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.

60.9% 67/110 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.

45.0 / 100
Cost $0.80
Tokens 169k / 126k input / output, all attempts
Duration 1h 12m
Filter:
Per-task results for run beb015b1-d92e-4ce8-ba58-5d8f83fba190
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK15.5s272 / 239
CG-AL-E002easy1100.0 / 1006/6OK2m 35s285 / 302
CG-AL-E003easy1100.0 / 1005/5OK19.2s273 / 120
CG-AL-E004easy1100.0 / 1006/6OK24.3s300 / 336
CG-AL-E005easy20.0 / 1000/0FAIL29.8s1.4k / 992
CG-AL-E006easy2100.0 / 1007/7OK2m 42s1.1k / 896
CG-AL-E007easy2100.0 / 1007/7OK32.4s1.1k / 397
CG-AL-E008easy1100.0 / 1006/6OK41.8s291 / 304
CG-AL-E009easy1100.0 / 1005/5OK43.7s285 / 164
CG-AL-E010easy1100.0 / 1005/5OK48.7s296 / 116
CG-AL-E031easy1100.0 / 1003/3OK50.9s428 / 401
CG-AL-E032easy1100.0 / 1001/1OK48.4s239 / 55
CG-AL-E045easy1100.0 / 1004/4OK14.9s385 / 338
CG-AL-E050easy20.0 / 1000/0FAIL8.2s2.2k / 451
CG-AL-E051easy262.5 / 1003/15OK19.1s6.1k / 2.0k
CG-AL-E052easy2100.0 / 10016/16OK15.6s1.7k / 570
CG-AL-E053easy2100.0 / 1003/3OK2m 18s831 / 303
CG-AL-E054easy20.0 / 1000/0FAIL6.3s1.2k / 490
CG-AL-E055easy1100.0 / 1008/8OK14.8s385 / 218
CG-AL-E056easy20.0 / 1000/0FAIL7.5s1.9k / 682
CG-AL-E057easy20.0 / 1000/0FAIL6.6s1.8k / 777
CG-AL-E058easy2100.0 / 1001/1OK14.4s988 / 231
CG-AL-H001hard1100.0 / 10025/25OK17.8s491 / 447
CG-AL-H002hard1100.0 / 1004/4OK15.7s496 / 570
CG-AL-H003hard1100.0 / 1005/5OK16.6s524 / 657
CG-AL-H004hard1100.0 / 10014/14OK16.3s535 / 437
CG-AL-H005hard2100.0 / 1006/6OK16.8s2.3k / 1.3k
CG-AL-H006hard1100.0 / 1006/6OK14.7s454 / 247
CG-AL-H007hard2100.0 / 10010/10OK15.6s2.0k / 1.3k
CG-AL-H008hard20.0 / 1000/0FAIL9.0s2.2k / 1.8k
CG-AL-H009hard1100.0 / 10011/11OK16.7s688 / 811
CG-AL-H010hard1100.0 / 1008/8OK15.2s561 / 406
CG-AL-H011hard20.0 / 1000/0FAIL5.9s1.4k / 428
CG-AL-H013hard1100.0 / 1009/9OK14.9s392 / 339
CG-AL-H014hard20.0 / 1000/0FAIL7.5s1.6k / 916
CG-AL-H015hard1100.0 / 1004/4OK14.6s443 / 312
CG-AL-H016hard20.0 / 1000/0FAIL7.2s1.3k / 632
CG-AL-H017hard20.0 / 1000/0FAIL6.2s1.3k / 616
CG-AL-H018hard2100.0 / 1006/6OK15.9s1.7k / 1.0k
CG-AL-H019hard2100.0 / 1005/5OK14.2s958 / 343
CG-AL-H020hard2100.0 / 10010/10OK17.7s2.4k / 1.6k
CG-AL-H021hard20.0 / 1000/0FAIL13.1s3.0k / 1.7k
CG-AL-H022hard262.5 / 10017/21OK17.6s2.7k / 1.9k
CG-AL-H023hard20.0 / 1000/0FAIL1m 32s17k / 23k
CG-AL-H024hard1100.0 / 1009/9OK18.6s573 / 1.0k
CG-AL-H025hard1100.0 / 1007/7OK35.4s388 / 272
CG-AL-H026hard1100.0 / 1008/8OK14.7s509 / 364
CG-AL-H027hard262.5 / 1002/4OK15.7s2.6k / 624
CG-AL-H028hard1100.0 / 1009/9OK16.6s692 / 573
CG-AL-H029hard262.5 / 10016/18OK19.6s3.4k / 2.4k
CG-AL-H030hard262.5 / 1009/10OK16.4s2.3k / 1.4k
CG-AL-H031hard20.0 / 1000/0FAIL14.7s3.3k / 2.3k
CG-AL-H032hard2100.0 / 10019/19OK19.8s2.8k / 2.0k
