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.

77.2% 179/232 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.

70.4 / 100
Cost $0.93
Tokens 680k / 663k input / output, all attempts
Duration 57m 9s
Filter:
Per-task results for run f45b64cf-a915-4b44-9a8b-a8a62fb26456
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK16.0s258 / 634
CG-AL-E006easy1100.0 / 1007/7OK29.3s305 / 797
CG-AL-E010easy1100.0 / 1005/5OK16.4s280 / 327
CG-AL-E050easy20.0 / 1000/0FAIL8.6s1.8k / 2.4k
CG-AL-E052easy2100.0 / 10016/16OK16.3s987 / 748
CG-AL-E054easy1100.0 / 1009/9OK10.6s372 / 1.2k
CG-AL-E056easy2100.0 / 10015/15OK15.9s1.7k / 2.0k
CG-AL-H007hard1100.0 / 10011/11OK10.9s545 / 2.0k
CG-AL-H011hard20.0 / 1000/0FAIL3.7s1.1k / 2.7k
CG-AL-H014hard20.0 / 1000/0FAIL4.0s1.4k / 2.2k
CG-AL-H017hard20.0 / 1000/0FAIL3.5s950 / 4.0k
CG-AL-H020hard2100.0 / 10010/10OK16.0s1.7k / 2.7k
CG-AL-H021hard262.5 / 1006/20OK11.0s1.9k / 1.9k
CG-AL-H023hard20.0 / 1000/0FAIL4.2s5.9k / 8.6k
CG-AL-H027hard262.5 / 1002/4OK10.9s2.1k / 1.8k
CG-AL-H029hard20.0 / 1000/0FAIL4.1s2.7k / 5.8k
CG-AL-H030hard20.0 / 1000/0FAIL4.0s2.2k / 4.5k
CG-AL-H031hard1100.0 / 10022/22OK11.1s939 / 2.9k
CG-AL-H034hard2100.0 / 1003/3OK11.9s1.6k / 1.9k
CG-AL-H036hard20.0 / 1000/0FAIL3.8s1.0k / 3.5k
CG-AL-H037hard10.0 / 1000/0FAIL4.6s497 / 1.2k
CG-AL-H041hard1100.0 / 1003/3OK11.1s565 / 2.4k
CG-AL-H050hard262.5 / 1002/3OK11.0s1.4k / 2.9k
CG-AL-H054hard2100.0 / 1005/5OK10.5s1.9k / 1.8k
CG-AL-H056hard20.0 / 1000/0FAIL4.0s1.4k / 2.3k
CG-AL-M001medium20.0 / 1000/0FAIL4.2s1.6k / 2.3k
CG-AL-M003medium262.5 / 1000/1OK25.5s1.4k / 4.2k
CG-AL-M004medium1100.0 / 10012/12OK28.7s449 / 2.3k
CG-AL-M006medium262.5 / 10015/18OK11.5s2.0k / 6.8k
CG-AL-M007medium20.0 / 1000/0FAIL4.1s3.5k / 7.2k
CG-AL-M008medium262.5 / 1004/12OK11.6s3.3k / 7.7k
CG-AL-M009medium2100.0 / 10011/11OK10.7s3.9k / 7.7k
CG-AL-M010medium2100.0 / 10021/21OK24.1s2.9k / 5.6k
CG-AL-M020medium2100.0 / 10017/17OK10.7s1.9k / 1.9k
CG-AL-M023medium2100.0 / 10011/11OK11.1s1.4k / 2.3k
CG-AL-M025medium2100.0 / 1008/8OK11.1s2.8k / 2.6k
CG-AL-M026medium1100.0 / 1008/8OK10.8s370 / 1.8k
CG-AL-M027medium2100.0 / 10018/18OK10.8s3.7k / 4.5k
CG-AL-M028medium2100.0 / 1003/3OK23.9s1.0k / 1.8k
CG-AL-M031medium2100.0 / 1002/2OK10.7s1.9k / 2.5k
CG-AL-M034medium1100.0 / 1002/2OK11.4s415 / 1.2k
