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.

97.8% 227/232 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.

89.4 / 100
Cost $17.89
Tokens 881k / 718k input / output, all attempts
Duration 49m 59s
Filter:
Per-task results for run 2ce1b33d-3d53-4724-a266-141f84869b51
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK16.7s415 / 563
CG-AL-E006easy1100.0 / 1007/7OK29.9s496 / 712
CG-AL-E010easy262.5 / 1000/1OK28.8s1.3k / 939
CG-AL-E050easy1100.0 / 10013/13OK10.2s632 / 656
CG-AL-E052easy1100.0 / 10016/16OK10.0s612 / 437
CG-AL-E054easy2100.0 / 1009/9OK15.5s1.8k / 1.3k
CG-AL-E056easy2100.0 / 10015/15OK15.4s2.8k / 1.1k
CG-AL-H007hard1100.0 / 10011/11OK9.8s949 / 2.0k
CG-AL-H011hard2100.0 / 1006/6OK9.9s1.6k / 1.4k
CG-AL-H014hard1100.0 / 1007/7OK9.4s729 / 1.8k
CG-AL-H017hard1100.0 / 1005/5OK9.6s612 / 815
CG-AL-H020hard1100.0 / 10010/10OK9.6s783 / 1.9k
CG-AL-H021hard2100.0 / 10020/20OK10.1s30k / 3.0k
CG-AL-H023hard2100.0 / 10025/25OK10.8s14k / 29k
CG-AL-H027hard1100.0 / 1004/4OK10.1s1.1k / 1.1k
CG-AL-H029hard1100.0 / 10018/18OK11.0s1.3k / 2.7k
CG-AL-H030hard1100.0 / 10010/10OK11.4s1.1k / 2.1k
CG-AL-H031hard1100.0 / 10022/22OK11.2s1.6k / 2.3k
CG-AL-H034hard1100.0 / 1003/3OK10.2s722 / 1.1k
CG-AL-H036hard1100.0 / 1005/5OK10.1s640 / 1.3k
CG-AL-H037hard1100.0 / 1003/3OK9.8s807 / 621
CG-AL-H041hard1100.0 / 1003/3OK10.0s925 / 2.3k
CG-AL-H050hard1100.0 / 1003/3OK10.0s815 / 1.2k
CG-AL-H054hard2100.0 / 1005/5OK9.9s3.1k / 2.0k
CG-AL-H056hard2100.0 / 1004/4OK9.6s2.4k / 1.0k
CG-AL-M001medium2100.0 / 10010/10OK21.0s2.4k / 2.9k
CG-AL-M003medium2100.0 / 1009/9OK10.4s3.1k / 4.9k
CG-AL-M004medium1100.0 / 10012/12OK27.9s775 / 3.2k
CG-AL-M006medium1100.0 / 10018/18OK10.4s707 / 5.7k
CG-AL-M007medium262.5 / 10013/15OK10.5s7.2k / 12k
CG-AL-M008medium2100.0 / 10012/12OK10.8s18k / 34k
CG-AL-M009medium1100.0 / 10011/11OK10.2s748 / 14k
CG-AL-M010medium1100.0 / 10021/21OK23.5s960 / 5.5k
CG-AL-M020medium1100.0 / 10017/17OK10.9s885 / 2.6k
CG-AL-M023medium1100.0 / 10011/11OK11.4s805 / 973
CG-AL-M025medium1100.0 / 1008/8OK10.2s657 / 1.3k
CG-AL-M026medium1100.0 / 1008/8OK9.8s626 / 1.1k
CG-AL-M027medium1100.0 / 10018/18OK9.9s1.4k / 3.0k
CG-AL-M028medium2100.0 / 1003/3OK22.3s1.8k / 1.6k
CG-AL-M031medium1100.0 / 1002/2OK10.5s1.2k / 1.4k
CG-AL-M034medium1100.0 / 1002/2OK10.1s697 / 825
