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.

95.7% 222/232 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 $17.97
Tokens 904k / 718k input / output, all attempts
Duration 59m 23s
Filter:
Per-task results for run ff88ccec-f809-4ba3-81ae-7785ada15057
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK20.0s415 / 644
CG-AL-E006easy1100.0 / 1007/7OK34.4s496 / 603
CG-AL-E010easy262.5 / 1000/1OK33.4s1.3k / 709
CG-AL-E050easy1100.0 / 10013/13OK12.1s632 / 684
CG-AL-E052easy1100.0 / 10016/16OK12.1s612 / 588
CG-AL-E054easy2100.0 / 1009/9OK18.1s1.8k / 1.6k
CG-AL-E056easy2100.0 / 10015/15OK18.1s2.8k / 1.1k
CG-AL-H007hard1100.0 / 10011/11OK12.2s949 / 1.8k
CG-AL-H011hard1100.0 / 1006/6OK13.5s576 / 1.1k
CG-AL-H014hard1100.0 / 1007/7OK14.3s729 / 1.8k
CG-AL-H017hard1100.0 / 1005/5OK13.2s612 / 1.0k
CG-AL-H020hard1100.0 / 10010/10OK12.9s783 / 1.9k
CG-AL-H021hard2100.0 / 10020/20OK10.2s30k / 3.0k
CG-AL-H023hard1100.0 / 10025/25OK13.4s2.0k / 16k
CG-AL-H027hard1100.0 / 1004/4OK12.0s1.1k / 1.4k
CG-AL-H029hard1100.0 / 10018/18OK15.1s1.3k / 3.1k
CG-AL-H030hard1100.0 / 10010/10OK13.8s1.1k / 1.9k
CG-AL-H031hard1100.0 / 10022/22OK13.0s1.6k / 2.4k
CG-AL-H034hard1100.0 / 1003/3OK11.3s722 / 786
CG-AL-H036hard1100.0 / 1005/5OK11.2s640 / 1.0k
CG-AL-H037hard1100.0 / 1003/3OK11.5s807 / 649
CG-AL-H041hard1100.0 / 1003/3OK11.7s925 / 2.1k
CG-AL-H050hard1100.0 / 1003/3OK11.9s815 / 1.1k
CG-AL-H054hard2100.0 / 1005/5OK9.9s2.3k / 2.1k
CG-AL-H056hard2100.0 / 1004/4OK9.9s2.4k / 1.1k
CG-AL-M001medium2100.0 / 10010/10OK20.5s2.4k / 2.7k
CG-AL-M003medium2100.0 / 1009/9OK15.7s3.6k / 5.7k
CG-AL-M004medium1100.0 / 10012/12OK39.2s775 / 3.4k
CG-AL-M006medium1100.0 / 10018/18OK12.9s707 / 4.8k
CG-AL-M007medium262.5 / 10013/15OK11.8s7.6k / 14k
CG-AL-M008medium262.5 / 1005/12OK10.7s22k / 40k
CG-AL-M009medium1100.0 / 10011/11OK11.7s748 / 18k
CG-AL-M010medium1100.0 / 10021/21OK25.6s960 / 4.8k
CG-AL-M020medium1100.0 / 10017/17OK14.4s885 / 2.5k
CG-AL-M023medium1100.0 / 10011/11OK13.5s805 / 1.2k
CG-AL-M025medium2100.0 / 1008/8OK10.1s4.9k / 2.1k
CG-AL-M026medium1100.0 / 1008/8OK11.4s626 / 1.1k
CG-AL-M027medium1100.0 / 10018/18OK14.2s1.4k / 2.8k
CG-AL-M028medium2100.0 / 1003/3OK21.4s1.8k / 1.5k
CG-AL-M031medium1100.0 / 1002/2OK12.9s1.2k / 1.4k
CG-AL-M034medium1100.0 / 1002/2OK12.2s697 / 656