CG-AL-M036medium211.1 / 1000/0FAIL4.0s1.5k / 2.3k
CG-AL-M040medium20.0 / 1000/0FAIL3.9s796 / 2.6k
CG-AL-M042medium1100.0 / 1008/8OK10.6s498 / 704
CG-AL-X001hard1100.0 / 1002/2OK10.8s308 / 984
CG-AL-X002hard262.5 / 1000/4OK11.4s1.4k / 4.4k
CG-AL-X003hard20.0 / 1000/0FAIL4.3s660 / 4.7k
CG-AL-X004medium1100.0 / 1003/3OK10.6s358 / 1.2k
CG-AL-X005hard2100.0 / 1002/2OK11.2s906 / 1.1k
CG-AL-X006hard1100.0 / 1003/3OK10.9s383 / 1.3k
CG-AL-X007hard1100.0 / 1002/2OK1m 33s372 / 693
CG-AL-X008hard1100.0 / 1001/1OK11.0s417 / 2.0k
CG-AL-X009medium1100.0 / 1002/2OK10.8s313 / 517
CG-AL-X010medium1100.0 / 1003/3OK11.0s284 / 337
CG-AL-X011medium1100.0 / 1002/2OK10.7s360 / 642
CG-AL-X012hard1100.0 / 1001/1OK10.9s380 / 2.4k
CG-AL-X013hard1100.0 / 1002/2OK10.3s263 / 279
CG-AL-X014medium1100.0 / 1004/4OK10.7s291 / 282
CG-AL-X017medium2100.0 / 1003/3OK10.5s1.4k / 725
CG-AL-X018medium1100.0 / 1003/3OK10.8s384 / 1.2k
CG-AL-X019medium2100.0 / 1003/3OK11.0s1.8k / 1.4k
CG-AL-X022medium2100.0 / 1003/3OK10.8s1.3k / 2.0k
CG-AL-X024medium1100.0 / 1003/3OK10.6s333 / 1.4k
CG-AL-X025medium1100.0 / 1001/1OK11.0s371 / 801
CG-AL-X026medium1100.0 / 1003/3OK10.9s327 / 399
CG-AL-X027medium1100.0 / 1004/4OK11.8s258 / 682
CG-AL-X029medium1100.0 / 1002/2OK11.6s276 / 2.2k
CG-AL-X030medium1100.0 / 1002/2OK10.8s239 / 388
CG-AL-X031medium1100.0 / 1003/3OK10.9s297 / 460
CG-AL-X033hard1100.0 / 1002/2OK10.6s348 / 318
CG-AL-X034hard1100.0 / 1003/3OK10.9s304 / 1.5k
CG-AL-X035hard1100.0 / 1003/3OK11.4s331 / 620
CG-AL-X037hard20.0 / 1000/0FAIL3.9s1.1k / 3.0k
CG-AL-X040hard20.0 / 1000/0FAIL4.2s1.5k / 3.5k
CG-AL-X041hard20.0 / 1000/0FAIL3.9s1.2k / 3.0k
CG-AL-X043hard2100.0 / 1001/1OK11.2s1.3k / 3.7k
CG-AL-X044hard262.5 / 1001/3OK10.8s958 / 2.8k
CG-AL-X045hard1100.0 / 1003/3OK10.9s371 / 580
CG-AL-X046hard1100.0 / 1002/2OK11.0s369 / 1.7k
CG-AL-X047hard262.5 / 1000/2OK11.0s1.4k / 5.2k
CG-AL-X050hard1100.0 / 1002/2OK11.1s405 / 736
CG-AL-X051hard1100.0 / 1002/2OK10.9s509 / 3.4k
CG-AL-X052hard1100.0 / 1003/3OK10.5s358 / 630
CG-AL-X055hard1100.0 / 1005/5OK10.5s344 / 536
CG-AL-X056hard2100.0 / 1005/5OK10.8s820 / 2.5k
CG-AL-X057hard1100.0 / 1005/5OK10.4s250 / 355
CG-AL-X058hard1100.0 / 1005/5OK10.8s314 / 1.2k
CG-AL-X059hard1100.0 / 1003/3OK10.7s327 / 322
CG-AL-X060hard1100.0 / 1003/3OK10.7s302 / 604
