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.

78.9% 183/232 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 $0.43
Tokens 636k / 734k input / output, all attempts
Duration 55m 46s
Filter:
Per-task results for run 6ca71f64-9b32-445a-8f7f-9c4fde29374d
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.9s258 / 381
CG-AL-E006easy1100.0 / 1007/7OK32.5s305 / 679
CG-AL-E010easy262.5 / 1000/1OK32.0s708 / 1.1k
CG-AL-E050easy20.0 / 1000/0FAIL9.2s1.7k / 1.7k
CG-AL-E052easy1100.0 / 10016/16OK10.4s352 / 434
CG-AL-E054easy2100.0 / 1009/9OK17.2s1.0k / 2.8k
CG-AL-E056easy2100.0 / 10015/15OK10.3s1.7k / 1.3k
CG-AL-H007hard1100.0 / 10011/11OK11.6s545 / 2.8k
CG-AL-H011hard20.0 / 1000/0FAIL3.7s1.1k / 4.6k
CG-AL-H014hard20.0 / 1000/0FAIL3.9s1.4k / 1.7k
CG-AL-H017hard20.0 / 1000/0FAIL3.8s968 / 4.6k
CG-AL-H020hard20.0 / 1000/0FAIL3.7s1.8k / 3.6k
CG-AL-H021hard20.0 / 1000/0FAIL3.9s1.9k / 3.0k
CG-AL-H023hard20.0 / 1000/0FAIL4.0s6.4k / 14k
CG-AL-H027hard2100.0 / 1004/4OK10.2s2.1k / 2.8k
CG-AL-H029hard2100.0 / 10018/18OK11.3s2.7k / 7.4k
CG-AL-H030hard2100.0 / 10010/10OK10.2s2.4k / 8.0k
CG-AL-H031hard1100.0 / 10022/22OK10.6s939 / 3.8k
CG-AL-H034hard2100.0 / 1003/3OK10.6s1.6k / 1.7k
CG-AL-H036hard20.0 / 1000/0FAIL12.6s1.0k / 5.1k
CG-AL-H037hard20.0 / 1000/0FAIL4.0s1.2k / 1.7k
CG-AL-H041hard1100.0 / 1003/3OK10.0s565 / 3.5k
CG-AL-H050hard262.5 / 1002/3OK10.2s1.4k / 3.8k
CG-AL-H054hard2100.0 / 1005/5OK10.6s1.8k / 2.1k
CG-AL-H056hard20.0 / 1000/0FAIL4.1s1.4k / 1.9k
CG-AL-M001medium20.0 / 1000/0FAIL4.4s1.4k / 3.4k
CG-AL-M003medium262.5 / 1000/1OK27.3s1.4k / 4.2k
CG-AL-M004medium1100.0 / 10012/12OK28.0s449 / 2.9k
CG-AL-M006medium262.5 / 10015/18OK11.6s2.5k / 7.6k
CG-AL-M007medium20.0 / 1000/0FAIL3.6s3.1k / 9.6k
CG-AL-M008medium20.0 / 1000/0FAIL3.8s3.8k / 12k
CG-AL-M009medium20.0 / 1000/0FAIL3.8s3.6k / 9.1k
CG-AL-M010medium2100.0 / 10021/21OK22.1s2.8k / 6.8k
CG-AL-M020medium1100.0 / 10017/17OK10.4s554 / 2.6k
CG-AL-M023medium1100.0 / 10011/11OK10.5s482 / 1.5k
CG-AL-M025medium2100.0 / 1008/8OK10.6s2.8k / 1.9k
CG-AL-M026medium1100.0 / 1008/8OK9.9s370 / 2.1k
CG-AL-M027medium20.0 / 1000/0FAIL3.8s4.0k / 6.2k
CG-AL-M028medium2100.0 / 1003/3OK23.4s1.0k / 1.2k
CG-AL-M031medium1100.0 / 1002/2OK10.4s685 / 2.1k
CG-AL-M034medium2100.0 / 1002/2OK10.1s1.1k / 2.6k
