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.

81.0% 188/232 of 232 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.

72.2 / 100
Cost $0.42
Tokens 636k / 721k input / output, all attempts
Duration 54m 59s
Filter:
Per-task results for run 41523ca6-be01-406d-8590-bcc3144b269f
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK19.5s258 / 346
CG-AL-E006easy2100.0 / 1007/7OK35.1s927 / 1.4k
CG-AL-E010easy1100.0 / 1005/5OK20.6s280 / 236
CG-AL-E050easy20.0 / 1000/0FAIL9.2s1.8k / 1.9k
CG-AL-E052easy1100.0 / 10016/16OK11.2s352 / 475
CG-AL-E054easy2100.0 / 1009/9OK23.9s949 / 2.2k
CG-AL-E056easy2100.0 / 10015/15OK14.8s1.7k / 1.1k
CG-AL-H007hard1100.0 / 10011/11OK20.8s545 / 1.6k
CG-AL-H011hard20.0 / 1000/0FAIL3.6s1.1k / 3.2k
CG-AL-H014hard20.0 / 1000/0FAIL3.9s1.4k / 1.7k
CG-AL-H017hard20.0 / 1000/0FAIL4.0s979 / 3.8k
CG-AL-H020hard20.0 / 1000/0FAIL6.0s1.7k / 3.0k
CG-AL-H021hard20.0 / 1000/0FAIL6.6s1.9k / 3.0k
CG-AL-H023hard20.0 / 1000/0FAIL4.1s5.8k / 12k
CG-AL-H027hard262.5 / 1002/4OK10.9s2.1k / 3.7k
CG-AL-H029hard20.0 / 1000/0FAIL4.0s2.6k / 6.9k
CG-AL-H030hard2100.0 / 10010/10OK9.8s2.4k / 8.4k
CG-AL-H031hard1100.0 / 10022/22OK10.6s939 / 3.7k
CG-AL-H034hard2100.0 / 1003/3OK16.5s1.6k / 1.5k
CG-AL-H036hard20.0 / 1000/0FAIL3.6s1.0k / 4.3k
CG-AL-H037hard10.0 / 1000/0FAIL5.4s497 / 1.2k
CG-AL-H041hard2100.0 / 1003/3OK16.5s1.5k / 2.7k
CG-AL-H050hard262.5 / 1002/3OK11.8s1.4k / 2.0k
CG-AL-H054hard2100.0 / 1005/5OK9.9s1.9k / 1.9k
CG-AL-H056hard20.0 / 1000/0FAIL5.5s1.4k / 2.1k
CG-AL-M001medium20.0 / 1000/0FAIL3.9s1.3k / 3.5k
CG-AL-M003medium1100.0 / 1009/9OK11.3s419 / 2.1k
CG-AL-M004medium20.0 / 1000/0FAIL4.3s1.8k / 3.6k
CG-AL-M006medium262.5 / 10016/18OK10.9s2.2k / 8.3k
CG-AL-M007medium262.5 / 10013/15OK11.6s2.4k / 7.1k
CG-AL-M008medium262.5 / 1004/12OK12.2s4.5k / 13k
CG-AL-M009medium2100.0 / 10011/11OK10.8s4.9k / 13k
CG-AL-M010medium1100.0 / 10021/21OK23.3s596 / 4.9k
CG-AL-M020medium2100.0 / 10017/17OK11.4s2.0k / 3.3k
CG-AL-M023medium1100.0 / 10011/11OK10.5s482 / 1.2k
CG-AL-M025medium2100.0 / 1008/8OK10.1s2.9k / 2.6k
CG-AL-M026medium1100.0 / 1008/8OK10.0s370 / 2.2k
CG-AL-M027medium20.0 / 1000/0FAIL3.8s3.7k / 4.4k
CG-AL-M028medium2100.0 / 1003/3OK23.7s1.0k / 1.8k
CG-AL-M031medium2100.0 / 1002/2OK10.9s2.0k / 3.4k
CG-AL-M034medium1100.0 / 1002/2OK10.4s415 / 1.7k