CG-AL-M036medium1100.0 / 1002/2OK12.5s912 / 959
CG-AL-M040medium1100.0 / 1002/2OK12.1s502 / 700
CG-AL-M042medium1100.0 / 1008/8OK12.6s755 / 952
CG-AL-X001hard1100.0 / 1002/2OK11.7s501 / 465
CG-AL-X002hard1100.0 / 1004/4OK11.7s730 / 1.6k
CG-AL-X003hard2100.0 / 1003/3OK10.3s1.4k / 2.9k
CG-AL-X004medium1100.0 / 1003/3OK11.7s553 / 958
CG-AL-X005hard1100.0 / 1002/2OK12.8s517 / 687
CG-AL-X006hard1100.0 / 1003/3OK12.3s605 / 1.0k
CG-AL-X007hard1100.0 / 1002/2OK1m 49s577 / 1.2k
CG-AL-X008hard20.0 / 1000/0FAIL0ms1.3k / 10
CG-AL-X009medium1100.0 / 1002/2OK12.0s495 / 632
CG-AL-X010medium1100.0 / 1003/3OK12.2s451 / 366
CG-AL-X011medium1100.0 / 1002/2OK11.5s559 / 597
CG-AL-X012hard1100.0 / 1001/1OK11.9s591 / 472
CG-AL-X013hard1100.0 / 1002/2OK12.7s425 / 213
CG-AL-X014medium1100.0 / 1004/4OK11.8s460 / 332
CG-AL-X017medium2100.0 / 1003/3OK9.6s2.4k / 492
CG-AL-X018medium1100.0 / 1003/3OK11.6s608 / 627
CG-AL-X019medium1100.0 / 1003/3OK11.6s581 / 848
CG-AL-X022medium1100.0 / 1003/3OK11.5s443 / 847
CG-AL-X024medium1100.0 / 1003/3OK11.6s543 / 921
CG-AL-X025medium1100.0 / 1001/1OK16.9s603 / 838
CG-AL-X026medium1100.0 / 1003/3OK12.0s526 / 477
CG-AL-X027medium1100.0 / 1004/4OK11.8s426 / 619
CG-AL-X029medium1100.0 / 1002/2OK11.4s437 / 1.1k
CG-AL-X030medium1100.0 / 1002/2OK11.6s410 / 316
CG-AL-X031medium1100.0 / 1003/3OK12.8s467 / 325
CG-AL-X033hard1100.0 / 1002/2OK11.4s560 / 294
CG-AL-X034hard1100.0 / 1003/3OK12.6s488 / 567
CG-AL-X035hard1100.0 / 1003/3OK12.4s525 / 605
CG-AL-X037hard1100.0 / 1004/4OK12.7s648 / 2.2k
CG-AL-X040hard1100.0 / 1004/4OK12.1s891 / 1.7k
CG-AL-X041hard1100.0 / 1005/5OK12.2s704 / 1.3k
CG-AL-X043hard2100.0 / 1001/1OK13.4s2.3k / 4.2k
CG-AL-X044hard2100.0 / 1003/3OK10.2s2.9k / 5.0k
CG-AL-X045hard1100.0 / 1003/3OK12.2s604 / 315
CG-AL-X046hard1100.0 / 1002/2OK11.7s571 / 775
CG-AL-X047hard1100.0 / 1002/2OK12.1s652 / 1.7k
CG-AL-X050hard1100.0 / 1002/2OK11.4s660 / 1.1k
CG-AL-X051hard1100.0 / 1002/2OK12.0s802 / 990
CG-AL-X052hard1100.0 / 1003/3OK11.5s584 / 1.1k
CG-AL-X055hard1100.0 / 1005/5OK11.1s548 / 495
CG-AL-X056hard1100.0 / 1005/5OK12.4s449 / 787
CG-AL-X057hard1100.0 / 1005/5OK11.4s413 / 162
CG-AL-X058hard1100.0 / 1005/5OK12.9s502 / 923
CG-AL-X059hard1100.0 / 1003/3OK11.7s513 / 106
CG-AL-X060hard1100.0 / 1003/3OK12.6s489 / 323
CG-AL-X061hard1100.0 / 1004/4OK12.2s574 / 175