CG-AL-M036medium211.1 / 1000/0FAIL4.0s1.5k / 1.6k
CG-AL-M040medium1100.0 / 1002/2OK10.2s311 / 1.1k
CG-AL-M042medium1100.0 / 1008/8OK10.3s498 / 849
CG-AL-X001hard1100.0 / 1002/2OK10.1s308 / 683
CG-AL-X002hard2100.0 / 1004/4OK10.1s2.7k / 4.8k
CG-AL-X003hard262.5 / 1002/3OK10.1s875 / 3.5k
CG-AL-X004medium2100.0 / 1003/3OK10.4s926 / 1.5k
CG-AL-X005hard1100.0 / 1002/2OK10.8s327 / 674
CG-AL-X006hard1100.0 / 1003/3OK10.0s383 / 729
CG-AL-X007hard1100.0 / 1002/2OK1m 17s372 / 1.4k
CG-AL-X008hard1100.0 / 1001/1OK10.6s417 / 2.4k
CG-AL-X009medium1100.0 / 1002/2OK9.8s313 / 661
CG-AL-X010medium1100.0 / 1003/3OK10.1s284 / 346
CG-AL-X011medium1100.0 / 1002/2OK9.9s360 / 503
CG-AL-X012hard1100.0 / 1001/1OK10.3s380 / 1.8k
CG-AL-X013hard1100.0 / 1002/2OK9.7s263 / 447
CG-AL-X014medium1100.0 / 1004/4OK10.2s291 / 403
CG-AL-X017medium2100.0 / 1003/3OK10.7s1.4k / 829
CG-AL-X018medium1100.0 / 1003/3OK10.2s384 / 636
CG-AL-X019medium1100.0 / 1003/3OK10.1s365 / 939
CG-AL-X022medium2100.0 / 1003/3OK10.2s1.3k / 1.1k
CG-AL-X024medium1100.0 / 1003/3OK9.9s333 / 669
CG-AL-X025medium1100.0 / 1001/1OK10.5s371 / 794
CG-AL-X026medium1100.0 / 1003/3OK10.3s327 / 371
CG-AL-X027medium2100.0 / 1004/4OK10.3s774 / 1.4k
CG-AL-X029medium1100.0 / 1002/2OK10.3s276 / 2.9k
CG-AL-X030medium1100.0 / 1002/2OK9.8s239 / 350
CG-AL-X031medium1100.0 / 1003/3OK10.1s297 / 311
CG-AL-X033hard1100.0 / 1002/2OK10.0s348 / 421
CG-AL-X034hard1100.0 / 1003/3OK10.6s304 / 868
CG-AL-X035hard1100.0 / 1003/3OK10.5s331 / 1.8k
CG-AL-X037hard1100.0 / 1004/4OK10.4s408 / 3.2k
CG-AL-X040hard20.0 / 1000/0FAIL4.3s1.4k / 3.4k
CG-AL-X041hard20.0 / 1000/0FAIL4.6s1.2k / 5.5k
CG-AL-X043hard20.0 / 1000/0FAIL3.9s1.4k / 7.1k
CG-AL-X044hard262.5 / 1001/3OK10.1s1.3k / 4.7k
CG-AL-X045hard1100.0 / 1003/3OK10.4s371 / 860
CG-AL-X046hard2100.0 / 1002/2OK10.2s1.5k / 1.4k
CG-AL-X047hard2100.0 / 1002/2OK10.1s2.0k / 4.1k
CG-AL-X050hard1100.0 / 1002/2OK10.6s405 / 1.8k
CG-AL-X051hard1100.0 / 1002/2OK10.7s509 / 855
CG-AL-X052hard1100.0 / 1003/3OK10.7s358 / 1.1k
CG-AL-X055hard1100.0 / 1005/5OK10.1s344 / 572
CG-AL-X056hard1100.0 / 1005/5OK11.4s280 / 1.4k
CG-AL-X057hard1100.0 / 1005/5OK10.0s250 / 327
CG-AL-X058hard1100.0 / 1005/5OK10.6s314 / 1.8k
CG-AL-X059hard1100.0 / 1003/3OK10.4s327 / 725
CG-AL-X060hard1100.0 / 1003/3OK10.5s302 / 627
CG-AL-X061hard1100.0 / 1004/4OK10.3s364 / 278
