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.

78.2% 86/110 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.

60.3 / 100
Cost $14.19
Tokens 129k / 451k input / output, all attempts
Duration 4h 5m
Filter:
Per-task results for run c82c44d5-3561-48ca-b5c0-0b9f41695101
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK22.5s258 / 418
CG-AL-E002easy1100.0 / 1006/6OK2m 50s272 / 609
CG-AL-E003easy1100.0 / 1005/5OK19.3s259 / 254
CG-AL-E004easy1100.0 / 1006/6OK26.7s279 / 709
CG-AL-E005easy1100.0 / 10013/13OK1m 7s293 / 3.4k
CG-AL-E006easy1100.0 / 1007/7OK3m 3s284 / 1.4k
CG-AL-E007easy2100.0 / 1007/7OK23.3s865 / 892
CG-AL-E008easy20.0 / 1000/0FAIL21.9s1.0k / 1.4k
CG-AL-E009easy1100.0 / 1005/5OK56.3s271 / 1.7k
CG-AL-E010easy1100.0 / 1005/5OK37.5s275 / 381
CG-AL-E031easy1100.0 / 1003/3OK38.8s401 / 832
CG-AL-E032easy1100.0 / 1001/1OK30.4s221 / 188
CG-AL-E045easy1100.0 / 1004/4OK25.8s360 / 778
CG-AL-E050easy20.0 / 1000/0FAIL1m 3s2.1k / 8.5k
CG-AL-E051easy1100.0 / 10015/15OK2m 16s910 / 7.6k
CG-AL-E052easy2100.0 / 10016/16OK21.1s1.4k / 1.1k
CG-AL-E053easy1100.0 / 1003/3OK2m 47s293 / 1.2k
CG-AL-E054easy2100.0 / 1009/9OK53.7s993 / 4.2k
CG-AL-E055easy1100.0 / 1008/8OK24.2s332 / 688
CG-AL-E056easy2100.0 / 10015/15OK27.4s1.7k / 1.6k
CG-AL-E057easy2100.0 / 1008/8OK26.3s1.2k / 1.6k
CG-AL-E058easy1100.0 / 1001/1OK54.0s368 / 2.2k
CG-AL-H001hard1100.0 / 10025/25OK24.1s453 / 766
CG-AL-H002hard1100.0 / 1004/4OK22.5s425 / 666
CG-AL-H003hard1100.0 / 1005/5OK27.2s464 / 1.0k
CG-AL-H004hard1100.0 / 10014/14OK41.7s474 / 2.0k
CG-AL-H005hard1100.0 / 1006/6OK27.7s687 / 1.0k
CG-AL-H006hard1100.0 / 1006/6OK25.7s421 / 722
CG-AL-H007hard2100.0 / 10010/10OK25.3s2.7k / 13k
CG-AL-H008hard1100.0 / 10010/10OK27.1s504 / 850
CG-AL-H009hard1100.0 / 10011/11OK34.1s574 / 1.5k
CG-AL-H010hard1100.0 / 1008/8OK23.7s493 / 839
CG-AL-H011hard2100.0 / 1005/5OK31.7s896 / 3.9k
CG-AL-H013hard1100.0 / 1009/9OK24.5s358 / 703
CG-AL-H014hard20.0 / 1000/0FAIL17.0s1.6k / 2.5k
CG-AL-H015hard1100.0 / 1004/4OK28.5s387 / 1.0k
CG-AL-H016hard1100.0 / 1004/4OK30.7s400 / 1.3k
CG-AL-H017hard2100.0 / 1003/3OK24.5s975 / 3.6k
CG-AL-H018hard1100.0 / 1006/6OK1m 12s420 / 3.7k
CG-AL-H019hard1100.0 / 1005/5OK51.4s310 / 2.2k
CG-AL-H020hard2100.0 / 10010/10OK29.4s2.2k / 3.7k
CG-AL-H021hard20.0 / 1000/0FAIL18.8s2.2k / 3.8k
CG-AL-H022hard1100.0 / 10021/21OK51.8s724 / 2.5k
CG-AL-H023hard20.0 / 1000/0FAIL3m 37s7.1k / 24k
CG-AL-H024hard1100.0 / 1009/9OK1m 2s508 / 3.3k
CG-AL-H025hard1100.0 / 1007/7OK25.0s356 / 705
CG-AL-H026hard1100.0 / 1008/8OK34.3s443 / 1.3k
CG-AL-H027hard2100.0 / 1004/4OK25.5s2.1k / 1.3k
CG-AL-H028hard1100.0 / 1009/9OK1m 42s1.2k / 5.7k
CG-AL-H029hard20.0 / 1000/0FAIL2m 15s4.4k / 12k
CG-AL-H030hard2100.0 / 10010/10OK1m 59s4.7k / 18k
CG-AL-H031hard20.0 / 1000/0FAIL2m 23s5.7k / 20k
CG-AL-H032hard1100.0 / 10019/19OK1m 3s732 / 3.5k