CG-AL-X062hard1100.0 / 1004/4OK11.3s603 / 660
CG-AL-X063hard1100.0 / 1003/3OK12.1s561 / 837
CG-AL-X064hard1100.0 / 1007/7OK11.0s459 / 987
CG-AL-X065hard1100.0 / 1006/6OK10.9s1.2k / 1.1k
CG-AL-X066hard1100.0 / 10014/14OK11.6s2.2k / 2.0k
CG-AL-X067hard1100.0 / 1007/7OK11.0s1.0k / 657
CG-AL-X068hard1100.0 / 10012/12OK11.2s2.0k / 1.7k
CG-AL-X069hard1100.0 / 1008/8OK12.8s1.9k / 3.2k
CG-AL-X070hard1100.0 / 10012/12OK11.9s1.9k / 1.7k
CG-AL-X071hard1100.0 / 1008/8OK11.8s2.3k / 1.9k
CG-AL-X072hard1100.0 / 1007/7OK11.9s2.1k / 1.8k
CG-AL-X073hard1100.0 / 1008/8OK12.6s2.5k / 2.6k
CG-AL-X074hard2100.0 / 1007/7OK10.3s5.9k / 5.8k
CG-AL-X075hard1100.0 / 1007/7OK12.5s1.4k / 1.2k
CG-AL-X076hard1100.0 / 10014/14OK12.1s1.6k / 1.4k
CG-AL-X077hard1100.0 / 10022/22OK15.4s2.6k / 2.2k
CG-AL-X078hard1100.0 / 10017/17OK12.2s2.0k / 1.5k
CG-AL-X079hard1100.0 / 10011/11OK13.0s2.0k / 2.2k
CG-AL-X080hard2100.0 / 1007/7OK10.7s4.3k / 3.2k
CG-AL-X081hard1100.0 / 1008/8OK12.0s1.5k / 1.0k
CG-AL-X082hard1100.0 / 10015/15OK12.2s2.1k / 1.9k
CG-AL-X083hard1100.0 / 1009/9OK11.8s2.8k / 2.3k
CG-AL-X084hard1100.0 / 10010/10OK12.6s2.5k / 2.4k
CG-AL-X085hard1100.0 / 1007/7OK11.9s1.6k / 1.2k
CG-AL-X086hard1100.0 / 1006/6OK11.5s2.4k / 2.4k
CG-AL-X087hard1100.0 / 1003/3OK11.4s1.8k / 1.7k
CG-AL-X088hard1100.0 / 1006/6OK11.9s1.7k / 1.6k
CG-AL-X089hard1100.0 / 10011/11OK11.3s1.8k / 3.2k
CG-AL-X090hard1100.0 / 10010/10OK11.8s1.5k / 2.1k
CG-AL-X091hard1100.0 / 1006/6OK11.4s943 / 539
CG-AL-X092hard1100.0 / 10015/15OK11.0s718 / 281
CG-AL-X093hard1100.0 / 10010/10OK11.5s1.7k / 1.3k
CG-AL-X094hard1100.0 / 1007/7OK11.0s1.3k / 911
CG-AL-X095hard2100.0 / 1005/5OK10.1s4.1k / 3.3k
CG-AL-X096hard1100.0 / 10049/49OK12.4s6.0k / 5.6k
CG-AL-X097hard1100.0 / 10046/46OK12.8s6.1k / 5.5k
CG-AL-X098hard1100.0 / 10029/29OK14.5s4.8k / 4.1k
CG-AL-X099hard1100.0 / 10039/39OK15.6s6.4k / 6.7k
CG-AL-X100hard1100.0 / 10035/35OK12.3s6.0k / 5.5k
CG-AL-X101hard1100.0 / 10010/10OK11.5s1.9k / 1.7k
CG-AL-X102hard1100.0 / 1008/8OK11.3s886 / 1.4k
CG-AL-X103hard1100.0 / 1007/7OK12.3s1.2k / 804
CG-AL-X104hard1100.0 / 1006/6OK12.1s1.7k / 1.4k
CG-AL-X105hard1100.0 / 1006/6OK11.6s1.3k / 807
CG-AL-X106hard1100.0 / 1005/5OK12.1s1.5k / 1.6k
CG-AL-X107hard1100.0 / 1004/4OK11.9s1.4k / 1.5k
CG-AL-X108hard1100.0 / 1006/6OK12.7s1.2k / 1.9k
CG-AL-X109hard1100.0 / 1005/5OK13.2s918 / 648
