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.

77.6% 180/232 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.

70.8 / 100
Cost $0.93
Tokens 672k / 663k input / output, all attempts
Duration 57m 19s
Filter:
Per-task results for run 4c8313eb-73a1-41af-b704-c0f04e9cca67
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK18.2s258 / 518
CG-AL-E006easy1100.0 / 1007/7OK31.6s305 / 840
CG-AL-E010easy1100.0 / 1005/5OK18.7s280 / 476
CG-AL-E050easy20.0 / 1000/0FAIL10.3s1.8k / 1.4k
CG-AL-E052easy1100.0 / 10016/16OK10.6s352 / 556
CG-AL-E054easy2100.0 / 1009/9OK19.8s1.0k / 1.7k
CG-AL-E056easy2100.0 / 10015/15OK20.1s1.7k / 1.6k
CG-AL-H007hard1100.0 / 10011/11OK10.8s545 / 2.0k
CG-AL-H011hard20.0 / 1000/0FAIL10.1s1.2k / 4.4k
CG-AL-H014hard20.0 / 1000/0FAIL4.4s1.3k / 1.4k
CG-AL-H017hard20.0 / 1000/0FAIL9.9s1.1k / 3.5k
CG-AL-H020hard2100.0 / 10010/10OK11.4s1.8k / 3.0k
CG-AL-H021hard262.5 / 1006/20OK12.0s1.8k / 2.2k
CG-AL-H023hard20.0 / 1000/0FAIL4.4s6.7k / 9.2k
CG-AL-H027hard2100.0 / 1004/4OK12.5s2.1k / 3.4k
CG-AL-H029hard20.0 / 1000/0FAIL4.1s2.8k / 6.2k
CG-AL-H030hard2100.0 / 10010/10OK10.9s2.2k / 5.3k
CG-AL-H031hard2100.0 / 10022/22OK11.6s3.4k / 6.1k
CG-AL-H034hard1100.0 / 1003/3OK10.5s431 / 1.2k
CG-AL-H036hard20.0 / 1000/0FAIL4.0s911 / 3.5k
CG-AL-H037hard20.0 / 1000/0FAIL4.1s1.2k / 3.8k
CG-AL-H041hard1100.0 / 1003/3OK10.7s565 / 3.1k
CG-AL-H050hard262.5 / 1002/3OK11.0s1.4k / 2.3k
CG-AL-H054hard20.0 / 1000/0FAIL9.4s1.9k / 1.4k
CG-AL-H056hard20.0 / 1000/0FAIL3.9s1.4k / 2.3k
CG-AL-M001medium20.0 / 1000/0FAIL4.1s1.5k / 2.2k
CG-AL-M003medium1100.0 / 1009/9OK12.1s419 / 1.9k
CG-AL-M004medium1100.0 / 10012/12OK29.5s449 / 2.7k
CG-AL-M006medium262.5 / 10017/18OK12.5s2.2k / 5.7k
CG-AL-M007medium20.0 / 1000/0FAIL4.2s3.8k / 7.3k
CG-AL-M008medium20.0 / 1000/0FAIL4.0s3.7k / 9.0k
CG-AL-M009medium1100.0 / 10011/11OK10.9s429 / 4.0k
CG-AL-M010medium2100.0 / 10021/21OK23.1s2.8k / 5.9k
CG-AL-M020medium2100.0 / 10017/17OK10.7s1.9k / 2.9k
CG-AL-M023medium2100.0 / 10011/11OK11.5s1.4k / 1.4k
CG-AL-M025medium2100.0 / 1008/8OK11.2s2.8k / 2.6k
CG-AL-M026medium1100.0 / 1008/8OK11.7s370 / 2.9k
CG-AL-M027medium2100.0 / 10018/18OK11.2s3.4k / 3.1k
CG-AL-M028medium2100.0 / 1003/3OK25.9s1.0k / 1.7k
CG-AL-M031medium2100.0 / 1002/2OK11.0s2.1k / 2.7k
CG-AL-M034medium2100.0 / 1002/2OK11.5s1.3k / 4.3k
