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.

65.9% 153/232 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.

61.6 / 100
Cost $3.16
Tokens 710k / 2.4M input / output, all attempts
Duration 58m 1s
Filter:
Per-task results for run 75675cb6-b54e-47e9-8005-48004237a745
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK26.0s427 / 667
CG-AL-E006easy262.5 / 1000/1OK27.5s1.3k / 5.5k
CG-AL-E010easy1100.0 / 1005/5OK24.7s448 / 755
CG-AL-E050easy20.0 / 1000/0FAIL8.7s2.1k / 8.8k
CG-AL-E052easy1100.0 / 10016/16OK11.8s521 / 1.1k
CG-AL-E054easy2100.0 / 1009/9OK16.7s1.4k / 2.7k
CG-AL-E056easy2100.0 / 10015/15OK11.9s2.0k / 2.9k
CG-AL-H007hard1100.0 / 10011/11OK15.3s714 / 3.5k
CG-AL-H011hard20.0 / 1000/0FAIL3.6s1.4k / 7.3k
CG-AL-H014hard20.0 / 1000/0FAIL4.4s1.7k / 2.8k
CG-AL-H017hard20.0 / 1000/0FAIL0ms526 / 1.1k
CG-AL-H020hard2100.0 / 10010/10OK11.7s2.4k / 18k
CG-AL-H021hard20.0 / 1000/0FAIL3.7s2.2k / 6.7k
CG-AL-H023hard20.0 / 1000/0FAIL4.4s6.3k / 36k
CG-AL-H027hard20.0 / 1000/0FAIL3.9s2.0k / 22k
CG-AL-H029hard20.0 / 1000/0FAIL4.2s3.0k / 19k
CG-AL-H030hard262.5 / 1009/10OK11.4s2.3k / 14k
CG-AL-H031hard2100.0 / 10022/22OK11.2s3.1k / 12k
CG-AL-H034hard2100.0 / 1003/3OK11.2s1.6k / 5.9k
CG-AL-H036hard20.0 / 1000/0FAIL3.9s1.3k / 4.6k
CG-AL-H037hard20.0 / 1000/0FAIL4.0s1.7k / 4.3k
CG-AL-H041hard20.0 / 1000/0FAIL4.1s1.8k / 14k
CG-AL-H050hard20.0 / 1000/0FAIL3.8s1.7k / 10k
CG-AL-H054hard20.0 / 1000/0FAIL5.2s2.2k / 5.9k
CG-AL-H056hard20.0 / 1000/0FAIL4.1s1.8k / 14k
CG-AL-M001medium20.0 / 1000/0FAIL0ms637 / 4.0k
CG-AL-M003medium2100.0 / 1009/9OK16.8s4.1k / 12k
CG-AL-M004medium1100.0 / 10012/12OK32.3s623 / 3.2k
CG-AL-M006medium20.0 / 1000/0FAIL0ms577 / 4.6k
CG-AL-M007medium20.0 / 1000/0FAIL3.7s3.4k / 26k
CG-AL-M008medium20.0 / 1000/0FAIL3.8s4.8k / 27k
CG-AL-M009medium2100.0 / 10011/11OK11.0s2.7k / 7.7k
CG-AL-M010medium1100.0 / 10021/21OK25.3s767 / 7.3k
CG-AL-M020medium20.0 / 1000/0FAIL3.8s2.2k / 2.8k
CG-AL-M023medium1100.0 / 10011/11OK11.8s650 / 1.7k
CG-AL-M025medium262.5 / 1002/8OK11.3s3.2k / 7.2k
CG-AL-M026medium20.0 / 1000/0FAIL3.8s1.4k / 3.1k
CG-AL-M027medium20.0 / 1000/0FAIL3.8s4.5k / 9.2k
CG-AL-M028medium20.0 / 1000/0FAIL8.5s1.4k / 7.0k
CG-AL-M031medium255.6 / 1000/2OK11.1s2.4k / 5.0k
CG-AL-M034medium266.7 / 1000/2OK11.3s1.9k / 13k
CG-AL-M036medium211.1 / 1000/0FAIL4.0s1.8k / 3.0k
CG-AL-M040medium20.0 / 1000/0FAIL0ms481 / 530
CG-AL-M042medium1100.0 / 1008/8OK11.5s667 / 2.9k
CG-AL-X001hard1100.0 / 1002/2OK10.7s477 / 902