CG-AL-M036medium1100.0 / 1002/2OK10.8s912 / 875
CG-AL-M040medium1100.0 / 1002/2OK10.0s502 / 619
CG-AL-M042medium1100.0 / 1008/8OK9.7s755 / 389
CG-AL-X001hard1100.0 / 1002/2OK9.7s501 / 303
CG-AL-X002hard1100.0 / 1004/4OK9.9s730 / 1.4k
CG-AL-X003hard2100.0 / 1003/3OK9.6s1.4k / 2.4k
CG-AL-X004medium1100.0 / 1003/3OK9.6s553 / 1.0k
CG-AL-X005hard1100.0 / 1002/2OK9.7s517 / 617
CG-AL-X006hard1100.0 / 1003/3OK10.0s605 / 1.1k
CG-AL-X007hard1100.0 / 1002/2OK1m 37s577 / 955
CG-AL-X008hard20.0 / 1000/0FAIL0ms1.3k / 0
CG-AL-X009medium1100.0 / 1002/2OK9.8s495 / 823
CG-AL-X010medium1100.0 / 1003/3OK9.9s451 / 352
CG-AL-X011medium1100.0 / 1002/2OK9.5s559 / 383
CG-AL-X012hard1100.0 / 1001/1OK10.1s591 / 498
CG-AL-X013hard1100.0 / 1002/2OK11.0s425 / 164
CG-AL-X014medium1100.0 / 1004/4OK10.0s460 / 347
CG-AL-X017medium2100.0 / 1003/3OK9.2s2.4k / 493
CG-AL-X018medium1100.0 / 1003/3OK9.8s608 / 770
CG-AL-X019medium2100.0 / 1003/3OK9.5s3.1k / 1.4k
CG-AL-X022medium1100.0 / 1003/3OK9.7s443 / 772
CG-AL-X024medium1100.0 / 1003/3OK16.7s543 / 1.0k
CG-AL-X025medium1100.0 / 1001/1OK9.8s603 / 779
CG-AL-X026medium1100.0 / 1003/3OK9.5s526 / 430
CG-AL-X027medium1100.0 / 1004/4OK9.7s426 / 412
CG-AL-X029medium2100.0 / 1002/2OK9.8s848 / 778
CG-AL-X030medium1100.0 / 1002/2OK9.6s410 / 340
CG-AL-X031medium1100.0 / 1003/3OK9.5s467 / 508
CG-AL-X033hard1100.0 / 1002/2OK9.7s560 / 276
CG-AL-X034hard1100.0 / 1003/3OK11.0s488 / 618
CG-AL-X035hard2100.0 / 1003/3OK9.9s1.0k / 757
CG-AL-X037hard1100.0 / 1004/4OK9.9s648 / 2.4k
CG-AL-X040hard1100.0 / 1004/4OK10.1s891 / 1.8k
CG-AL-X041hard2100.0 / 1005/5OK10.0s1.4k / 1.8k
CG-AL-X043hard2100.0 / 1001/1OK11.4s2.3k / 3.8k
CG-AL-X044hard2100.0 / 1003/3OK10.2s2.9k / 6.3k
CG-AL-X045hard1100.0 / 1003/3OK10.1s604 / 310
CG-AL-X046hard1100.0 / 1002/2OK9.8s571 / 605
CG-AL-X047hard1100.0 / 1002/2OK10.1s652 / 2.0k
CG-AL-X050hard1100.0 / 1002/2OK9.8s660 / 1.1k
CG-AL-X051hard1100.0 / 1002/2OK9.8s802 / 891
CG-AL-X052hard1100.0 / 1003/3OK9.7s584 / 817
CG-AL-X055hard1100.0 / 1005/5OK9.8s548 / 498
CG-AL-X056hard1100.0 / 1005/5OK9.9s449 / 635
CG-AL-X057hard1100.0 / 1005/5OK12.7s413 / 162
CG-AL-X058hard1100.0 / 1005/5OK9.8s502 / 1.3k
CG-AL-X059hard1100.0 / 1003/3OK9.7s513 / 110
CG-AL-X060hard1100.0 / 1003/3OK9.9s489 / 222
CG-AL-X061hard1100.0 / 1004/4OK9.9s574 / 159