CG-AL-M036medium211.1 / 1000/0FAIL4.2s1.4k / 1.3k
CG-AL-M040medium20.0 / 1000/0FAIL3.9s785 / 1.9k
CG-AL-M042medium1100.0 / 1008/8OK10.8s498 / 1.3k
CG-AL-X001hard1100.0 / 1002/2OK10.7s308 / 1.1k
CG-AL-X002hard1100.0 / 1004/4OK10.9s488 / 2.4k
CG-AL-X003hard20.0 / 1000/0FAIL4.0s712 / 5.6k
CG-AL-X004medium1100.0 / 1003/3OK10.8s358 / 1.2k
CG-AL-X005hard1100.0 / 1002/2OK10.7s327 / 1.2k
CG-AL-X006hard1100.0 / 1003/3OK10.8s383 / 1.2k
CG-AL-X007hard1100.0 / 1002/2OK1m 21s372 / 1.2k
CG-AL-X008hard20.0 / 1000/0FAIL4.3s1.2k / 3.4k
CG-AL-X009medium1100.0 / 1002/2OK10.9s313 / 500
CG-AL-X010medium1100.0 / 1003/3OK11.1s284 / 500
CG-AL-X011medium1100.0 / 1002/2OK10.9s360 / 680
CG-AL-X012hard1100.0 / 1001/1OK10.4s380 / 665
CG-AL-X013hard1100.0 / 1002/2OK10.3s263 / 312
CG-AL-X014medium1100.0 / 1004/4OK11.3s291 / 325
CG-AL-X017medium262.5 / 1000/3OK11.1s647 / 605
CG-AL-X018medium1100.0 / 1003/3OK10.6s384 / 679
CG-AL-X019medium1100.0 / 1003/3OK10.4s365 / 713
CG-AL-X022medium2100.0 / 1003/3OK11.1s1.3k / 1.4k
CG-AL-X024medium1100.0 / 1003/3OK10.4s333 / 1.3k
CG-AL-X025medium1100.0 / 1001/1OK10.6s371 / 1.9k
CG-AL-X026medium1100.0 / 1003/3OK10.5s327 / 396
CG-AL-X027medium1100.0 / 1004/4OK10.5s258 / 668
CG-AL-X029medium1100.0 / 1002/2OK10.5s276 / 952
CG-AL-X030medium1100.0 / 1002/2OK10.4s239 / 461
CG-AL-X031medium1100.0 / 1003/3OK10.7s297 / 262
CG-AL-X033hard1100.0 / 1002/2OK10.8s348 / 343
CG-AL-X034hard1100.0 / 1003/3OK11.0s304 / 623
CG-AL-X035hard1100.0 / 1003/3OK10.8s331 / 1.1k
CG-AL-X037hard20.0 / 1000/0FAIL3.9s2.1k / 4.5k
CG-AL-X040hard20.0 / 1000/0FAIL4.1s1.4k / 4.7k
CG-AL-X041hard262.5 / 1000/5OK11.8s1.2k / 4.4k
CG-AL-X043hard2100.0 / 1001/1OK12.4s1.4k / 5.4k
CG-AL-X044hard262.5 / 1001/3OK11.8s997 / 2.6k
CG-AL-X045hard1100.0 / 1003/3OK11.0s371 / 531
CG-AL-X046hard2100.0 / 1002/2OK11.6s1.5k / 1.6k
CG-AL-X047hard262.5 / 1000/2OK11.5s1.3k / 5.7k
CG-AL-X050hard1100.0 / 1002/2OK10.8s405 / 733
CG-AL-X051hard2100.0 / 1002/2OK11.5s1.8k / 3.5k
CG-AL-X052hard1100.0 / 1003/3OK10.6s358 / 1.1k
CG-AL-X055hard1100.0 / 1005/5OK10.3s344 / 708
CG-AL-X056hard1100.0 / 1005/5OK10.3s280 / 1.1k
CG-AL-X057hard1100.0 / 1005/5OK10.3s250 / 364
CG-AL-X058hard1100.0 / 1005/5OK10.9s314 / 1.2k
CG-AL-X059hard1100.0 / 1003/3OK10.9s327 / 276
CG-AL-X060hard1100.0 / 1003/3OK10.7s302 / 1.1k
