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.

87.3% 96/110 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.

72.3 / 100
Cost $3.87
Tokens 124k / 130k input / output, all attempts
Duration 1h 56m
Filter:
Per-task results for run c611fa66-e0e0-4274-9f5e-a7f1f9704262
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy2100.0 / 1007/7OK1m 0s929 / 571
CG-AL-E002easy1100.0 / 1006/6OK2m 47s285 / 297
CG-AL-E003easy1100.0 / 1005/5OK26.3s273 / 129
CG-AL-E004easy1100.0 / 1006/6OK30.0s300 / 247
CG-AL-E005easy1100.0 / 10013/13OK37.6s315 / 586
CG-AL-E006easy1100.0 / 1007/7OK2m 56s301 / 422
CG-AL-E007easy2100.0 / 1007/7OK19.6s879 / 360
CG-AL-E008easy1100.0 / 1006/6OK51.8s291 / 350
CG-AL-E009easy1100.0 / 1005/5OK57.1s285 / 224
CG-AL-E010easy2100.0 / 1005/5OK18.9s696 / 250
CG-AL-E031easy1100.0 / 1003/3OK1m 0s428 / 404
CG-AL-E032easy1100.0 / 1001/1OK58.8s239 / 56
CG-AL-E045easy1100.0 / 1004/4OK19.8s385 / 328
CG-AL-E050easy1100.0 / 10013/13OK24.9s415 / 770
CG-AL-E051easy1100.0 / 10015/15OK25.7s520 / 812
CG-AL-E052easy2100.0 / 10016/16OK18.1s1.6k / 523
CG-AL-E053easy1100.0 / 1003/3OK2m 28s312 / 166
CG-AL-E054easy1100.0 / 1009/9OK19.7s426 / 316
CG-AL-E055easy1100.0 / 1008/8OK17.9s385 / 216
CG-AL-E056easy262.5 / 10013/15OK17.7s2.0k / 725
CG-AL-E057easy20.0 / 1000/0FAIL10.7s1.5k / 774
CG-AL-E058easy1100.0 / 1001/1OK16.4s414 / 117
CG-AL-H001hard1100.0 / 10025/25OK19.8s491 / 394
CG-AL-H002hard1100.0 / 1004/4OK20.8s496 / 579
CG-AL-H003hard1100.0 / 1005/5OK21.7s524 / 673
CG-AL-H004hard1100.0 / 10014/14OK20.1s535 / 450
CG-AL-H005hard1100.0 / 1006/6OK23.2s802 / 690
CG-AL-H006hard1100.0 / 1006/6OK18.4s454 / 243
CG-AL-H007hard1100.0 / 10010/10OK22.2s625 / 689
CG-AL-H008hard1100.0 / 10010/10OK26.7s588 / 423
CG-AL-H009hard1100.0 / 10011/11OK23.4s688 / 813
CG-AL-H010hard1100.0 / 1008/8OK19.5s561 / 407
CG-AL-H011hard20.0 / 1000/0FAIL7.7s1.1k / 401
CG-AL-H013hard1100.0 / 1009/9OK19.8s392 / 323
CG-AL-H014hard2100.0 / 1007/7OK19.8s1.8k / 1.3k
CG-AL-H015hard1100.0 / 1004/4OK17.6s443 / 325
CG-AL-H016hard1100.0 / 1004/4OK18.8s446 / 313
CG-AL-H017hard2100.0 / 1003/3OK17.1s1.1k / 581
CG-AL-H018hard1100.0 / 1006/6OK21.2s462 / 537
CG-AL-H019hard1100.0 / 1005/5OK17.2s349 / 169
CG-AL-H020hard2100.0 / 10010/10OK21.1s2.4k / 1.6k
CG-AL-H021hard20.0 / 1000/0FAIL11.9s2.6k / 1.5k
CG-AL-H022hard1100.0 / 10021/21OK29.5s826 / 1.1k
CG-AL-H023hard20.0 / 1000/0FAIL2m 45s16k / 22k
CG-AL-H024hard1100.0 / 1009/9OK2m 5s573 / 937
CG-AL-H025hard1100.0 / 1007/7OK19.0s388 / 223
CG-AL-H026hard1100.0 / 1008/8OK20.6s509 / 367
CG-AL-H027hard1100.0 / 1004/4OK20.7s827 / 227
CG-AL-H028hard2100.0 / 1009/9OK22.8s2.7k / 1.9k
CG-AL-H029hard20.0 / 1000/0FAIL16.6s3.1k / 2.5k
CG-AL-H030hard1100.0 / 10010/10OK23.4s747 / 732
CG-AL-H031hard1100.0 / 10022/22OK27.6s1.1k / 1.2k