CG-AL-M036medium2100.0 / 1002/2OK10.0s1.5k / 1.4k
CG-AL-M040medium1100.0 / 1002/2OK9.7s311 / 802
CG-AL-M042medium1100.0 / 1008/8OK10.2s498 / 838
CG-AL-X001hard1100.0 / 1002/2OK11.4s308 / 490
CG-AL-X002hard1100.0 / 1004/4OK10.2s488 / 2.1k
CG-AL-X003hard2100.0 / 1003/3OK10.1s973 / 2.4k
CG-AL-X004medium1100.0 / 1003/3OK10.3s358 / 1.9k
CG-AL-X005hard1100.0 / 1002/2OK10.3s327 / 1.3k
CG-AL-X006hard1100.0 / 1003/3OK10.3s383 / 1.6k
CG-AL-X007hard1100.0 / 1002/2OK1m 19s372 / 874
CG-AL-X008hard1100.0 / 1001/1OK10.9s417 / 2.5k
CG-AL-X009medium1100.0 / 1002/2OK10.3s313 / 468
CG-AL-X010medium1100.0 / 1003/3OK10.4s284 / 496
CG-AL-X011medium1100.0 / 1002/2OK9.9s360 / 538
CG-AL-X012hard1100.0 / 1001/1OK10.2s380 / 2.0k
CG-AL-X013hard1100.0 / 1002/2OK10.2s263 / 456
CG-AL-X014medium1100.0 / 1004/4OK11.7s291 / 536
CG-AL-X017medium2100.0 / 1003/3OK10.1s1.4k / 474
CG-AL-X018medium1100.0 / 1003/3OK10.7s384 / 1.0k
CG-AL-X019medium1100.0 / 1003/3OK11.5s365 / 848
CG-AL-X022medium2100.0 / 1003/3OK9.8s1.3k / 1.5k
CG-AL-X024medium1100.0 / 1003/3OK10.0s333 / 760
CG-AL-X025medium1100.0 / 1001/1OK10.1s371 / 1.1k
CG-AL-X026medium1100.0 / 1003/3OK10.5s327 / 380
CG-AL-X027medium1100.0 / 1004/4OK10.3s258 / 560
CG-AL-X029medium1100.0 / 1002/2OK10.1s276 / 2.2k
CG-AL-X030medium1100.0 / 1002/2OK10.2s239 / 302
CG-AL-X031medium1100.0 / 1003/3OK10.2s297 / 397
CG-AL-X033hard1100.0 / 1002/2OK11.3s348 / 426
CG-AL-X034hard1100.0 / 1003/3OK10.5s304 / 932
CG-AL-X035hard2100.0 / 1003/3OK10.6s1.6k / 2.0k
CG-AL-X037hard20.0 / 1000/0FAIL3.9s1.1k / 2.7k
CG-AL-X040hard20.0 / 1000/0FAIL3.9s1.4k / 3.4k
CG-AL-X041hard2100.0 / 1005/5OK10.3s2.5k / 4.1k
CG-AL-X043hard20.0 / 1000/0FAIL3.7s1.5k / 5.4k
CG-AL-X044hard262.5 / 1000/3OK10.4s1.4k / 5.0k
CG-AL-X045hard1100.0 / 1003/3OK10.4s371 / 594
CG-AL-X046hard1100.0 / 1002/2OK9.9s369 / 1.1k
CG-AL-X047hard262.5 / 1001/2OK10.6s1.3k / 5.7k
CG-AL-X050hard1100.0 / 1002/2OK11.6s405 / 1.6k
CG-AL-X051hard1100.0 / 1002/2OK11.7s509 / 932
CG-AL-X052hard1100.0 / 1003/3OK10.8s358 / 974
CG-AL-X055hard1100.0 / 1005/5OK10.3s344 / 1.0k
CG-AL-X056hard1100.0 / 1005/5OK10.2s280 / 764
CG-AL-X057hard1100.0 / 1005/5OK10.1s250 / 497
CG-AL-X058hard2100.0 / 1005/5OK10.3s883 / 1.4k
CG-AL-X059hard1100.0 / 1003/3OK10.5s327 / 437
CG-AL-X060hard1100.0 / 1003/3OK10.4s302 / 647
