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.

68.8 / 100
Cost $4.29
Tokens 133k / 145k input / output, all attempts
Duration 1h 34m
Filter:
Per-task results for run 7a0dcd0a-b8a1-410d-be90-d1c4995c1660
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy2100.0 / 1007/7OK54.2s927 / 571
CG-AL-E002easy1100.0 / 1006/6OK2m 41s285 / 297
CG-AL-E003easy1100.0 / 1005/5OK27.1s273 / 129
CG-AL-E004easy1100.0 / 1006/6OK29.6s300 / 247
CG-AL-E005easy1100.0 / 10013/13OK37.4s315 / 595
CG-AL-E006easy1100.0 / 1007/7OK3m 5s301 / 422
CG-AL-E007easy1100.0 / 1007/7OK49.2s371 / 165
CG-AL-E008easy1100.0 / 1006/6OK52.9s291 / 346
CG-AL-E009easy1100.0 / 1005/5OK57.4s285 / 224
CG-AL-E010easy1100.0 / 1005/5OK1m 0s296 / 132
CG-AL-E031easy1100.0 / 1003/3OK1m 0s428 / 404
CG-AL-E032easy1100.0 / 1001/1OK59.5s239 / 56
CG-AL-E045easy1100.0 / 1004/4OK19.4s385 / 337
CG-AL-E050easy2100.0 / 10013/13OK22.0s1.7k / 670
CG-AL-E051easy1100.0 / 10015/15OK25.0s520 / 801
CG-AL-E052easy2100.0 / 10016/16OK20.9s1.6k / 493
CG-AL-E053easy1100.0 / 1003/3OK2m 35s312 / 166
CG-AL-E054easy1100.0 / 1009/9OK17.7s426 / 315
CG-AL-E055easy1100.0 / 1008/8OK19.1s385 / 216
CG-AL-E056easy262.5 / 10013/15OK18.4s2.0k / 725
CG-AL-E057easy20.0 / 1000/0FAIL9.4s1.5k / 774
CG-AL-E058easy1100.0 / 1001/1OK17.1s414 / 117
CG-AL-H001hard1100.0 / 10025/25OK20.6s491 / 394
CG-AL-H002hard1100.0 / 1004/4OK20.5s496 / 579
CG-AL-H003hard1100.0 / 1005/5OK22.1s524 / 673
CG-AL-H004hard1100.0 / 10014/14OK19.7s535 / 495
CG-AL-H005hard1100.0 / 1006/6OK24.1s802 / 690
CG-AL-H006hard1100.0 / 1006/6OK19.7s454 / 243
CG-AL-H007hard1100.0 / 10010/10OK23.0s625 / 689
CG-AL-H008hard1100.0 / 10010/10OK19.8s588 / 423
CG-AL-H009hard1100.0 / 10011/11OK24.3s688 / 876
CG-AL-H010hard1100.0 / 1008/8OK20.0s561 / 407
CG-AL-H011hard20.0 / 1000/0FAIL7.9s1.1k / 399
CG-AL-H013hard1100.0 / 1009/9OK19.0s392 / 322
CG-AL-H014hard2100.0 / 1007/7OK21.7s1.8k / 1.3k
CG-AL-H015hard1100.0 / 1004/4OK18.5s443 / 325
CG-AL-H016hard1100.0 / 1004/4OK26.3s446 / 313
CG-AL-H017hard2100.0 / 1003/3OK18.0s1.1k / 566
CG-AL-H018hard1100.0 / 1006/6OK21.9s462 / 537
CG-AL-H019hard1100.0 / 1005/5OK18.1s349 / 169
CG-AL-H020hard2100.0 / 10010/10OK24.2s2.4k / 1.6k
CG-AL-H021hard20.0 / 1000/0FAIL11.6s2.6k / 1.5k
CG-AL-H022hard1100.0 / 10021/21OK25.3s826 / 1.0k
CG-AL-H023hard20.0 / 1000/0FAIL2m 50s15k / 22k
CG-AL-H024hard1100.0 / 1009/9OK31.8s573 / 937
CG-AL-H025hard1100.0 / 1007/7OK1m 29s388 / 223
CG-AL-H026hard1100.0 / 1008/8OK1m 19s509 / 367
CG-AL-H027hard1100.0 / 1004/4OK18.5s827 / 227
CG-AL-H028hard2100.0 / 1009/9OK24.2s2.7k / 1.9k
CG-AL-H029hard262.5 / 10016/18OK26.7s3.1k / 2.4k
CG-AL-H030hard1100.0 / 10010/10OK28.4s747 / 722
CG-AL-H031hard1100.0 / 10022/22OK26.7s1.1k / 1.2k
CG-AL-H032hard1100.0 / 10019/19OK27.4s824 / 1.1k