CG-AL-X110hard1100.0 / 10017/17OK12.6s2.1k / 1.8k
CG-AL-X111hard1100.0 / 1008/8OK12.7s2.0k / 2.4k
CG-AL-X112hard1100.0 / 10012/12OK13.0s1.5k / 2.1k
CG-AL-X113hard1100.0 / 10013/13OK13.3s1.3k / 1.3k
CG-AL-X114hard1100.0 / 1007/7OK13.6s1.2k / 838
CG-AL-X115hard1100.0 / 10013/13OK14.3s795 / 601
CG-AL-X116hard1100.0 / 10017/17OK13.9s1.5k / 1.2k
CG-AL-X117hard1100.0 / 1008/8OK14.2s1.7k / 1.5k
CG-AL-X118hard1100.0 / 10017/17OK13.4s2.4k / 2.0k
CG-AL-X119hard1100.0 / 10015/15OK13.0s2.8k / 2.6k
CG-AL-X120hard1100.0 / 10012/12OK12.5s2.2k / 1.9k
CG-AL-X121hard1100.0 / 1006/6OK11.8s1.7k / 1.4k
CG-AL-X122hard1100.0 / 10010/10OK12.9s2.6k / 2.4k
CG-AL-X123hard1100.0 / 1005/5OK11.7s983 / 868
CG-AL-X124hard1100.0 / 10010/10OK11.7s1.7k / 1.3k
CG-AL-X125hard1100.0 / 1008/8OK11.5s2.3k / 2.4k
CG-AL-X126hard1100.0 / 10014/14OK11.6s1.2k / 1.0k
CG-AL-X127hard1100.0 / 1005/5OK11.6s1.1k / 641
CG-AL-X128hard1100.0 / 1008/8OK11.5s2.0k / 1.5k
CG-AL-X129hard1100.0 / 10014/14OK12.3s2.0k / 1.8k
CG-AL-X130hard1100.0 / 1005/5OK11.0s847 / 648
CG-AL-X131hard1100.0 / 10013/13OK11.1s1.6k / 1.2k
CG-AL-X132hard20.0 / 1000/0FAIL4.3s2.2k / 1.4k
CG-AL-X133hard2100.0 / 1008/8OK10.0s6.2k / 6.0k
CG-AL-X134hard1100.0 / 1006/6OK11.9s2.0k / 1.9k
CG-AL-X135hard1100.0 / 1004/4OK11.2s1.4k / 954
CG-AL-X136hard1100.0 / 1007/7OK11.5s1.2k / 795
CG-AL-X137hard1100.0 / 1004/4OK19.1s1.5k / 1.2k
CG-AL-X138hard1100.0 / 1009/9OK11.9s2.4k / 2.3k
CG-AL-X139hard1100.0 / 10011/11OK11.3s2.8k / 2.6k
CG-AL-X140hard1100.0 / 1007/7OK12.5s2.5k / 4.1k
CG-AL-X141hard1100.0 / 10039/39OK12.5s6.1k / 5.7k
CG-AL-X142hard2100.0 / 10048/48OK10.7s15k / 14k
CG-AL-X143hard1100.0 / 10035/35OK16.6s7.2k / 6.6k
CG-AL-X144hard1100.0 / 10043/43OK12.2s6.4k / 6.3k
CG-AL-X145hard2100.0 / 10032/32OK10.9s16k / 14k
CG-AL-X146hard1100.0 / 1009/9OK11.9s2.9k / 4.2k
CG-AL-X147hard1100.0 / 1008/8OK12.2s2.2k / 1.8k
CG-AL-X148hard1100.0 / 1006/6OK11.0s1.9k / 1.4k
CG-AL-X149hard1100.0 / 1007/7OK11.3s1.9k / 1.4k
CG-AL-X150hard1100.0 / 1009/9OK12.6s3.2k / 4.9k
CG-AL-X151hard1100.0 / 1006/6OK11.2s1.4k / 951
CG-AL-X152hard1100.0 / 1008/8OK11.3s1.9k / 1.4k
CG-AL-X153hard1100.0 / 1009/9OK16.0s1.5k / 1.6k
CG-AL-X154hard1100.0 / 1009/9OK11.3s2.1k / 1.9k
CG-AL-X155hard1100.0 / 10011/11OK11.6s1.5k / 1.3k
CG-AL-X156hard1100.0 / 1007/7OK11.4s1.5k / 942