CG-AL-X062hard1100.0 / 1004/4OK10.1s358 / 775
CG-AL-X063hard2100.0 / 1003/3OK10.0s912 / 1.9k
CG-AL-X064hard1100.0 / 1007/7OK9.9s277 / 1.3k
CG-AL-X065hard1100.0 / 1006/6OK10.1s709 / 705
CG-AL-X066hard1100.0 / 10014/14OK10.3s1.2k / 1.3k
CG-AL-X067hard262.5 / 1006/7OK10.0s1.6k / 3.3k
CG-AL-X068hard1100.0 / 10012/12OK10.5s1.2k / 1.9k
CG-AL-X069hard1100.0 / 1008/8OK10.4s1.1k / 3.8k
CG-AL-X070hard1100.0 / 10012/12OK10.6s1.2k / 1.1k
CG-AL-X071hard1100.0 / 1008/8OK10.3s1.4k / 1.3k
CG-AL-X072hard1100.0 / 1007/7OK10.3s1.1k / 874
CG-AL-X073hard1100.0 / 1008/8OK10.6s1.4k / 1.4k
CG-AL-X074hard2100.0 / 1007/7OK10.4s3.4k / 5.7k
CG-AL-X075hard1100.0 / 1007/7OK10.2s810 / 2.0k
CG-AL-X076hard1100.0 / 10014/14OK10.4s954 / 1.7k
CG-AL-X077hard1100.0 / 10022/22OK10.1s1.5k / 1.4k
CG-AL-X078hard1100.0 / 10017/17OK10.4s1.2k / 999
CG-AL-X079hard262.5 / 10010/11OK10.2s3.4k / 8.3k
CG-AL-X080hard2100.0 / 1007/7OK10.1s2.4k / 2.5k
CG-AL-X081hard1100.0 / 1008/8OK10.8s902 / 632
CG-AL-X082hard1100.0 / 10015/15OK10.5s1.2k / 1.1k
CG-AL-X083hard1100.0 / 1009/9OK10.5s1.5k / 1.3k
CG-AL-X084hard1100.0 / 10010/10OK11.3s1.4k / 3.2k
CG-AL-X085hard1100.0 / 1007/7OK10.7s980 / 798
CG-AL-X086hard1100.0 / 1006/6OK10.5s1.4k / 2.3k
CG-AL-X087hard1100.0 / 1003/3OK10.5s1.0k / 1.0k
CG-AL-X088hard1100.0 / 1006/6OK10.3s974 / 1.2k
CG-AL-X089hard2100.0 / 10011/11OK10.4s2.5k / 6.0k
CG-AL-X090hard1100.0 / 10010/10OK10.6s889 / 1.9k
CG-AL-X091hard1100.0 / 1006/6OK10.4s569 / 409
CG-AL-X092hard1100.0 / 10015/15OK16.8s444 / 366
CG-AL-X093hard1100.0 / 10010/10OK11.6s989 / 967
CG-AL-X094hard1100.0 / 1007/7OK11.9s754 / 659
CG-AL-X095hard262.5 / 1003/5OK11.0s2.1k / 1.8k
CG-AL-X096hard1100.0 / 10049/49OK11.7s3.3k / 3.1k
CG-AL-X097hard2100.0 / 10046/46OK16.3s7.1k / 7.1k
CG-AL-X098hard1100.0 / 10029/29OK12.1s2.6k / 2.3k
CG-AL-X099hard1100.0 / 10039/39OK13.2s3.6k / 4.5k
CG-AL-X100hard1100.0 / 10035/35OK10.9s3.5k / 4.1k
CG-AL-X101hard1100.0 / 10010/10OK10.5s1.1k / 2.0k
CG-AL-X102hard2100.0 / 1008/8OK10.3s2.3k / 3.3k
CG-AL-X103hard1100.0 / 1007/7OK10.7s725 / 649
CG-AL-X104hard1100.0 / 1006/6OK10.4s1.1k / 927
CG-AL-X105hard1100.0 / 1006/6OK10.5s777 / 630
CG-AL-X106hard1100.0 / 1005/5OK10.6s878 / 1.5k
CG-AL-X107hard1100.0 / 1004/4OK10.0s805 / 700
CG-AL-X108hard1100.0 / 1006/6OK11.7s729 / 448