CG-AL-X061hard1100.0 / 1004/4OK10.8s364 / 461
CG-AL-X062hard1100.0 / 1004/4OK10.9s358 / 782
CG-AL-X063hard1100.0 / 1003/3OK10.9s360 / 1.2k
CG-AL-X064hard2100.0 / 1007/7OK11.2s810 / 996
CG-AL-X065hard1100.0 / 1006/6OK10.6s709 / 732
CG-AL-X066hard1100.0 / 10014/14OK11.3s1.2k / 1.2k
CG-AL-X067hard262.5 / 1006/7OK11.1s1.6k / 3.9k
CG-AL-X068hard1100.0 / 10012/12OK10.8s1.2k / 1.3k
CG-AL-X069hard1100.0 / 1008/8OK11.0s1.1k / 3.2k
CG-AL-X070hard1100.0 / 10012/12OK10.7s1.2k / 2.7k
CG-AL-X071hard1100.0 / 1008/8OK10.7s1.4k / 1.4k
CG-AL-X072hard1100.0 / 1007/7OK11.0s1.1k / 850
CG-AL-X073hard1100.0 / 1008/8OK10.9s1.4k / 1.4k
CG-AL-X074hard262.5 / 1006/7OK11.3s3.7k / 6.7k
CG-AL-X075hard1100.0 / 1007/7OK10.7s810 / 1.6k
CG-AL-X076hard1100.0 / 10014/14OK10.8s954 / 2.6k
CG-AL-X077hard1100.0 / 10022/22OK10.9s1.5k / 1.4k
CG-AL-X078hard1100.0 / 10017/17OK11.1s1.2k / 959
CG-AL-X079hard262.5 / 10010/11OK10.9s3.2k / 7.6k
CG-AL-X080hard20.0 / 1000/0FAIL4.0s2.4k / 4.1k
CG-AL-X081hard1100.0 / 1008/8OK10.6s902 / 627
CG-AL-X082hard1100.0 / 10015/15OK10.6s1.2k / 988
CG-AL-X083hard1100.0 / 1009/9OK10.7s1.5k / 1.2k
CG-AL-X084hard1100.0 / 10010/10OK11.5s1.4k / 4.0k
CG-AL-X085hard1100.0 / 1007/7OK10.6s980 / 899
CG-AL-X086hard1100.0 / 1006/6OK10.6s1.4k / 2.2k
CG-AL-X087hard1100.0 / 1003/3OK10.6s1.0k / 923
CG-AL-X088hard1100.0 / 1006/6OK10.8s974 / 1.0k
CG-AL-X089hard1100.0 / 10011/11OK11.0s1.1k / 3.7k
CG-AL-X090hard262.5 / 1008/10OK11.2s1.9k / 5.9k
CG-AL-X091hard1100.0 / 1006/6OK10.8s569 / 432
CG-AL-X092hard1100.0 / 10015/15OK10.7s444 / 603
CG-AL-X093hard1100.0 / 10010/10OK10.6s989 / 1.1k
CG-AL-X094hard1100.0 / 1007/7OK10.5s754 / 759
CG-AL-X095hard1100.0 / 1005/5OK11.1s797 / 709
CG-AL-X096hard1100.0 / 10049/49OK11.2s3.3k / 3.1k
CG-AL-X097hard1100.0 / 10046/46OK11.1s3.4k / 3.2k
CG-AL-X098hard1100.0 / 10029/29OK10.9s2.6k / 2.3k
CG-AL-X099hard1100.0 / 10039/39OK12.7s3.6k / 4.6k
CG-AL-X100hard1100.0 / 10035/35OK11.2s3.5k / 3.6k
CG-AL-X101hard262.5 / 1005/10OK11.2s4.0k / 4.5k
CG-AL-X102hard2100.0 / 1008/8OK11.3s2.3k / 2.4k
CG-AL-X103hard1100.0 / 1007/7OK10.7s725 / 628
CG-AL-X104hard1100.0 / 1006/6OK10.8s1.1k / 947
CG-AL-X105hard1100.0 / 1006/6OK10.8s777 / 643
CG-AL-X106hard1100.0 / 1005/5OK10.5s878 / 914
CG-AL-X107hard1100.0 / 1004/4OK10.9s805 / 723
CG-AL-X108hard1100.0 / 1006/6OK11.5s729 / 511