CG-AL-X062hard1100.0 / 1004/4OK9.9s603 / 654
CG-AL-X063hard1100.0 / 1003/3OK9.7s561 / 585
CG-AL-X064hard1100.0 / 1007/7OK9.8s459 / 1.1k
CG-AL-X065hard1100.0 / 1006/6OK9.6s1.2k / 1.2k
CG-AL-X066hard1100.0 / 10014/14OK9.7s2.2k / 2.0k
CG-AL-X067hard1100.0 / 1007/7OK9.6s1.0k / 752
CG-AL-X068hard1100.0 / 10012/12OK9.7s2.0k / 1.7k
CG-AL-X069hard1100.0 / 1008/8OK10.2s1.9k / 3.0k
CG-AL-X070hard1100.0 / 10012/12OK9.7s1.9k / 1.7k
CG-AL-X071hard1100.0 / 1008/8OK9.5s2.3k / 2.0k
CG-AL-X072hard1100.0 / 1007/7OK9.5s2.1k / 1.9k
CG-AL-X073hard1100.0 / 1008/8OK9.7s2.5k / 2.7k
CG-AL-X074hard2100.0 / 1007/7OK9.5s5.9k / 6.2k
CG-AL-X075hard1100.0 / 1007/7OK9.5s1.4k / 1.3k
CG-AL-X076hard1100.0 / 10014/14OK9.8s1.6k / 1.3k
CG-AL-X077hard1100.0 / 10022/22OK9.6s2.6k / 2.2k
CG-AL-X078hard1100.0 / 10017/17OK9.7s2.0k / 1.5k
CG-AL-X079hard1100.0 / 10011/11OK9.8s2.0k / 2.2k
CG-AL-X080hard2100.0 / 1007/7OK10.0s4.3k / 3.4k
CG-AL-X081hard1100.0 / 1008/8OK9.6s1.5k / 1.0k
CG-AL-X082hard2100.0 / 10015/15OK10.4s5.7k / 3.7k
CG-AL-X083hard1100.0 / 1009/9OK9.6s2.8k / 2.3k
CG-AL-X084hard1100.0 / 10010/10OK10.1s2.5k / 2.5k
CG-AL-X085hard1100.0 / 1007/7OK9.7s1.6k / 1.2k
CG-AL-X086hard1100.0 / 1006/6OK9.6s2.4k / 2.3k
CG-AL-X087hard1100.0 / 1003/3OK9.5s1.8k / 1.6k
CG-AL-X088hard1100.0 / 1006/6OK10.1s1.7k / 1.6k
CG-AL-X089hard2100.0 / 10011/11OK10.2s4.2k / 4.6k
CG-AL-X090hard1100.0 / 10010/10OK9.7s1.5k / 2.0k
CG-AL-X091hard1100.0 / 1006/6OK9.4s943 / 513
CG-AL-X092hard1100.0 / 10015/15OK10.1s718 / 281
CG-AL-X093hard1100.0 / 10010/10OK9.5s1.7k / 1.3k
CG-AL-X094hard1100.0 / 1007/7OK9.4s1.3k / 936
CG-AL-X095hard2100.0 / 1005/5OK9.6s3.6k / 3.2k
CG-AL-X096hard1100.0 / 10049/49OK10.1s6.0k / 5.6k
CG-AL-X097hard1100.0 / 10046/46OK10.8s6.1k / 5.5k
CG-AL-X098hard1100.0 / 10029/29OK10.1s4.8k / 4.0k
CG-AL-X099hard1100.0 / 10039/39OK11.4s6.4k / 6.8k
CG-AL-X100hard1100.0 / 10035/35OK10.5s6.0k / 5.7k
CG-AL-X101hard1100.0 / 10010/10OK9.8s1.9k / 1.7k
CG-AL-X102hard1100.0 / 1008/8OK9.5s886 / 1.4k
CG-AL-X103hard1100.0 / 1007/7OK9.4s1.2k / 804
CG-AL-X104hard1100.0 / 1006/6OK9.7s1.7k / 1.4k
CG-AL-X105hard1100.0 / 1006/6OK9.9s1.3k / 807
CG-AL-X106hard1100.0 / 1005/5OK9.8s1.5k / 1.7k
CG-AL-X107hard1100.0 / 1004/4OK9.5s1.4k / 1.1k
CG-AL-X108hard1100.0 / 1006/6OK10.6s1.2k / 1.8k
CG-AL-X109hard1100.0 / 1005/5OK9.7s918 / 677