CG-AL-X061hard1100.0 / 1004/4OK10.8s364 / 403
CG-AL-X062hard1100.0 / 1004/4OK10.6s358 / 1.3k
CG-AL-X063hard2100.0 / 1003/3OK10.8s877 / 1.8k
CG-AL-X064hard1100.0 / 1007/7OK10.5s277 / 683
CG-AL-X065hard1100.0 / 1006/6OK10.6s709 / 665
CG-AL-X066hard1100.0 / 10014/14OK10.8s1.2k / 1.3k
CG-AL-X067hard262.5 / 1006/7OK10.2s1.7k / 4.7k
CG-AL-X068hard1100.0 / 10012/12OK10.8s1.2k / 2.4k
CG-AL-X069hard1100.0 / 1008/8OK11.2s1.1k / 3.2k
CG-AL-X070hard1100.0 / 10012/12OK10.7s1.2k / 1.8k
CG-AL-X071hard1100.0 / 1008/8OK11.2s1.4k / 1.3k
CG-AL-X072hard1100.0 / 1007/7OK10.4s1.1k / 883
CG-AL-X073hard1100.0 / 1008/8OK10.8s1.4k / 1.7k
CG-AL-X074hard262.5 / 1006/7OK10.8s3.7k / 5.9k
CG-AL-X075hard1100.0 / 1007/7OK10.5s810 / 2.1k
CG-AL-X076hard1100.0 / 10014/14OK10.9s954 / 2.7k
CG-AL-X077hard1100.0 / 10022/22OK11.2s1.5k / 1.4k
CG-AL-X078hard1100.0 / 10017/17OK10.7s1.2k / 986
CG-AL-X079hard262.5 / 10010/11OK10.9s3.3k / 7.3k
CG-AL-X080hard262.5 / 1006/7OK10.8s2.4k / 3.0k
CG-AL-X081hard1100.0 / 1008/8OK10.7s902 / 645
CG-AL-X082hard1100.0 / 10015/15OK10.6s1.2k / 993
CG-AL-X083hard1100.0 / 1009/9OK10.4s1.5k / 1.3k
CG-AL-X084hard1100.0 / 10010/10OK11.1s1.4k / 3.6k
CG-AL-X085hard1100.0 / 1007/7OK10.6s980 / 1.1k
CG-AL-X086hard1100.0 / 1006/6OK10.6s1.4k / 2.4k
CG-AL-X087hard1100.0 / 1003/3OK10.6s1.0k / 933
CG-AL-X088hard1100.0 / 1006/6OK10.7s974 / 1.2k
CG-AL-X089hard1100.0 / 10011/11OK10.8s1.1k / 3.7k
CG-AL-X090hard1100.0 / 10010/10OK11.1s889 / 2.7k
CG-AL-X091hard1100.0 / 1006/6OK10.6s569 / 401
CG-AL-X092hard1100.0 / 10015/15OK10.5s444 / 611
CG-AL-X093hard1100.0 / 10010/10OK10.9s989 / 1.2k
CG-AL-X094hard1100.0 / 1007/7OK10.6s754 / 750
CG-AL-X095hard1100.0 / 1005/5OK10.7s797 / 1.1k
CG-AL-X096hard1100.0 / 10049/49OK11.1s3.3k / 3.0k
CG-AL-X097hard1100.0 / 10046/46OK11.5s3.4k / 3.2k
CG-AL-X098hard1100.0 / 10029/29OK11.2s2.6k / 2.4k
CG-AL-X099hard1100.0 / 10039/39OK12.6s3.6k / 4.8k
CG-AL-X100hard1100.0 / 10035/35OK11.0s3.5k / 3.5k
CG-AL-X101hard1100.0 / 10010/10OK10.6s1.1k / 2.4k
CG-AL-X102hard2100.0 / 1008/8OK10.7s2.3k / 3.2k
CG-AL-X103hard1100.0 / 1007/7OK10.6s725 / 626
CG-AL-X104hard1100.0 / 1006/6OK10.7s1.1k / 950
CG-AL-X105hard1100.0 / 1006/6OK10.6s777 / 635
CG-AL-X106hard1100.0 / 1005/5OK10.9s878 / 884
CG-AL-X107hard1100.0 / 1004/4OK11.4s805 / 760
CG-AL-X108hard1100.0 / 1006/6OK11.5s729 / 605