CG-AL-X002hard2100.0 / 1004/4OK11.0s1.7k / 26k
CG-AL-X003hard20.0 / 1000/0FAIL0ms408 / 817
CG-AL-X004medium1100.0 / 1003/3OK11.0s528 / 1.3k
CG-AL-X005hard1100.0 / 1002/2OK11.4s496 / 878
CG-AL-X006hard1100.0 / 1003/3OK11.4s553 / 1.8k
CG-AL-X007hard1100.0 / 1002/2OK1m 46s541 / 1.3k
CG-AL-X008hard2100.0 / 1001/1OK10.7s1.7k / 11k
CG-AL-X009medium1100.0 / 1002/2OK11.6s482 / 1.2k
CG-AL-X010medium1100.0 / 1003/3OK11.3s453 / 762
CG-AL-X011medium1100.0 / 1002/2OK12.0s532 / 886
CG-AL-X012hard2100.0 / 1001/1OK10.9s1.9k / 6.5k
CG-AL-X013hard1100.0 / 1002/2OK11.1s431 / 452
CG-AL-X014medium1100.0 / 1004/4OK11.1s461 / 143
CG-AL-X017medium2100.0 / 1003/3OK10.6s1.8k / 934
CG-AL-X018medium1100.0 / 1003/3OK11.3s554 / 1.6k
CG-AL-X019medium2100.0 / 1003/3OK10.8s2.1k / 2.7k
CG-AL-X022medium20.0 / 1000/0FAIL0ms445 / 1.4k
CG-AL-X024medium1100.0 / 1003/3OK11.4s502 / 1.5k
CG-AL-X025medium2100.0 / 1001/1OK11.6s1.6k / 2.2k
CG-AL-X026medium1100.0 / 1003/3OK11.4s496 / 406
CG-AL-X027medium1100.0 / 1004/4OK10.9s427 / 991
CG-AL-X029medium1100.0 / 1002/2OK10.8s446 / 1.1k
CG-AL-X030medium1100.0 / 1002/2OK11.1s408 / 184
CG-AL-X031medium1100.0 / 1003/3OK11.3s467 / 555
CG-AL-X033hard1100.0 / 1002/2OK10.8s517 / 545
CG-AL-X034hard1100.0 / 1003/3OK11.0s472 / 1.1k
CG-AL-X035hard1100.0 / 1003/3OK10.9s500 / 2.0k
CG-AL-X037hard2100.0 / 1004/4OK10.8s2.4k / 11k
CG-AL-X040hard262.5 / 1000/4OK10.9s1.7k / 16k
CG-AL-X041hard262.5 / 1000/5OK10.9s1.7k / 18k
CG-AL-X043hard20.0 / 1000/0FAIL4.4s1.6k / 19k
CG-AL-X044hard20.0 / 1000/0FAIL4.2s1.6k / 20k
CG-AL-X045hard1100.0 / 1003/3OK11.2s540 / 1.4k
CG-AL-X046hard2100.0 / 1002/2OK10.8s1.9k / 2.0k
CG-AL-X047hard2100.0 / 1002/2OK11.1s2.2k / 6.2k
CG-AL-X050hard2100.0 / 1002/2OK10.8s1.9k / 8.3k
CG-AL-X051hard262.5 / 1000/2OK11.2s2.1k / 10k
CG-AL-X052hard262.5 / 1000/3OK11.8s2.0k / 7.7k
CG-AL-X055hard1100.0 / 1005/5OK10.9s513 / 848
CG-AL-X056hard2100.0 / 1005/5OK11.2s1.1k / 2.9k
CG-AL-X057hard1100.0 / 1005/5OK10.5s419 / 1.8k
CG-AL-X058hard1100.0 / 1005/5OK11.2s481 / 2.4k
CG-AL-X059hard1100.0 / 1003/3OK11.1s496 / 2.3k
CG-AL-X060hard1100.0 / 1003/3OK11.2s471 / 562
CG-AL-X061hard1100.0 / 1004/4OK12.7s533 / 935
CG-AL-X062hard1100.0 / 1004/4OK11.0s527 / 1.2k
CG-AL-X063hard1100.0 / 1003/3OK10.9s529 / 1.5k
CG-AL-X064hard1100.0 / 1007/7OK10.8s446 / 1.8k
CG-AL-X065hard1100.0 / 1006/6OK10.9s885 / 1.5k
CG-AL-X066hard1100.0 / 10014/14OK11.2s1.4k / 3.0k
CG-AL-X067hard262.5 / 1006/7OK10.6s2.2k / 7.9k
CG-AL-X068hard20.0 / 1000/0FAIL3.9s2.8k / 6.3k
CG-AL-X069hard262.5 / 1007/8OK11.1s2.7k / 10k
