E056easy262.5 / 10013/15OK17.7s3.8k / 992
CG-AL-E057easy20.0 / 1000/0FAIL10.9s2.2k / 1.1k
CG-AL-E058easy1100.0 / 1001/1OK14.5s628 / 168
CG-AL-H001hard1100.0 / 10025/25OK16.8s726 / 428
CG-AL-H002hard1100.0 / 1004/4OK19.3s747 / 770
CG-AL-H003hard1100.0 / 1005/5OK21.3s766 / 898
CG-AL-H004hard1100.0 / 10014/14OK19.3s779 / 625
CG-AL-H005hard1100.0 / 1006/6OK21.5s1.2k / 880
CG-AL-H006hard1100.0 / 1006/6OK16.7s715 / 365
CG-AL-H007hard1100.0 / 10010/10OK20.6s952 / 903
CG-AL-H008hard1100.0 / 10010/10OK18.4s886 / 586
CG-AL-H009hard1100.0 / 10011/11OK23.2s1.0k / 1.3k
CG-AL-H010hard1100.0 / 1008/8OK18.7s901 / 632
CG-AL-H011hard20.0 / 1000/0FAIL7.9s1.6k / 563
CG-AL-H013hard1100.0 / 1009/9OK21.3s607 / 464
CG-AL-H014hard20.0 / 1000/0FAIL11.5s2.3k / 1.4k
CG-AL-H015hard1100.0 / 1004/4OK19.2s663 / 431
CG-AL-H016hard1100.0 / 1004/4OK21.7s703 / 402
CG-AL-H017hard20.0 / 1000/0FAIL9.5s1.6k / 708
CG-AL-H018hard1100.0 / 1006/6OK19.9s732 / 764
CG-AL-H019hard2100.0 / 1005/5OK13.6s1.4k / 473
CG-AL-H020hard2100.0 / 10010/10OK21.5s2.8k / 2.0k
CG-AL-H021hard2100.0 / 10020/20OK52.0s30k / 2.1k
CG-AL-H022hard1100.0 / 10021/21OK25.8s1.2k / 1.5k
CG-AL-H023hard2100.0 / 10025/25OK1m 5s5.7k / 12k
CG-AL-H024hard1100.0 / 1009/9OK34.9s852 / 1.2k
CG-AL-H025hard1100.0 / 1007/7OK18.3s575 / 453
CG-AL-H026hard1100.0 / 1008/8OK16.9s750 / 465
CG-AL-H027hard262.5 / 1002/4OK17.6s3.4k / 619
CG-AL-H028hard1100.0 / 1009/9OK21.7s1.1k / 1.0k
CG-AL-H029hard20.0 / 1000/0FAIL20.1s4.5k / 3.2k
CG-AL-H030hard2100.0 / 10010/10OK28.0s4.2k / 2.9k
CG-AL-H031hard1100.0 / 10022/22OK27.6s1.6k / 1.8k
CG-AL-H032hard1100.0 / 10019/19OK25.3s1.3k / 1.4k
CG-AL-H033hard1100.0 / 1005/5OK2m 52s1.2k / 2.3k
CG-AL-H034hard2100.0 / 1003/3OK14.1s2.1k / 465
CG-AL-H035hard1100.0 / 1003/3OK13.6s500 / 162
CG-AL-H036hard2100.0 / 1005/5OK14.0s1.6k / 447
CG-AL-H037hard1100.0 / 1003/3OK14.8s810 / 270
CG-AL-H038hard1100.0 / 1003/3OK15.3s892 / 346
CG-AL-H039hard1100.0 / 1004/4OK15.4s778 / 319
CG-AL-H040hard1100.0 / 1002/2OK15.5s650 / 252
CG-AL-H041hard1100.0 / 1003/3OK18.4s928 / 599
CG-AL-H042hard1100.0 / 1003/3OK15.0s663 / 181
CG-AL-H043hard1100.0 / 1005/5OK15.5s655 / 169
CG-AL-H050hard20.0 / 1000/0FAIL8.9s2.3k / 529