CG-AL-X109hard1100.0 / 1005/5OK11.5s548 / 700
CG-AL-X110hard1100.0 / 10017/17OK11.5s1.2k / 1.0k
CG-AL-X111hard1100.0 / 1008/8OK14.2s1.2k / 2.2k
CG-AL-X112hard1100.0 / 10012/12OK11.5s906 / 2.8k
CG-AL-X113hard1100.0 / 10013/13OK12.3s705 / 2.3k
CG-AL-X114hard1100.0 / 1007/7OK11.1s718 / 487
CG-AL-X115hard1100.0 / 10013/13OK10.2s478 / 698
CG-AL-X116hard1100.0 / 10017/17OK10.8s926 / 4.8k
CG-AL-X117hard1100.0 / 1008/8OK11.4s1.0k / 1.1k
CG-AL-X118hard1100.0 / 10017/17OK11.9s1.4k / 2.4k
CG-AL-X119hard1100.0 / 10015/15OK12.4s1.7k / 1.8k
CG-AL-X120hard2100.0 / 10012/12OK10.3s4.3k / 2.5k
CG-AL-X121hard1100.0 / 1006/6OK10.3s1.0k / 834
CG-AL-X122hard1100.0 / 10010/10OK10.7s1.5k / 2.0k
CG-AL-X123hard1100.0 / 1005/5OK9.9s603 / 513
CG-AL-X124hard1100.0 / 10010/10OK10.4s994 / 984
CG-AL-X125hard1100.0 / 1008/8OK10.3s1.4k / 1.6k
CG-AL-X126hard1100.0 / 10014/14OK10.4s711 / 1.8k
CG-AL-X127hard1100.0 / 1005/5OK10.3s666 / 619
CG-AL-X128hard1100.0 / 1008/8OK10.5s1.1k / 857
CG-AL-X129hard1100.0 / 10014/14OK10.6s1.2k / 1.2k
CG-AL-X130hard262.5 / 1001/5OK10.4s1.1k / 2.7k
CG-AL-X131hard1100.0 / 10013/13OK10.3s941 / 707
CG-AL-X132hard1100.0 / 10010/10OK10.3s709 / 487
CG-AL-X133hard20.0 / 1000/0FAIL3.8s3.5k / 6.3k
CG-AL-X134hard1100.0 / 1006/6OK11.1s1.2k / 2.3k
CG-AL-X135hard1100.0 / 1004/4OK10.4s866 / 696
CG-AL-X136hard1100.0 / 1007/7OK10.9s754 / 638
CG-AL-X137hard1100.0 / 1004/4OK10.4s915 / 1.2k
CG-AL-X138hard1100.0 / 1009/9OK10.6s1.4k / 2.2k
CG-AL-X139hard1100.0 / 10011/11OK10.8s1.6k / 1.6k
CG-AL-X140hard262.5 / 1004/7OK10.6s4.3k / 7.2k
CG-AL-X141hard1100.0 / 10039/39OK11.1s3.5k / 3.6k
CG-AL-X142hard2100.0 / 10048/48OK11.6s9.0k / 12k
CG-AL-X143hard1100.0 / 10035/35OK15.3s4.0k / 4.0k
CG-AL-X144hard1100.0 / 10043/43OK10.7s3.6k / 3.8k
CG-AL-X145hard1100.0 / 10032/32OK11.0s4.2k / 4.0k
CG-AL-X146hard20.0 / 1000/0FAIL8.7s4.1k / 8.8k
CG-AL-X147hard1100.0 / 1008/8OK10.2s1.3k / 1.1k
CG-AL-X148hard1100.0 / 1006/6OK10.2s1.1k / 813
CG-AL-X149hard1100.0 / 1007/7OK10.2s1.1k / 1.2k
CG-AL-X150hard1100.0 / 1009/9OK12.0s1.9k / 5.6k
CG-AL-X151hard1100.0 / 1006/6OK12.0s818 / 600
CG-AL-X152hard1100.0 / 1008/8OK12.6s1.1k / 932
CG-AL-X153hard1100.0 / 1009/9OK15.9s888 / 5.7k
CG-AL-X154hard1100.0 / 1009/9OK10.4s1.2k / 1.1k
CG-AL-X155hard1100.0 / 10011/11OK10.4s923 / 912
CG-AL-X156hard1100.0 / 1007/7OK11.8s884 / 583