CG-AL-X061hard1100.0 / 1004/4OK11.1s364 / 300
CG-AL-X062hard1100.0 / 1004/4OK10.2s358 / 802
CG-AL-X063hard1100.0 / 1003/3OK10.4s360 / 693
CG-AL-X064hard1100.0 / 1007/7OK10.1s277 / 1.0k
CG-AL-X065hard1100.0 / 1006/6OK9.9s709 / 730
CG-AL-X066hard1100.0 / 10014/14OK10.2s1.2k / 1.2k
CG-AL-X067hard262.5 / 1006/7OK10.4s1.6k / 4.0k
CG-AL-X068hard1100.0 / 10012/12OK10.2s1.2k / 1.9k
CG-AL-X069hard20.0 / 1000/0FAIL4.7s2.6k / 6.4k
CG-AL-X070hard1100.0 / 10012/12OK10.0s1.2k / 1.2k
CG-AL-X071hard1100.0 / 1008/8OK10.2s1.4k / 1.3k
CG-AL-X072hard1100.0 / 1007/7OK10.3s1.1k / 852
CG-AL-X073hard1100.0 / 1008/8OK10.0s1.4k / 1.4k
CG-AL-X074hard2100.0 / 1007/7OK10.0s3.4k / 4.9k
CG-AL-X075hard1100.0 / 1007/7OK10.2s810 / 2.0k
CG-AL-X076hard1100.0 / 10014/14OK11.7s954 / 1.7k
CG-AL-X077hard1100.0 / 10022/22OK10.5s1.5k / 1.3k
CG-AL-X078hard1100.0 / 10017/17OK10.8s1.2k / 977
CG-AL-X079hard262.5 / 10010/11OK10.1s3.3k / 7.2k
CG-AL-X080hard262.5 / 1006/7OK10.1s2.4k / 2.7k
CG-AL-X081hard1100.0 / 1008/8OK9.8s902 / 600
CG-AL-X082hard1100.0 / 10015/15OK10.5s1.2k / 1.0k
CG-AL-X083hard1100.0 / 1009/9OK10.3s1.5k / 1.2k
CG-AL-X084hard2100.0 / 10010/10OK10.7s3.2k / 4.8k
CG-AL-X085hard1100.0 / 1007/7OK11.6s980 / 1.1k
CG-AL-X086hard1100.0 / 1006/6OK11.7s1.4k / 2.7k
CG-AL-X087hard1100.0 / 1003/3OK10.9s1.0k / 870
CG-AL-X088hard1100.0 / 1006/6OK10.4s974 / 1.2k
CG-AL-X089hard1100.0 / 10011/11OK10.7s1.1k / 3.1k
CG-AL-X090hard1100.0 / 10010/10OK10.8s889 / 2.2k
CG-AL-X091hard1100.0 / 1006/6OK10.4s569 / 355
CG-AL-X092hard1100.0 / 10015/15OK10.2s444 / 376
CG-AL-X093hard1100.0 / 10010/10OK10.2s989 / 896
CG-AL-X094hard1100.0 / 1007/7OK10.0s754 / 818
CG-AL-X095hard1100.0 / 1005/5OK10.1s797 / 714
CG-AL-X096hard1100.0 / 10049/49OK10.3s3.3k / 3.0k
CG-AL-X097hard2100.0 / 10046/46OK10.6s7.1k / 7.5k
CG-AL-X098hard1100.0 / 10029/29OK10.9s2.6k / 2.3k
CG-AL-X099hard1100.0 / 10039/39OK14.7s3.6k / 5.1k
CG-AL-X100hard1100.0 / 10035/35OK10.4s3.5k / 3.8k
CG-AL-X101hard1100.0 / 10010/10OK10.4s1.1k / 1.2k
CG-AL-X102hard1100.0 / 1008/8OK9.9s531 / 2.2k
CG-AL-X103hard1100.0 / 1007/7OK10.3s725 / 613
CG-AL-X104hard1100.0 / 1006/6OK10.6s1.1k / 943
CG-AL-X105hard1100.0 / 1006/6OK9.9s777 / 981
CG-AL-X106hard1100.0 / 1005/5OK9.9s878 / 1.5k
CG-AL-X107hard1100.0 / 1004/4OK10.1s805 / 782
CG-AL-X108hard1100.0 / 1006/6OK10.9s729 / 530