CG-AL-X110hard1100.0 / 10017/17OK10.3s2.1k / 1.7k
CG-AL-X111hard1100.0 / 1008/8OK10.0s2.0k / 2.4k
CG-AL-X112hard1100.0 / 10012/12OK9.6s1.5k / 1.8k
CG-AL-X113hard1100.0 / 10013/13OK9.9s1.3k / 1.0k
CG-AL-X114hard1100.0 / 1007/7OK9.7s1.2k / 826
CG-AL-X115hard1100.0 / 10013/13OK9.4s795 / 742
CG-AL-X116hard1100.0 / 10017/17OK9.7s1.5k / 1.3k
CG-AL-X117hard1100.0 / 1008/8OK9.8s1.7k / 1.8k
CG-AL-X118hard1100.0 / 10017/17OK9.8s2.4k / 2.1k
CG-AL-X119hard1100.0 / 10015/15OK10.0s2.8k / 2.6k
CG-AL-X120hard1100.0 / 10012/12OK10.0s2.2k / 1.9k
CG-AL-X121hard1100.0 / 1006/6OK9.7s1.7k / 1.3k
CG-AL-X122hard1100.0 / 10010/10OK11.6s2.6k / 2.4k
CG-AL-X123hard1100.0 / 1005/5OK12.0s983 / 747
CG-AL-X124hard1100.0 / 10010/10OK10.1s1.7k / 1.4k
CG-AL-X125hard1100.0 / 1008/8OK9.7s2.3k / 2.4k
CG-AL-X126hard1100.0 / 10014/14OK9.7s1.2k / 935
CG-AL-X127hard1100.0 / 1005/5OK9.5s1.1k / 641
CG-AL-X128hard1100.0 / 1008/8OK10.2s2.0k / 1.5k
CG-AL-X129hard1100.0 / 10014/14OK10.0s2.0k / 1.8k
CG-AL-X130hard1100.0 / 1005/5OK9.5s847 / 627
CG-AL-X131hard1100.0 / 10013/13OK9.7s1.6k / 1.3k
CG-AL-X132hard1100.0 / 10010/10OK9.8s1.2k / 753
CG-AL-X133hard2100.0 / 1008/8OK9.8s6.0k / 6.4k
CG-AL-X134hard1100.0 / 1006/6OK10.2s2.0k / 2.0k
CG-AL-X135hard1100.0 / 1004/4OK9.7s1.4k / 954
CG-AL-X136hard1100.0 / 1007/7OK9.5s1.2k / 827
CG-AL-X137hard1100.0 / 1004/4OK9.6s1.5k / 1.5k
CG-AL-X138hard1100.0 / 1009/9OK10.1s2.4k / 2.7k
CG-AL-X139hard1100.0 / 10011/11OK10.1s2.8k / 2.6k
CG-AL-X140hard1100.0 / 1007/7OK10.6s2.5k / 4.5k
CG-AL-X141hard1100.0 / 10039/39OK10.4s6.1k / 5.8k
CG-AL-X142hard2100.0 / 10048/48OK11.1s15k / 14k
CG-AL-X143hard1100.0 / 10035/35OK14.7s7.2k / 6.8k
CG-AL-X144hard1100.0 / 10043/43OK10.4s6.4k / 6.2k
CG-AL-X145hard1100.0 / 10032/32OK10.2s7.4k / 7.1k
CG-AL-X146hard1100.0 / 1009/9OK9.9s2.9k / 3.7k
CG-AL-X147hard1100.0 / 1008/8OK10.2s2.2k / 1.8k
CG-AL-X148hard1100.0 / 1006/6OK9.5s1.9k / 1.4k
CG-AL-X149hard1100.0 / 1007/7OK9.5s1.9k / 1.4k
CG-AL-X150hard1100.0 / 1009/9OK10.6s3.2k / 5.2k
CG-AL-X151hard1100.0 / 1006/6OK9.2s1.4k / 951
CG-AL-X152hard1100.0 / 1008/8OK10.5s1.9k / 1.6k
CG-AL-X153hard1100.0 / 1009/9OK13.4s1.5k / 1.6k
CG-AL-X154hard1100.0 / 1009/9OK10.9s2.1k / 1.9k
CG-AL-X155hard1100.0 / 10011/11OK9.6s1.5k / 1.3k
CG-AL-X156hard1100.0 / 1007/7OK9.9s1.5k / 942