CG-AL-X109hard1100.0 / 1005/5OK10.7s548 / 781
CG-AL-X110hard1100.0 / 10017/17OK10.9s1.2k / 1.0k
CG-AL-X111hard1100.0 / 1008/8OK10.8s1.2k / 2.4k
CG-AL-X112hard1100.0 / 10012/12OK10.6s906 / 2.0k
CG-AL-X113hard1100.0 / 10013/13OK11.0s705 / 922
CG-AL-X114hard1100.0 / 1007/7OK10.8s718 / 525
CG-AL-X115hard1100.0 / 10013/13OK11.0s478 / 705
CG-AL-X116hard262.5 / 10015/17OK10.6s2.0k / 4.0k
CG-AL-X117hard1100.0 / 1008/8OK10.8s1.0k / 1.1k
CG-AL-X118hard2100.0 / 10017/17OK10.9s3.2k / 4.1k
CG-AL-X119hard1100.0 / 10015/15OK11.1s1.7k / 1.7k
CG-AL-X120hard2100.0 / 10012/12OK10.5s4.3k / 2.3k
CG-AL-X121hard1100.0 / 1006/6OK10.5s1.0k / 908
CG-AL-X122hard1100.0 / 10010/10OK10.7s1.5k / 2.0k
CG-AL-X123hard1100.0 / 1005/5OK10.6s603 / 759
CG-AL-X124hard1100.0 / 10010/10OK10.9s994 / 1.0k
CG-AL-X125hard1100.0 / 1008/8OK11.0s1.4k / 1.7k
CG-AL-X126hard1100.0 / 10014/14OK10.5s711 / 1.3k
CG-AL-X127hard1100.0 / 1005/5OK10.6s666 / 487
CG-AL-X128hard1100.0 / 1008/8OK11.2s1.1k / 850
CG-AL-X129hard1100.0 / 10014/14OK10.8s1.2k / 1.3k
CG-AL-X130hard1100.0 / 1005/5OK10.6s529 / 1.8k
CG-AL-X131hard1100.0 / 10013/13OK10.7s941 / 804
CG-AL-X132hard1100.0 / 10010/10OK10.5s709 / 447
CG-AL-X133hard262.5 / 1007/8OK11.1s3.4k / 6.3k
CG-AL-X134hard1100.0 / 1006/6OK11.1s1.2k / 1.7k
CG-AL-X135hard1100.0 / 1004/4OK10.9s866 / 617
CG-AL-X136hard1100.0 / 1007/7OK10.8s754 / 450
CG-AL-X137hard1100.0 / 1004/4OK11.2s915 / 1.5k
CG-AL-X138hard1100.0 / 1009/9OK12.5s1.4k / 3.1k
CG-AL-X139hard1100.0 / 10011/11OK12.0s1.6k / 1.5k
CG-AL-X140hard2100.0 / 1007/7OK10.8s4.1k / 7.5k
CG-AL-X141hard1100.0 / 10039/39OK11.5s3.5k / 3.1k
CG-AL-X142hard2100.0 / 10048/48OK12.2s9.1k / 10k
CG-AL-X143hard262.5 / 10033/35OK16.0s8.1k / 7.7k
CG-AL-X144hard1100.0 / 10043/43OK11.8s3.6k / 3.2k
CG-AL-X145hard1100.0 / 10032/32OK11.6s4.2k / 3.9k
CG-AL-X146hard1100.0 / 1009/9OK11.2s1.7k / 3.5k
CG-AL-X147hard1100.0 / 1008/8OK10.9s1.3k / 1.1k
CG-AL-X148hard1100.0 / 1006/6OK10.9s1.1k / 854
CG-AL-X149hard1100.0 / 1007/7OK12.1s1.1k / 1.0k
CG-AL-X150hard262.5 / 1008/9OK11.4s4.8k / 7.3k
CG-AL-X151hard1100.0 / 1006/6OK10.5s818 / 611
CG-AL-X152hard1100.0 / 1008/8OK10.8s1.1k / 1.1k
CG-AL-X153hard2100.0 / 1009/9OK15.1s2.5k / 5.2k
CG-AL-X154hard1100.0 / 1009/9OK11.3s1.2k / 1.1k
CG-AL-X155hard1100.0 / 10011/11OK11.2s923 / 1.6k
CG-AL-X156hard1100.0 / 1007/7OK10.8s884 / 568