CG-AL-X070hard1100.0 / 10012/12OK11.2s1.4k / 3.0k
CG-AL-X071hard262.5 / 1006/8OK11.3s3.8k / 8.4k
CG-AL-X072hard1100.0 / 1007/7OK11.1s1.3k / 1.5k
CG-AL-X073hard1100.0 / 1008/8OK11.6s1.6k / 2.1k
CG-AL-X074hard262.5 / 1006/7OK11.3s4.0k / 41k
CG-AL-X075hard1100.0 / 1007/7OK11.4s988 / 2.0k
CG-AL-X076hard1100.0 / 10014/14OK11.8s1.1k / 21k
CG-AL-X077hard1100.0 / 10022/22OK11.6s1.7k / 3.3k
CG-AL-X078hard1100.0 / 10017/17OK11.8s1.4k / 992
CG-AL-X079hard2100.0 / 10011/11OK11.1s3.7k / 37k
CG-AL-X080hard262.5 / 1006/7OK11.1s2.8k / 8.0k
CG-AL-X081hard1100.0 / 1008/8OK11.4s1.1k / 1.1k
CG-AL-X082hard1100.0 / 10015/15OK11.8s1.4k / 1.2k
CG-AL-X083hard262.5 / 1003/9OK11.2s3.5k / 3.8k
CG-AL-X084hard2100.0 / 10010/10OK11.6s3.5k / 12k
CG-AL-X085hard1100.0 / 1007/7OK11.5s1.2k / 6.4k
CG-AL-X086hard1100.0 / 1006/6OK11.6s1.6k / 5.6k
CG-AL-X087hard1100.0 / 1003/3OK11.4s1.2k / 2.9k
CG-AL-X088hard1100.0 / 1006/6OK11.8s1.2k / 3.6k
CG-AL-X089hard1100.0 / 10011/11OK12.0s1.3k / 11k
CG-AL-X090hard20.0 / 1000/0FAIL3.7s3.0k / 16k
CG-AL-X091hard1100.0 / 1006/6OK11.7s744 / 929
CG-AL-X092hard2100.0 / 10015/15OK10.9s1.9k / 19k
CG-AL-X093hard1100.0 / 10010/10OK11.5s1.2k / 2.0k
CG-AL-X094hard1100.0 / 1007/7OK11.8s932 / 923
CG-AL-X095hard1100.0 / 1005/5OK17.7s973 / 1.3k
CG-AL-X096hard1100.0 / 10049/49OK12.1s3.6k / 7.4k
CG-AL-X097hard1100.0 / 10046/46OK11.9s3.6k / 4.3k
CG-AL-X098hard1100.0 / 10029/29OK11.6s2.8k / 2.6k
CG-AL-X099hard2100.0 / 10039/39OK12.8s8.0k / 44k
CG-AL-X100hard1100.0 / 10035/35OK10.9s3.7k / 4.4k
CG-AL-X101hard262.5 / 1005/10OK11.2s4.3k / 13k
CG-AL-X102hard20.0 / 1000/0FAIL3.7s2.3k / 13k
CG-AL-X103hard1100.0 / 1007/7OK10.7s897 / 907
CG-AL-X104hard1100.0 / 1006/6OK10.8s1.2k / 1.1k
CG-AL-X105hard1100.0 / 1006/6OK10.6s950 / 787
CG-AL-X106hard1100.0 / 1005/5OK11.2s1.1k / 1.4k
CG-AL-X107hard1100.0 / 1004/4OK10.8s980 / 2.0k
CG-AL-X108hard1100.0 / 1006/6OK11.4s906 / 729
CG-AL-X109hard1100.0 / 1005/5OK10.7s722 / 801
CG-AL-X110hard1100.0 / 10017/17OK10.8s1.4k / 1.3k
CG-AL-X111hard1100.0 / 1008/8OK10.8s1.4k / 4.4k
CG-AL-X112hard1100.0 / 10012/12OK11.2s1.1k / 6.6k
CG-AL-X113hard1100.0 / 10013/13OK11.1s899 / 1.8k
CG-AL-X114hard1100.0 / 1007/7OK10.4s915 / 1.3k
CG-AL-X115hard2100.0 / 10013/13OK10.8s1.5k / 6.8k
CG-AL-X116hard2100.0 / 10017/17OK10.9s2.9k / 12k
CG-AL-X117hard1100.0 / 1008/8OK10.7s1.2k / 1.1k
CG-AL-X118hard1100.0 / 10017/17OK10.8s1.6k / 10k
CG-AL-X119hard1100.0 / 10015/15OK10.8s2.0k / 2.6k
CG-AL-X120hard1100.0 / 10012/12OK11.4s1.5k / 1.5k