CG-AL-X109hard1100.0 / 1005/5OK10.3s548 / 534
CG-AL-X110hard1100.0 / 10017/17OK10.2s1.2k / 1.0k
CG-AL-X111hard1100.0 / 1008/8OK10.0s1.2k / 2.4k
CG-AL-X112hard2100.0 / 10012/12OK10.6s2.5k / 4.8k
CG-AL-X113hard1100.0 / 10013/13OK11.0s705 / 4.5k
CG-AL-X114hard1100.0 / 1007/7OK9.9s718 / 519
CG-AL-X115hard1100.0 / 10013/13OK10.0s478 / 861
CG-AL-X116hard2100.0 / 10017/17OK10.2s2.0k / 7.0k
CG-AL-X117hard1100.0 / 1008/8OK10.1s1.0k / 1.3k
CG-AL-X118hard1100.0 / 10017/17OK10.1s1.4k / 1.4k
CG-AL-X119hard1100.0 / 10015/15OK10.3s1.7k / 1.7k
CG-AL-X120hard1100.0 / 10012/12OK9.9s1.2k / 1.1k
CG-AL-X121hard1100.0 / 1006/6OK10.1s1.0k / 859
CG-AL-X122hard1100.0 / 10010/10OK10.0s1.5k / 1.9k
CG-AL-X123hard1100.0 / 1005/5OK10.0s603 / 466
CG-AL-X124hard1100.0 / 10010/10OK10.1s994 / 988
CG-AL-X125hard1100.0 / 1008/8OK10.3s1.4k / 1.2k
CG-AL-X126hard1100.0 / 10014/14OK10.0s711 / 614
CG-AL-X127hard1100.0 / 1005/5OK9.8s666 / 506
CG-AL-X128hard1100.0 / 1008/8OK10.0s1.1k / 893
CG-AL-X129hard1100.0 / 10014/14OK10.3s1.2k / 1.1k
CG-AL-X130hard1100.0 / 1005/5OK9.9s529 / 2.6k
CG-AL-X131hard1100.0 / 10013/13OK11.6s941 / 717
CG-AL-X132hard1100.0 / 10010/10OK10.0s709 / 459
CG-AL-X133hard20.0 / 1000/0FAIL5.0s3.4k / 7.5k
CG-AL-X134hard1100.0 / 1006/6OK10.6s1.2k / 1.7k
CG-AL-X135hard1100.0 / 1004/4OK10.1s866 / 706
CG-AL-X136hard1100.0 / 1007/7OK10.3s754 / 504
CG-AL-X137hard1100.0 / 1004/4OK9.8s915 / 1.2k
CG-AL-X138hard1100.0 / 1009/9OK10.3s1.4k / 2.3k
CG-AL-X139hard1100.0 / 10011/11OK10.3s1.6k / 1.5k
CG-AL-X140hard2100.0 / 1007/7OK10.3s4.1k / 7.8k
CG-AL-X141hard1100.0 / 10039/39OK10.8s3.5k / 3.5k
CG-AL-X142hard2100.0 / 10048/48OK12.2s9.0k / 12k
CG-AL-X143hard1100.0 / 10035/35OK15.8s4.0k / 4.5k
CG-AL-X144hard1100.0 / 10043/43OK11.0s3.6k / 3.5k
CG-AL-X145hard1100.0 / 10032/32OK10.9s4.2k / 4.1k
CG-AL-X146hard20.0 / 1000/0FAIL4.0s4.3k / 9.9k
CG-AL-X147hard1100.0 / 1008/8OK10.1s1.3k / 1.0k
CG-AL-X148hard1100.0 / 1006/6OK10.6s1.1k / 843
CG-AL-X149hard1100.0 / 1007/7OK10.1s1.1k / 1.2k
CG-AL-X150hard262.5 / 1007/9OK12.4s5.0k / 10.0k
CG-AL-X151hard1100.0 / 1006/6OK10.6s818 / 558
CG-AL-X152hard1100.0 / 1008/8OK10.8s1.1k / 896
CG-AL-X153hard2100.0 / 1009/9OK19.6s3.1k / 7.7k
CG-AL-X154hard1100.0 / 1009/9OK10.4s1.2k / 1.2k
CG-AL-X155hard1100.0 / 10011/11OK10.5s923 / 997
CG-AL-X156hard1100.0 / 1007/7OK10.4s884 / 575