CG-AL-H032hard1100.0 / 10019/19OK28.3s824 / 1.1k
CG-AL-H033hard1100.0 / 1005/5OK2m 52s823 / 1.7k
CG-AL-H034hard2100.0 / 1003/3OK16.9s1.5k / 1.3k
CG-AL-H035hard1100.0 / 1003/3OK18.6s317 / 102
CG-AL-H036hard1100.0 / 1005/5OK18.6s419 / 221
CG-AL-H037hard1100.0 / 1003/3OK20.9s546 / 413
CG-AL-H038hard1100.0 / 1003/3OK18.9s610 / 241
CG-AL-H039hard1100.0 / 1004/4OK21.6s524 / 390
CG-AL-H040hard1100.0 / 1002/2OK18.0s430 / 184
CG-AL-H041hard1100.0 / 1003/3OK20.5s662 / 414
CG-AL-H042hard1100.0 / 1003/3OK17.7s434 / 155
CG-AL-H043hard1100.0 / 1005/5OK16.4s430 / 98
CG-AL-H050hard262.5 / 1002/3OK28.1s1.6k / 1.4k
CG-AL-H051hard1100.0 / 1004/4OK18.9s695 / 137
CG-AL-H052hard1100.0 / 1005/5OK19.6s784 / 119
CG-AL-H053hard1100.0 / 1004/4OK18.6s598 / 256
CG-AL-H054hard2100.0 / 1005/5OK21.2s2.5k / 1.4k
CG-AL-H056hard2100.0 / 1004/4OK17.2s1.7k / 353
CG-AL-H057hard1100.0 / 1004/4OK2m 35s776 / 360
CG-AL-H058hard1100.0 / 1005/5OK18.8s644 / 325
CG-AL-H205hard1100.0 / 1006/6OK21.3s535 / 477
CG-AL-M001medium20.0 / 1000/0FAIL9.5s1.6k / 959
CG-AL-M002medium1100.0 / 10022/22OK27.2s471 / 506
CG-AL-M003medium2100.0 / 1009/9OK27.1s1.8k / 1.7k
CG-AL-M004medium1100.0 / 10012/12OK2m 51s496 / 1.3k
CG-AL-M005medium2100.0 / 10022/22OK43.6s2.4k / 5.1k
CG-AL-M006medium1100.0 / 10018/18OK38.2s445 / 1.8k
CG-AL-M007medium2100.0 / 10015/15OK1m 36s2.6k / 7.1k
CG-AL-M008medium2100.0 / 10012/12OK2m 30s8.6k / 17k
CG-AL-M009medium2100.0 / 10011/11OK1m 59s3.2k / 10k
CG-AL-M010medium1100.0 / 10021/21OK5m 0s661 / 3.0k
CG-AL-M020medium2100.0 / 10017/17OK41.6s2.2k / 1.6k
CG-AL-M021medium1100.0 / 10011/11OK49.2s595 / 555
CG-AL-M022medium1100.0 / 1009/9OK22.9s554 / 664
CG-AL-M023medium262.5 / 10010/11OK26.5s1.9k / 1.1k
CG-AL-M024medium1100.0 / 10010/10OK27.1s518 / 1.2k
CG-AL-M025medium1100.0 / 1007/7OK21.4s457 / 386
CG-AL-M026medium1100.0 / 1008/8OK21.2s426 / 408
CG-AL-M027medium2100.0 / 10018/18OK26.3s3.9k / 3.0k
CG-AL-M028medium2100.0 / 1003/3OK2m 40s1.2k / 649
CG-AL-M029medium2100.0 / 1003/3OK2m 29s999 / 233
CG-AL-M031medium20.0 / 1000/0FAIL14.7s3.3k / 1.9k
CG-AL-M032medium1100.0 / 1003/3OK18.5s549 / 240
CG-AL-M033medium1100.0 / 1002/2OK19.0s492 / 285
CG-AL-M034medium262.5 / 1001/2OK19.2s1.9k / 618
CG-AL-M035medium1100.0 / 1002/2OK17.6s358 / 98
CG-AL-M036medium20.0 / 1000/0FAIL9.7s1.8k / 705
CG-AL-M037medium20.0 / 1000/0FAIL8.2s1.5k / 506
CG-AL-M038medium1100.0 / 1002/2OK18.9s433 / 180
CG-AL-M039medium1100.0 / 1002/2OK2m 36s502 / 458
CG-AL-M040medium20.0 / 1000/0FAIL7.7s884 / 313
CG-AL-M041medium1100.0 / 1003/3OK18.2s345 / 119
CG-AL-M042medium1100.0 / 1008/8OK18.3s538 / 291
CG-AL-M043medium1100.0 / 1005/5OK19.6s483 / 382
CG-AL-M044medium1100.0 / 1006/6OK2m 38s719 / 678
CG-AL-M045medium1100.0 / 1006/6OK17.6s776 / 183
CG-AL-M088medium1100.0 / 1006/6OK20.7s451 / 467
CG-AL-M112medium1100.0 / 1004/4OK22.4s620 / 736