CG-AL-H033hard1100.0 / 1005/5OK2m 44s732 / 1.7k
CG-AL-H034hard1100.0 / 1003/3OK34.4s431 / 1.2k
CG-AL-H035hard1100.0 / 1003/3OK21.1s290 / 461
CG-AL-H036hard20.0 / 1000/0FAIL32.8s928 / 3.4k
CG-AL-H037hard20.0 / 1000/0FAIL39.6s1.2k / 3.8k
CG-AL-H038hard1100.0 / 1003/3OK34.2s532 / 1.2k
CG-AL-H039hard1100.0 / 1004/4OK33.5s456 / 1.3k
CG-AL-H040hard1100.0 / 1002/2OK41.5s380 / 1.7k
CG-AL-H041hard1100.0 / 1003/3OK45.4s565 / 1.9k
CG-AL-H042hard1100.0 / 1003/3OK22.8s392 / 609
CG-AL-H043hard1100.0 / 1005/5OK23.2s381 / 608
CG-AL-H050hard2100.0 / 1003/3OK23.9s1.2k / 4.4k
CG-AL-H051hard1100.0 / 1004/4OK23.6s617 / 627
CG-AL-H052hard1100.0 / 1005/5OK28.1s675 / 944
CG-AL-H053hard1100.0 / 1004/4OK25.0s520 / 708
CG-AL-H054hard20.0 / 1000/0FAIL14.4s1.8k / 1.8k
CG-AL-H056hard20.0 / 1000/0FAIL13.5s1.4k / 2.1k
CG-AL-H057hard1100.0 / 1004/4OK2m 39s673 / 786
CG-AL-H058hard1100.0 / 1005/5OK23.7s561 / 769
CG-AL-H205hard1100.0 / 1006/6OK27.9s434 / 865
CG-AL-M001medium20.0 / 1000/0FAIL18.2s2.4k / 12k
CG-AL-M002medium1100.0 / 10022/22OK1m 5s403 / 3.0k
CG-AL-M003medium2100.0 / 1009/9OK29.0s3.4k / 5.2k
CG-AL-M004medium1100.0 / 10012/12OK4m 34s898 / 7.0k
CG-AL-M005medium20.0 / 1000/0FAIL3m 49s3.2k / 24k
CG-AL-M006medium20.0 / 1000/0FAIL3m 38s2.4k / 24k
CG-AL-M007medium20.0 / 1000/0FAIL3m 16s2.5k / 24k
CG-AL-M008medium20.0 / 1000/0FAIL3m 48s2.9k / 24k
CG-AL-M009medium20.0 / 1000/0FAIL2m 29s2.7k / 16k
CG-AL-M010medium20.0 / 1000/0FAIL2m 4s2.9k / 19k
CG-AL-M020medium262.5 / 1000/0OK13m 19s2.4k / 6.2k
CG-AL-M021medium2100.0 / 10011/11OK55.2s1.5k / 4.1k
CG-AL-M022medium2100.0 / 1009/9OK1m 1s1.7k / 11k
CG-AL-M023medium262.5 / 10010/11OK2m 30s2.7k / 8.8k
CG-AL-M024medium2100.0 / 10010/10OK54.9s1.8k / 5.5k
CG-AL-M025medium262.5 / 1002/7OK25.9s1.3k / 4.9k
CG-AL-M026medium1100.0 / 1008/8OK41.5s370 / 2.0k
CG-AL-M027medium2100.0 / 10018/18OK46.0s3.4k / 5.3k
CG-AL-M028medium2100.0 / 1003/3OK2m 33s1.0k / 2.9k
CG-AL-M029medium2100.0 / 1003/3OK2m 30s873 / 2.1k
CG-AL-M031medium2100.0 / 1002/2OK1m 5s2.6k / 7.0k
CG-AL-M032medium1100.0 / 1003/3OK24.5s488 / 688
CG-AL-M033medium1100.0 / 1002/2OK34.8s426 / 1.2k
CG-AL-M034medium262.5 / 1001/2OK1m 10s1.3k / 4.0k
CG-AL-M035medium1100.0 / 1002/2OK18.0s316 / 216
CG-AL-M036medium2100.0 / 1002/2OK31.1s1.5k / 1.8k
CG-AL-M037medium20.0 / 1000/0FAIL23.9s1.3k / 2.0k
CG-AL-M038medium1100.0 / 1002/2OK24.2s381 / 653
CG-AL-M039medium1100.0 / 1002/2OK2m 49s442 / 845
CG-AL-M040medium20.0 / 1000/0FAIL14.7s786 / 1.3k
CG-AL-M041medium1100.0 / 1003/3OK18.1s313 / 287
CG-AL-M042medium1100.0 / 1008/8OK26.4s498 / 738
CG-AL-M043medium2100.0 / 1005/5OK21.8s1.9k / 1.3k
CG-AL-M044medium1100.0 / 1006/6OK2m 52s613 / 983
CG-AL-M045medium1100.0 / 1006/6OK43.4s698 / 1.7k
CG-AL-M088medium1100.0 / 1006/6OK26.3s391 / 872
CG-AL-M112medium1100.0 / 1004/4OK29.6s559 / 989