CG-AL-H033hard1100.0 / 1005/5OK2m 52s823 / 1.7k
CG-AL-H034hard2100.0 / 1003/3OK17.3s1.5k / 828
CG-AL-H035hard1100.0 / 1003/3OK17.0s317 / 102
CG-AL-H036hard1100.0 / 1005/5OK18.5s419 / 221
CG-AL-H037hard1100.0 / 1003/3OK20.4s546 / 424
CG-AL-H038hard1100.0 / 1003/3OK20.7s610 / 241
CG-AL-H039hard1100.0 / 1004/4OK20.5s524 / 390
CG-AL-H040hard1100.0 / 1002/2OK23.5s430 / 184
CG-AL-H041hard1100.0 / 1003/3OK22.2s662 / 549
CG-AL-H042hard1100.0 / 1003/3OK17.9s434 / 155
CG-AL-H043hard1100.0 / 1005/5OK16.6s430 / 98
CG-AL-H050hard262.5 / 1002/3OK22.2s1.4k / 1.6k
CG-AL-H051hard1100.0 / 1004/4OK17.6s695 / 137
CG-AL-H052hard1100.0 / 1005/5OK18.5s784 / 120
CG-AL-H053hard1100.0 / 1004/4OK18.8s598 / 256
CG-AL-H054hard2100.0 / 1005/5OK20.6s2.5k / 1.4k
CG-AL-H056hard20.0 / 1000/0FAIL15.1s1.7k / 878
CG-AL-H057hard1100.0 / 1004/4OK2m 32s776 / 375
CG-AL-H058hard1100.0 / 1005/5OK18.9s644 / 326
CG-AL-H205hard1100.0 / 1006/6OK22.4s535 / 477
CG-AL-M001medium20.0 / 1000/0FAIL9.6s1.6k / 961
CG-AL-M002medium1100.0 / 10022/22OK20.9s471 / 506
CG-AL-M003medium2100.0 / 1009/9OK22.2s1.8k / 1.7k
CG-AL-M004medium1100.0 / 10012/12OK2m 48s496 / 1.3k
CG-AL-M005medium262.5 / 10017/22OK52.6s2.4k / 5.6k
CG-AL-M006medium2100.0 / 10018/18OK27.9s2.1k / 3.0k
CG-AL-M007medium20.0 / 1000/0FAIL1m 34s2.9k / 8.0k
CG-AL-M008medium20.0 / 1000/0FAIL3m 2s12k / 26k
CG-AL-M009medium20.0 / 1000/0FAIL1m 28s7.0k / 14k
CG-AL-M010medium1100.0 / 10021/21OK3m 4s661 / 3.0k
CG-AL-M020medium2100.0 / 10017/17OK21.5s2.2k / 1.6k
CG-AL-M021medium1100.0 / 10011/11OK21.1s595 / 605
CG-AL-M022medium1100.0 / 1009/9OK23.2s554 / 664
CG-AL-M023medium262.5 / 10010/11OK21.8s1.9k / 1.1k
CG-AL-M024medium1100.0 / 10010/10OK26.6s518 / 1.2k
CG-AL-M025medium1100.0 / 1007/7OK18.0s457 / 365
CG-AL-M026medium1100.0 / 1008/8OK20.4s426 / 421
CG-AL-M027medium2100.0 / 10018/18OK26.3s3.9k / 3.0k
CG-AL-M028medium2100.0 / 1003/3OK2m 30s1.2k / 649
CG-AL-M029medium2100.0 / 1003/3OK2m 26s1.0k / 224
CG-AL-M031medium20.0 / 1000/0FAIL14.7s3.3k / 2.0k
CG-AL-M032medium1100.0 / 1003/3OK23.8s549 / 240
CG-AL-M033medium1100.0 / 1002/2OK18.5s492 / 285
CG-AL-M034medium262.5 / 1001/2OK18.8s1.9k / 610
CG-AL-M035medium1100.0 / 1002/2OK16.8s358 / 98
CG-AL-M036medium20.0 / 1000/0FAIL9.4s1.8k / 716
CG-AL-M037medium20.0 / 1000/0FAIL9.9s1.5k / 506
CG-AL-M038medium1100.0 / 1002/2OK17.4s433 / 180
CG-AL-M039medium1100.0 / 1002/2OK2m 33s502 / 466
CG-AL-M040medium20.0 / 1000/0FAIL7.9s881 / 313
CG-AL-M041medium1100.0 / 1003/3OK16.4s345 / 119
CG-AL-M042medium1100.0 / 1008/8OK19.4s538 / 291
CG-AL-M043medium1100.0 / 1005/5OK19.5s483 / 405
CG-AL-M044medium1100.0 / 1006/6OK2m 33s719 / 677
CG-AL-M045medium1100.0 / 1006/6OK16.8s776 / 176
CG-AL-M088medium1100.0 / 1006/6OK20.1s451 / 467
CG-AL-M112medium1100.0 / 1004/4OK23.3s620 / 736