CG-AL-X157hard1100.0 / 10010/10OK10.7s1.3k / 1.0k
CG-AL-X158hard1100.0 / 1007/7OK11.4s801 / 511
CG-AL-X159hard1100.0 / 1007/7OK10.7s849 / 708
CG-AL-X160hard1100.0 / 10013/13OK10.3s1.2k / 1.5k
CG-AL-X161hard1100.0 / 10010/10OK10.5s1.4k / 1.4k
CG-AL-X162hard1100.0 / 1007/7OK10.4s956 / 796
CG-AL-X163hard1100.0 / 1007/7OK10.6s1.0k / 834
CG-AL-X164hard1100.0 / 1007/7OK10.6s945 / 809
CG-AL-X165hard20.0 / 1000/0FAIL4.7s5.5k / 9.6k
CG-AL-X166hard2100.0 / 10014/14OK11.7s3.9k / 3.1k
CG-AL-X167hard1100.0 / 10013/13OK11.3s1.4k / 4.2k
CG-AL-X168hard2100.0 / 1009/9OK12.0s3.1k / 5.0k
CG-AL-X169hard1100.0 / 10011/11OK12.7s1.6k / 2.9k
CG-AL-X170hard1100.0 / 10011/11OK11.9s3.1k / 4.8k
CG-AL-X171hard1100.0 / 1009/9OK11.2s1.4k / 4.2k
CG-AL-X172hard1100.0 / 10011/11OK11.2s2.2k / 5.1k
CG-AL-X173hard20.0 / 1000/0FAIL4.2s7.4k / 8.2k
CG-AL-X174hard1100.0 / 10016/16OK11.0s3.9k / 7.4k
CG-AL-X185hard2100.0 / 10043/43OK12.0s6.9k / 4.0k
CG-AL-X187hard2100.0 / 10033/33OK11.7s7.5k / 5.3k
CG-AL-X194hard2100.0 / 10050/50OK11.1s9.9k / 5.5k
CG-AL-X211hard262.5 / 10037/43OK10.9s7.7k / 5.5k
CG-AL-X214hard262.5 / 10032/34OK11.0s10.0k / 6.4k
CG-AL-X218hard262.5 / 10024/27OK10.6s9.8k / 5.4k
CG-AL-X234hard2100.0 / 10035/35OK10.6s9.0k / 5.1k
CG-AL-X239hard2100.0 / 10037/37OK10.9s11k / 8.2k
CG-AL-X244hard262.5 / 10032/38OK10.7s12k / 13k
CG-AL-X245hard2100.0 / 10063/63OK11.3s9.8k / 3.5k
CG-AL-X248hard262.5 / 10062/66OK11.0s8.4k / 5.4k
CG-AL-X249hard2100.0 / 10037/37OK11.2s9.6k / 6.8k
CG-AL-X254hard262.5 / 10064/70OK11.2s15k / 7.8k
CG-AL-X257hard2100.0 / 10053/53OK10.7s8.9k / 8.3k
CG-AL-X263hard2100.0 / 10061/61OK11.9s11k / 11k
CG-AL-X264hard262.5 / 10062/65OK11.1s12k / 9.7k
CG-AL-X270hard2100.0 / 10063/63OK11.4s17k / 10k
CG-AL-X271hard262.5 / 10069/70OK12.7s18k / 15k
CG-AL-X272hard2100.0 / 10079/79OK11.8s14k / 5.8k
CG-AL-X274hard20.0 / 1000/0FAIL3.5s18k / 9.8k
CG-AL-X276hard2100.0 / 10078/78OK11.6s14k / 7.5k
CG-AL-X278hard262.5 / 10068/71OK12.1s14k / 10k
CG-AL-X283hard2100.0 / 10076/76OK11.7s15k / 9.0k
CG-AL-X289hard2100.0 / 10057/57OK11.3s13k / 9.4k
CG-AL-X290hard2100.0 / 10047/47OK11.5s12k / 6.8k
CG-AL-X292hard2100.0 / 10057/57OK11.1s11k / 3.4k
CG-AL-X293hard2100.0 / 10049/49OK10.7s10k / 4.9k
CG-AL-X296hard2100.0 / 10047/47OK11.1s19k / 9.9k
CG-AL-X298hard262.5 / 10054/55OK10.8s9.4k / 7.4k