CG-AL-H033hard1100.0 / 1005/5OK2m 25s823 / 1.5k
CG-AL-H034hard2100.0 / 1003/3OK13.6s1.5k / 338
CG-AL-H035hard1100.0 / 1003/3OK15.3s317 / 102
CG-AL-H036hard20.0 / 1000/0FAIL6.7s1.3k / 327
CG-AL-H037hard20.0 / 1000/0FAIL6.5s1.6k / 402
CG-AL-H038hard20.0 / 1000/0FAIL7.3s1.7k / 605
CG-AL-H039hard1100.0 / 1004/4OK14.7s524 / 273
CG-AL-H040hard1100.0 / 1002/2OK14.2s430 / 174
CG-AL-H041hard20.0 / 1000/0FAIL9.6s2.1k / 1.2k
CG-AL-H042hard20.0 / 1000/0FAIL6.0s1.1k / 301
CG-AL-H043hard1100.0 / 1005/5OK15.6s430 / 99
CG-AL-H050hard262.5 / 1002/3OK17.4s1.6k / 563
CG-AL-H051hard1100.0 / 1004/4OK14.5s695 / 208
CG-AL-H052hard1100.0 / 1005/5OK17.0s784 / 219
CG-AL-H053hard2100.0 / 1004/4OK17.6s1.5k / 533
CG-AL-H054hard2100.0 / 1005/5OK19.2s2.7k / 1.9k
CG-AL-H056hard20.0 / 1000/0FAIL6.1s1.7k / 330
CG-AL-H057hard1100.0 / 1004/4OK2m 26s776 / 392
CG-AL-H058hard1100.0 / 1005/5OK14.6s644 / 325
CG-AL-H205hard2100.0 / 1006/6OK1m 19s1.9k / 1.1k
CG-AL-M001medium20.0 / 1000/0FAIL7.4s1.9k / 1.1k
CG-AL-M002medium262.5 / 10021/22OK18.7s4.0k / 2.0k
CG-AL-M003medium20.0 / 1000/0FAIL8.9s1.9k / 1.7k
CG-AL-M004medium1100.0 / 10012/12OK2m 38s496 / 1.1k
CG-AL-M005medium20.0 / 1000/0FAIL15.7s2.5k / 4.3k
CG-AL-M006medium1100.0 / 10018/18OK20.4s445 / 1.1k
CG-AL-M007medium20.0 / 1000/0FAIL16.7s2.4k / 4.9k
CG-AL-M008medium20.0 / 1000/0FAIL1m 25s2.9k / 6.0k
CG-AL-M009medium1100.0 / 10011/11OK31.0s475 / 3.4k
CG-AL-M010medium2100.0 / 10021/21OK3m 15s2.6k / 4.0k
CG-AL-M020medium20.0 / 1000/0FAIL7.9s2.2k / 1.3k
CG-AL-M021medium20.0 / 1000/0FAIL10.8s2.1k / 1.1k
CG-AL-M022medium2100.0 / 1009/9OK17.4s1.9k / 1.5k
CG-AL-M023medium262.5 / 10010/11OK16.3s1.9k / 1.1k
CG-AL-M024medium2100.0 / 10010/10OK19.6s2.5k / 2.5k
CG-AL-M025medium262.5 / 1002/7OK15.1s1.4k / 773
CG-AL-M026medium1100.0 / 1008/8OK15.7s426 / 347
CG-AL-M027medium20.0 / 1000/0FAIL21.7s3.9k / 3.7k
CG-AL-M028medium2100.0 / 1003/3OK2m 25s1.2k / 610
CG-AL-M029medium2100.0 / 1003/3OK2m 18s999 / 220
CG-AL-M031medium20.0 / 1000/0FAIL8.3s2.1k / 1.6k
CG-AL-M032medium2100.0 / 1003/3OK15.5s1.9k / 429
CG-AL-M033medium2100.0 / 1002/2OK14.6s1.3k / 537
CG-AL-M034medium262.5 / 1000/2OK13.7s1.5k / 470
CG-AL-M035medium1100.0 / 1002/2OK14.2s358 / 107
CG-AL-M036medium20.0 / 1000/0FAIL10.8s1.7k / 633
CG-AL-M037medium20.0 / 1000/0FAIL6.2s1.5k / 508
CG-AL-M038medium1100.0 / 1002/2OK16.5s433 / 186
CG-AL-M039medium1100.0 / 1002/2OK2m 50s502 / 369
CG-AL-M040medium20.0 / 1000/0FAIL6.0s908 / 361
CG-AL-M041medium20.0 / 1000/0FAIL5.7s845 / 244
CG-AL-M042medium2100.0 / 1008/8OK21.9s3.0k / 1.4k
CG-AL-M043medium262.5 / 1000/5OK14.9s1.4k / 542
CG-AL-M044medium1100.0 / 1006/6OK2m 29s719 / 650
CG-AL-M045medium2100.0 / 1006/6OK14.9s2.2k / 378
CG-AL-M088medium1100.0 / 1006/6OK18.5s451 / 429
CG-AL-M112medium2100.0 / 1004/4OK16.5s2.2k / 1.5k