CG-AL-X157hard1100.0 / 10010/10OK10.7s1.3k / 1.1k
CG-AL-X158hard1100.0 / 1007/7OK10.9s801 / 505
CG-AL-X159hard1100.0 / 1007/7OK11.2s849 / 776
CG-AL-X160hard1100.0 / 10013/13OK10.9s1.2k / 2.1k
CG-AL-X161hard1100.0 / 10010/10OK11.6s1.4k / 1.4k
CG-AL-X162hard1100.0 / 1007/7OK11.0s956 / 780
CG-AL-X163hard1100.0 / 1007/7OK10.3s1.0k / 979
CG-AL-X164hard262.5 / 1003/7OK10.7s2.0k / 3.1k
CG-AL-X165hard20.0 / 1000/0FAIL3.7s6.1k / 7.6k
CG-AL-X166hard2100.0 / 10014/14OK12.0s3.8k / 3.0k
CG-AL-X167hard2100.0 / 10013/13OK11.5s3.6k / 6.4k
CG-AL-X168hard20.0 / 1000/0FAIL3.9s4.7k / 6.4k
CG-AL-X169hard2100.0 / 10011/11OK11.6s3.9k / 5.3k
CG-AL-X170hard1100.0 / 10011/11OK11.3s3.1k / 4.9k
CG-AL-X171hard2100.0 / 1009/9OK10.7s4.4k / 6.4k
CG-AL-X172hard20.0 / 1000/0FAIL3.8s7.2k / 8.4k
CG-AL-X173hard2100.0 / 10019/19OK11.9s6.7k / 8.1k
CG-AL-X174hard1100.0 / 10016/16OK11.8s3.9k / 5.1k
CG-AL-X185hard262.5 / 10041/43OK11.2s6.9k / 3.5k
CG-AL-X187hard2100.0 / 10033/33OK11.7s7.5k / 6.5k
CG-AL-X194hard2100.0 / 10050/50OK11.3s10k / 6.2k
CG-AL-X211hard2100.0 / 10043/43OK12.4s9.2k / 5.1k
CG-AL-X214hard2100.0 / 10034/34OK12.6s8.0k / 5.7k
CG-AL-X218hard20.0 / 1000/0FAIL4.1s8.8k / 4.7k
CG-AL-X234hard2100.0 / 10035/35OK12.6s9.1k / 4.6k
CG-AL-X239hard2100.0 / 10037/37OK11.9s11k / 5.7k
CG-AL-X244hard262.5 / 10035/38OK12.4s11k / 7.0k
CG-AL-X245hard262.5 / 10061/63OK11.6s15k / 6.9k
CG-AL-X248hard262.5 / 10050/66OK12.0s11k / 5.3k
CG-AL-X249hard2100.0 / 10037/37OK11.8s9.6k / 6.4k
CG-AL-X254hard262.5 / 10064/70OK11.9s18k / 6.4k
CG-AL-X257hard262.5 / 10052/53OK11.8s11k / 7.4k
CG-AL-X263hard2100.0 / 10061/61OK11.9s16k / 8.1k
CG-AL-X264hard262.5 / 10062/65OK11.7s12k / 7.0k
CG-AL-X270hard262.5 / 10060/63OK12.3s18k / 6.7k
CG-AL-X271hard262.5 / 10063/70OK12.5s17k / 11k
CG-AL-X272hard2100.0 / 10079/79OK12.0s14k / 6.7k
CG-AL-X274hard20.0 / 1000/0FAIL4.0s18k / 6.2k
CG-AL-X276hard2100.0 / 10078/78OK12.7s16k / 7.7k
CG-AL-X278hard2100.0 / 10071/71OK12.6s15k / 6.7k
CG-AL-X283hard2100.0 / 10076/76OK12.7s16k / 7.8k
CG-AL-X289hard20.0 / 1000/0FAIL4.0s15k / 8.6k
CG-AL-X290hard2100.0 / 10047/47OK11.7s12k / 4.5k
CG-AL-X292hard2100.0 / 10057/57OK12.2s14k / 3.8k
CG-AL-X293hard2100.0 / 10049/49OK11.9s12k / 6.2k
CG-AL-X296hard262.5 / 10046/47OK12.1s17k / 6.3k
CG-AL-X298hard262.5 / 10052/55OK11.7s15k / 7.3k