CG-AL-X157hard1100.0 / 10010/10OK12.2s1.3k / 1.0k
CG-AL-X158hard1100.0 / 1007/7OK11.6s801 / 492
CG-AL-X159hard1100.0 / 1007/7OK10.6s849 / 779
CG-AL-X160hard1100.0 / 10013/13OK10.2s1.2k / 1.6k
CG-AL-X161hard2100.0 / 10010/10OK10.4s3.3k / 3.1k
CG-AL-X162hard1100.0 / 1007/7OK11.2s956 / 803
CG-AL-X163hard1100.0 / 1007/7OK10.0s1.0k / 818
CG-AL-X164hard2100.0 / 1007/7OK10.6s2.0k / 1.9k
CG-AL-X165hard20.0 / 1000/0FAIL3.9s5.4k / 11k
CG-AL-X166hard2100.0 / 10014/14OK11.4s3.9k / 2.9k
CG-AL-X167hard1100.0 / 10013/13OK12.3s1.4k / 6.0k
CG-AL-X168hard1100.0 / 1009/9OK10.9s1.3k / 4.9k
CG-AL-X169hard262.5 / 10010/11OK11.4s3.9k / 5.0k
CG-AL-X170hard1100.0 / 10011/11OK10.8s3.1k / 5.1k
CG-AL-X171hard1100.0 / 1009/9OK10.0s1.4k / 4.0k
CG-AL-X172hard1100.0 / 10011/11OK11.4s2.2k / 5.2k
CG-AL-X173hard2100.0 / 10019/19OK11.4s7.5k / 9.9k
CG-AL-X174hard1100.0 / 10016/16OK11.9s3.9k / 7.1k
CG-AL-X185hard262.5 / 10041/43OK11.0s6.9k / 3.7k
CG-AL-X187hard2100.0 / 10033/33OK11.1s7.5k / 5.4k
CG-AL-X194hard262.5 / 10049/50OK11.6s10k / 6.6k
CG-AL-X211hard262.5 / 10038/43OK12.3s7.8k / 6.1k
CG-AL-X214hard262.5 / 10031/34OK12.4s9.9k / 7.1k
CG-AL-X218hard262.5 / 10024/27OK11.1s9.8k / 5.1k
CG-AL-X234hard2100.0 / 10035/35OK11.1s11k / 7.5k
CG-AL-X239hard262.5 / 10033/37OK11.4s12k / 7.3k
CG-AL-X244hard2100.0 / 10038/38OK10.8s12k / 9.2k
CG-AL-X245hard262.5 / 10059/63OK11.8s8.6k / 4.9k
CG-AL-X248hard2100.0 / 10066/66OK11.2s9.7k / 4.3k
CG-AL-X249hard2100.0 / 10037/37OK10.9s9.7k / 6.4k
CG-AL-X254hard262.5 / 10060/70OK11.2s12k / 7.0k
CG-AL-X257hard262.5 / 10052/53OK11.7s9.3k / 9.3k
CG-AL-X263hard2100.0 / 10061/61OK11.1s11k / 9.3k
CG-AL-X264hard262.5 / 10062/65OK11.6s12k / 8.7k
CG-AL-X270hard2100.0 / 10063/63OK11.5s16k / 7.2k
CG-AL-X271hard262.5 / 10069/70OK11.8s19k / 15k
CG-AL-X272hard2100.0 / 10079/79OK11.4s13k / 6.5k
CG-AL-X274hard20.0 / 1000/0FAIL3.5s15k / 8.1k
CG-AL-X276hard2100.0 / 10078/78OK11.7s15k / 8.4k
CG-AL-X278hard262.5 / 10068/71OK12.9s14k / 8.2k
CG-AL-X283hard2100.0 / 10076/76OK12.9s15k / 8.3k
CG-AL-X289hard262.5 / 10053/57OK11.4s10k / 9.0k
CG-AL-X290hard2100.0 / 10047/47OK11.8s12k / 6.0k
CG-AL-X292hard2100.0 / 10057/57OK12.8s11k / 3.7k
CG-AL-X293hard2100.0 / 10049/49OK13.2s10k / 5.1k
CG-AL-X296hard2100.0 / 10047/47OK12.3s15k / 11k
CG-AL-X298hard262.5 / 10054/55OK10.8s15k / 10k