CG-AL-H051hard1100.0 / 1004/4OK13.8s994 / 196
CG-AL-H052hard1100.0 / 1005/5OK14.1s1.1k / 157
CG-AL-H053hard1100.0 / 1004/4OK15.2s852 / 333
CG-AL-H054hard20.0 / 1000/0FAIL10.0s3.0k / 1.0k
CG-AL-H056hard20.0 / 1000/0FAIL7.9s2.4k / 454
CG-AL-H057hard1100.0 / 1004/4OK2m 35s1.1k / 403
CG-AL-H058hard1100.0 / 1005/5OK16.4s934 / 459
CG-AL-H205hard1100.0 / 1006/6OK17.9s784 / 664
CG-AL-M001medium20.0 / 1000/0FAIL11.5s2.3k / 1.3k
CG-AL-M002medium1100.0 / 10022/22OK19.3s730 / 842
CG-AL-M003medium1100.0 / 1009/9OK26.5s692 / 1.0k
CG-AL-M004medium1100.0 / 10012/12OK2m 49s778 / 1.3k
CG-AL-M005medium1100.0 / 10022/22OK40.9s948 / 3.0k
CG-AL-M006medium1100.0 / 10018/18OK30.4s710 / 1.8k
CG-AL-M007medium2100.0 / 10015/15OK35.2s3.9k / 4.8k
CG-AL-M008medium1100.0 / 10012/12OK46.8s907 / 3.6k
CG-AL-M009medium1100.0 / 10011/11OK36.7s751 / 2.5k
CG-AL-M010medium1100.0 / 10021/21OK2m 45s963 / 2.9k
CG-AL-M020medium20.0 / 1000/0FAIL14.7s3.0k / 2.0k
CG-AL-M021medium1100.0 / 10011/11OK19.0s913 / 757
CG-AL-M022medium1100.0 / 1009/9OK22.2s815 / 1.1k
CG-AL-M023medium262.5 / 10010/11OK22.9s2.7k / 1.5k
CG-AL-M024medium1100.0 / 10010/10OK24.6s762 / 1.4k
CG-AL-M025medium1100.0 / 1007/7OK17.4s660 / 502
CG-AL-M026medium2100.0 / 1008/8OK17.7s2.3k / 1.3k
CG-AL-M027medium2100.0 / 10018/18OK29.4s6.0k / 4.2k
CG-AL-M028medium20.0 / 1000/0FAIL9.4s1.7k / 812
CG-AL-M029medium2100.0 / 1003/3OK2m 22s1.4k / 318
CG-AL-M031medium20.0 / 1000/0FAIL15.8s3.0k / 2.3k
CG-AL-M032medium1100.0 / 1003/3OK16.2s798 / 320
CG-AL-M033medium1100.0 / 1002/2OK16.6s740 / 398
CG-AL-M034medium262.5 / 1001/2OK17.8s2.6k / 840
CG-AL-M035medium1100.0 / 1002/2OK14.3s549 / 159
CG-AL-M036medium20.0 / 1000/0FAIL9.6s2.6k / 1.1k
CG-AL-M037medium20.0 / 1000/0FAIL8.1s2.1k / 712
CG-AL-M038medium1100.0 / 1002/2OK14.5s643 / 262
CG-AL-M039medium1100.0 / 1002/2OK2m 35s715 / 491
CG-AL-M040medium20.0 / 1000/0FAIL7.5s1.3k / 476
CG-AL-M041medium1100.0 / 1003/3OK13.2s506 / 159
CG-AL-M042medium1100.0 / 1008/8OK16.6s758 / 413
CG-AL-M043medium1100.0 / 1005/5OK16.5s682 / 426
CG-AL-M044medium1100.0 / 1006/6OK2m 24s990 / 859
CG-AL-M045medium1100.0 / 1006/6OK14.2s1.0k / 248
CG-AL-M088medium1100.0 / 1006/6OK17.6s678 / 623
CG-AL-M112medium1100.0 / 1004/4OK20.7s913 / 971