CG-AL-X157hard1100.0 / 10010/10OK9.5s2.2k / 1.6k
CG-AL-X158hard1100.0 / 1007/7OK9.7s1.3k / 761
CG-AL-X159hard1100.0 / 1007/7OK10.0s1.4k / 1.1k
CG-AL-X160hard1100.0 / 10013/13OK9.5s2.0k / 2.1k
CG-AL-X161hard1100.0 / 10010/10OK9.8s2.4k / 2.4k
CG-AL-X162hard1100.0 / 1007/7OK9.9s1.6k / 1.4k
CG-AL-X163hard1100.0 / 1007/7OK9.4s1.7k / 1.5k
CG-AL-X164hard1100.0 / 1007/7OK9.7s1.5k / 1.2k
CG-AL-X165hard1100.0 / 10013/13OK12.5s4.7k / 4.7k
CG-AL-X166hard1100.0 / 10014/14OK10.7s2.7k / 2.3k
CG-AL-X167hard2100.0 / 10013/13OK10.2s6.1k / 5.1k
CG-AL-X168hard2100.0 / 1009/9OK9.7s6.5k / 7.1k
CG-AL-X169hard2100.0 / 10011/11OK11.5s7.1k / 6.7k
CG-AL-X170hard1100.0 / 10011/11OK10.2s5.2k / 5.7k
CG-AL-X171hard1100.0 / 1009/9OK10.2s2.5k / 3.1k
CG-AL-X172hard1100.0 / 10011/11OK9.9s3.8k / 6.6k
CG-AL-X173hard2100.0 / 10019/19OK10.8s13k / 14k
CG-AL-X174hard1100.0 / 10016/16OK10.8s6.8k / 6.8k
CG-AL-X185hard262.5 / 10041/43OK10.6s9.2k / 2.9k
CG-AL-X187hard2100.0 / 10033/33OK10.2s13k / 6.2k
CG-AL-X194hard2100.0 / 10050/50OK10.5s18k / 7.1k
CG-AL-X211hard1100.0 / 10043/43OK10.4s6.0k / 4.8k
CG-AL-X214hard2100.0 / 10034/34OK10.1s14k / 8.7k
CG-AL-X218hard262.5 / 10026/27OK10.2s13k / 7.8k
CG-AL-X234hard1100.0 / 10035/35OK10.3s6.6k / 4.9k
CG-AL-X239hard2100.0 / 10037/37OK11.2s18k / 7.3k
CG-AL-X244hard2100.0 / 10038/38OK10.6s20k / 12k
CG-AL-X245hard1100.0 / 10063/63OK10.6s7.5k / 3.8k
CG-AL-X248hard2100.0 / 10066/66OK10.6s17k / 6.2k
CG-AL-X249hard2100.0 / 10037/37OK10.9s17k / 7.5k
CG-AL-X254hard1100.0 / 10070/70OK11.7s10k / 6.5k
CG-AL-X257hard2100.0 / 10053/53OK10.6s15k / 6.4k
CG-AL-X263hard1100.0 / 10061/61OK11.3s7.5k / 6.8k
CG-AL-X264hard2100.0 / 10065/65OK10.8s17k / 7.1k
CG-AL-X270hard2100.0 / 10063/63OK11.4s27k / 12k
CG-AL-X271hard2100.0 / 10070/70OK11.2s28k / 11k
CG-AL-X272hard1100.0 / 10079/79OK11.2s11k / 7.0k
CG-AL-X274hard2100.0 / 10064/64OK10.8s21k / 8.5k
CG-AL-X276hard2100.0 / 10078/78OK11.2s24k / 10k
CG-AL-X278hard2100.0 / 10071/71OK11.4s23k / 9.1k
CG-AL-X283hard1100.0 / 10076/76OK11.1s11k / 8.2k
CG-AL-X289hard1100.0 / 10057/57OK10.8s8.8k / 9.1k
CG-AL-X290hard1100.0 / 10047/47OK10.7s9.1k / 8.9k
CG-AL-X292hard1100.0 / 10057/57OK10.6s8.3k / 3.6k
CG-AL-X293hard1100.0 / 10049/49OK10.5s7.5k / 5.3k
CG-AL-X296hard2100.0 / 10047/47OK10.6s24k / 13k
CG-AL-X298hard1100.0 / 10055/55OK10.5s7.7k / 4.5k