CG-AL-X157hard1100.0 / 10010/10OK11.4s2.2k / 1.6k
CG-AL-X158hard1100.0 / 1007/7OK11.3s1.3k / 761
CG-AL-X159hard1100.0 / 1007/7OK12.0s1.4k / 1.2k
CG-AL-X160hard1100.0 / 10013/13OK11.7s2.0k / 2.2k
CG-AL-X161hard1100.0 / 10010/10OK12.0s2.4k / 2.4k
CG-AL-X162hard1100.0 / 1007/7OK11.7s1.6k / 1.4k
CG-AL-X163hard1100.0 / 1007/7OK11.4s1.7k / 1.4k
CG-AL-X164hard1100.0 / 1007/7OK11.4s1.5k / 1.3k
CG-AL-X165hard1100.0 / 10013/13OK14.9s4.7k / 5.7k
CG-AL-X166hard1100.0 / 10014/14OK12.3s2.7k / 2.3k
CG-AL-X167hard2100.0 / 10013/13OK10.5s6.1k / 5.3k
CG-AL-X168hard2100.0 / 1009/9OK10.4s6.3k / 7.0k
CG-AL-X169hard2100.0 / 10011/11OK11.5s7.0k / 6.1k
CG-AL-X170hard1100.0 / 10011/11OK13.0s5.2k / 5.7k
CG-AL-X171hard1100.0 / 1009/9OK14.8s2.5k / 3.4k
CG-AL-X172hard1100.0 / 10011/11OK13.2s3.8k / 5.9k
CG-AL-X173hard2100.0 / 10019/19OK11.3s12k / 13k
CG-AL-X174hard1100.0 / 10016/16OK12.5s6.8k / 7.0k
CG-AL-X185hard262.5 / 10041/43OK10.5s9.2k / 3.0k
CG-AL-X187hard262.5 / 10030/33OK10.9s11k / 4.1k
CG-AL-X194hard2100.0 / 10050/50OK11.5s18k / 6.9k
CG-AL-X211hard1100.0 / 10043/43OK15.1s6.0k / 5.0k
CG-AL-X214hard2100.0 / 10034/34OK10.8s13k / 5.8k
CG-AL-X218hard2100.0 / 10027/27OK10.8s13k / 6.1k
CG-AL-X234hard1100.0 / 10035/35OK12.7s6.6k / 4.7k
CG-AL-X239hard2100.0 / 10037/37OK11.0s18k / 6.5k
CG-AL-X244hard2100.0 / 10038/38OK10.9s21k / 11k
CG-AL-X245hard2100.0 / 10063/63OK11.2s17k / 4.9k
CG-AL-X248hard262.5 / 10065/66OK11.0s26k / 7.6k
CG-AL-X249hard2100.0 / 10037/37OK10.9s16k / 7.4k
CG-AL-X254hard1100.0 / 10070/70OK15.0s10k / 6.3k
CG-AL-X257hard2100.0 / 10053/53OK11.2s15k / 6.9k
CG-AL-X263hard1100.0 / 10061/61OK14.3s7.5k / 6.2k
CG-AL-X264hard2100.0 / 10065/65OK11.0s18k / 7.2k
CG-AL-X270hard2100.0 / 10063/63OK11.7s27k / 11k
CG-AL-X271hard2100.0 / 10070/70OK12.5s28k / 13k
CG-AL-X272hard1100.0 / 10079/79OK15.9s11k / 7.3k
CG-AL-X274hard262.5 / 10063/64OK11.2s22k / 12k
CG-AL-X276hard2100.0 / 10078/78OK12.7s23k / 8.9k
CG-AL-X278hard2100.0 / 10071/71OK12.0s26k / 10k
CG-AL-X283hard1100.0 / 10076/76OK13.7s11k / 7.0k
CG-AL-X289hard1100.0 / 10057/57OK13.0s8.8k / 9.9k
CG-AL-X290hard1100.0 / 10047/47OK12.9s9.1k / 5.8k
CG-AL-X292hard1100.0 / 10057/57OK14.0s8.3k / 4.3k
CG-AL-X293hard1100.0 / 10049/49OK13.9s7.5k / 5.0k
CG-AL-X296hard2100.0 / 10047/47OK11.7s24k / 14k
CG-AL-X298hard262.5 / 10054/55OK10.8s16k / 8.2k