CG-AL-X109hard1100.0 / 1005/5OK11.3s548 / 680
CG-AL-X110hard1100.0 / 10017/17OK10.8s1.2k / 1.1k
CG-AL-X111hard2100.0 / 1008/8OK11.1s2.8k / 5.7k
CG-AL-X112hard1100.0 / 10012/12OK10.9s906 / 2.3k
CG-AL-X113hard1100.0 / 10013/13OK11.0s705 / 658
CG-AL-X114hard1100.0 / 1007/7OK10.6s718 / 493
CG-AL-X115hard1100.0 / 10013/13OK10.6s478 / 698
CG-AL-X116hard2100.0 / 10017/17OK10.7s2.6k / 5.4k
CG-AL-X117hard1100.0 / 1008/8OK11.2s1.0k / 1.1k
CG-AL-X118hard1100.0 / 10017/17OK10.9s1.4k / 1.6k
CG-AL-X119hard1100.0 / 10015/15OK10.9s1.7k / 1.8k
CG-AL-X120hard2100.0 / 10012/12OK11.0s4.3k / 2.3k
CG-AL-X121hard1100.0 / 1006/6OK10.5s1.0k / 880
CG-AL-X122hard1100.0 / 10010/10OK11.3s1.5k / 1.5k
CG-AL-X123hard1100.0 / 1005/5OK10.8s603 / 492
CG-AL-X124hard1100.0 / 10010/10OK10.9s994 / 944
CG-AL-X125hard1100.0 / 1008/8OK11.2s1.4k / 1.7k
CG-AL-X126hard1100.0 / 10014/14OK13.7s711 / 973
CG-AL-X127hard1100.0 / 1005/5OK11.5s666 / 554
CG-AL-X128hard1100.0 / 1008/8OK13.6s1.1k / 918
CG-AL-X129hard1100.0 / 10014/14OK11.8s1.2k / 1.2k
CG-AL-X130hard1100.0 / 1005/5OK11.4s529 / 2.2k
CG-AL-X131hard1100.0 / 10013/13OK14.1s941 / 831
CG-AL-X132hard1100.0 / 10010/10OK14.0s709 / 452
CG-AL-X133hard262.5 / 1007/8OK11.0s3.4k / 4.9k
CG-AL-X134hard1100.0 / 1006/6OK11.4s1.2k / 1.4k
CG-AL-X135hard1100.0 / 1004/4OK11.0s866 / 677
CG-AL-X136hard1100.0 / 1007/7OK10.8s754 / 456
CG-AL-X137hard1100.0 / 1004/4OK11.1s915 / 1.1k
CG-AL-X138hard1100.0 / 1009/9OK11.4s1.4k / 2.1k
CG-AL-X139hard1100.0 / 10011/11OK11.7s1.6k / 1.6k
CG-AL-X140hard2100.0 / 1007/7OK11.2s4.0k / 7.0k
CG-AL-X141hard1100.0 / 10039/39OK12.0s3.5k / 3.0k
CG-AL-X142hard262.5 / 10045/48OK12.1s9.7k / 9.6k
CG-AL-X143hard1100.0 / 10035/35OK13.2s4.0k / 3.7k
CG-AL-X144hard1100.0 / 10043/43OK8.9s3.6k / 3.3k
CG-AL-X145hard1100.0 / 10032/32OK11.6s4.2k / 4.0k
CG-AL-X146hard1100.0 / 1009/9OK11.5s1.7k / 4.3k
CG-AL-X147hard1100.0 / 1008/8OK10.7s1.3k / 1.1k
CG-AL-X148hard1100.0 / 1006/6OK10.9s1.1k / 825
CG-AL-X149hard1100.0 / 1007/7OK10.7s1.1k / 1.2k
CG-AL-X150hard2100.0 / 1009/9OK11.5s5.0k / 7.0k
CG-AL-X151hard1100.0 / 1006/6OK10.7s818 / 563
CG-AL-X152hard1100.0 / 1008/8OK10.9s1.1k / 1.0k
CG-AL-X153hard1100.0 / 1009/9OK14.7s888 / 2.1k
CG-AL-X154hard1100.0 / 1009/9OK10.9s1.2k / 1.1k
CG-AL-X155hard1100.0 / 10011/11OK11.6s923 / 1.7k
CG-AL-X156hard1100.0 / 1007/7OK10.8s884 / 586
CG-AL-X157hard1100.0 / 10010/10OK11.5s1.3k / 1.1k
CG-AL-X158hard1100.0 / 1007/7OK11.0s801 / 494
CG-AL-X159hard1100.0 / 1007/7OK11.6s849 / 851
CG-AL-X160hard1100.0 / 10013/13OK11.3s1.2k / 1.4k
CG-AL-X161hard1100.0 / 10010/10OK11.0s1.4k / 1.4k
CG-AL-X162hard1100.0 / 1007/7OK10.8s956 / 782
CG-AL-X163hard1100.0 / 1007/7OK10.8s1.0k / 851
CG-AL-X164hard1100.0 / 1007/7OK10.7s945 / 1.1k
CG-AL-X165hard20.0 / 1000/0FAIL4.0s6.1k / 8.1k
CG-AL-X166hard2100.0 / 10014/14OK12.2s3.9k / 3.0k
CG-AL-X167hard2100.0 / 10013/13OK11.4s3.7k / 7.4k
CG-AL-X168hard262.5 / 1002/9OK11.7s3.6k / 7.6k
CG-AL-X169hard2100.0 / 10011/11OK11.7s4.0k / 6.5k
CG-AL-X170hard1100.0 / 10011/11OK11.2s3.1k / 5.0k
CG-AL-X171hard1100.0 / 1009/9OK12.1s1.4k / 3.7k
CG-AL-X172hard2100.0 / 10011/11OK11.7s5.9k / 8.2k
CG-AL-X173hard2100.0 / 10019/19OK12.4s6.7k / 8.0k
CG-AL-X174hard2100.0 / 10016/16OK12.1s10k / 9.4k
CG-AL-X185hard262.5 / 10041/43OK11.5s6.9k / 2.5k
CG-AL-X187hard2100.0 / 10033/33OK11.8s7.5k / 5.9k
CG-AL-X194hard262.5 / 10049/50OK12.5s10k / 5.7k
CG-AL-X211hard262.5 / 10041/43OK12.1s11k / 6.9k
CG-AL-X214hard20.0 / 1000/0FAIL4.2s10.0k / 6.2k
CG-AL-X218hard2100.0 / 10027/27OK11.8s8.8k / 5.6k
CG-AL-X234hard2100.0 / 10035/35OK12.0s9.1k / 3.9k
CG-AL-X239hard2100.0 / 10037/37OK12.1s11k / 5.8k
CG-AL-X244hard20.0 / 1000/0FAIL4.3s10k / 6.9k
CG-AL-X245hard262.5 / 10048/63OK12.3s15k / 6.6k
CG-AL-X248hard2100.0 / 10066/66OK12.4s10k / 5.3k
CG-AL-X249hard2100.0 / 10037/37OK12.1s11k / 8.1k
CG-AL-X254hard20.0 / 1000/0FAIL4.1s12k / 4.6k
CG-AL-X257hard262.5 / 10052/53OK12.4s9.5k / 7.0k
CG-AL-X263hard2100.0 / 10061/61OK12.5s12k / 6.8k
CG-AL-X264hard262.5 / 10063/65OK12.4s12k / 6.1k
CG-AL-X270hard262.5 / 10060/63OK12.3s19k / 6.1k
CG-AL-X271hard20.0 / 1000/0FAIL4.2s17k / 10k
CG-AL-X272hard2100.0 / 10079/79OK12.5s14k / 6.8k
CG-AL-X274hard2100.0 / 10064/64OK12.5s18k / 6.5k
CG-AL-X276hard262.5 / 10070/78OK13.5s18k / 7.5k
CG-AL-X278hard20.0 / 1000/0FAIL4.1s15k / 6.7k
CG-AL-X283hard262.5 / 10073/76OK12.6s17k / 8.3k
CG-AL-X289hard2100.0 / 10057/57OK12.7s12k / 6.2k
CG-AL-X290hard2100.0 / 10047/47OK12.2s12k / 5.9k
CG-AL-X292hard2100.0 / 10057/57OK12.7s15k / 4.9k
CG-AL-X293hard2100.0 / 10049/49OK12.1s10k / 4.4k
CG-AL-X296hard262.5 / 10032/47OK12.5s17k / 7.6k
CG-AL-X298hard262.5 / 10054/55OK11.8s13k / 6.5k