CG-AL-X121hard1100.0 / 1006/6OK10.9s1.2k / 1.1k
CG-AL-X122hard20.0 / 1000/0FAIL0ms1.7k / 4.3k
CG-AL-X123hard1100.0 / 1005/5OK11.0s788 / 483
CG-AL-X124hard1100.0 / 10010/10OK11.6s1.2k / 1.0k
CG-AL-X125hard1100.0 / 1008/8OK11.8s1.6k / 13k
CG-AL-X126hard1100.0 / 10014/14OK11.8s897 / 2.9k
CG-AL-X127hard1100.0 / 1005/5OK11.7s863 / 827
CG-AL-X128hard1100.0 / 1008/8OK11.6s1.4k / 1.1k
CG-AL-X129hard1100.0 / 10014/14OK11.9s1.4k / 1.3k
CG-AL-X130hard20.0 / 1000/0FAIL4.0s1.8k / 3.1k
CG-AL-X131hard1100.0 / 10013/13OK11.9s1.1k / 2.3k
CG-AL-X132hard1100.0 / 10010/10OK11.4s902 / 585
CG-AL-X133hard20.0 / 1000/0FAIL3.9s4.2k / 27k
CG-AL-X134hard1100.0 / 1006/6OK11.3s1.4k / 1.8k
CG-AL-X135hard1100.0 / 1004/4OK11.3s1.1k / 1.1k
CG-AL-X136hard1100.0 / 1007/7OK11.1s943 / 3.1k
CG-AL-X137hard2100.0 / 1004/4OK10.7s2.4k / 5.7k
CG-AL-X138hard2100.0 / 1009/9OK11.5s5.1k / 8.4k
CG-AL-X139hard1100.0 / 10011/11OK11.0s1.8k / 2.0k
CG-AL-X140hard262.5 / 1004/7OK10.9s4.6k / 40k
CG-AL-X141hard2100.0 / 10039/39OK12.2s9.0k / 11k
CG-AL-X142hard262.5 / 10045/48OK12.0s9.7k / 35k
CG-AL-X143hard1100.0 / 10035/35OK16.3s4.4k / 6.2k
CG-AL-X144hard2100.0 / 10043/43OK12.0s11k / 16k
CG-AL-X145hard1100.0 / 10032/32OK11.7s4.6k / 6.1k
CG-AL-X146hard2100.0 / 1009/9OK11.9s5.4k / 30k
CG-AL-X147hard1100.0 / 1008/8OK11.8s1.5k / 1.3k
CG-AL-X148hard1100.0 / 1006/6OK11.5s1.3k / 975
CG-AL-X149hard1100.0 / 1007/7OK11.6s1.4k / 3.1k
CG-AL-X150hard262.5 / 1006/9OK11.3s5.9k / 39k
CG-AL-X151hard1100.0 / 1006/6OK10.8s1.0k / 651
CG-AL-X152hard1100.0 / 1008/8OK11.1s1.3k / 1.9k
CG-AL-X153hard20.0 / 1000/0FAIL4.4s2.8k / 7.4k
CG-AL-X154hard1100.0 / 1009/9OK10.8s1.5k / 1.7k
CG-AL-X155hard1100.0 / 10011/11OK11.3s1.1k / 1.7k
CG-AL-X156hard1100.0 / 1007/7OK11.3s1.1k / 715
CG-AL-X157hard1100.0 / 10010/10OK11.1s1.5k / 1.8k
CG-AL-X158hard1100.0 / 1007/7OK10.7s1.0k / 601
CG-AL-X159hard1100.0 / 1007/7OK11.6s1.1k / 994
CG-AL-X160hard1100.0 / 10013/13OK11.1s1.4k / 2.1k
CG-AL-X161hard1100.0 / 10010/10OK11.0s1.6k / 2.0k
CG-AL-X162hard1100.0 / 1007/7OK10.8s1.2k / 1.1k
CG-AL-X163hard1100.0 / 1007/7OK10.6s1.2k / 2.1k
CG-AL-X164hard1100.0 / 1007/7OK11.3s1.2k / 1.4k
CG-AL-X165hard2100.0 / 10013/13OK14.1s8.5k / 40k
CG-AL-X166hard1100.0 / 10014/14OK11.8s1.8k / 4.8k
CG-AL-X167hard262.5 / 10012/13OK11.6s4.1k / 29k
CG-AL-X168hard2100.0 / 1009/9OK11.2s3.5k / 31k
CG-AL-X169hard262.5 / 1009/11OK11.9s4.3k / 16k
CG-AL-X170hard1100.0 / 10011/11OK11.1s3.4k / 13k
CG-AL-X171hard1100.0 / 1009/9OK12.2s1.6k / 10k
CG-AL-X172hard262.5 / 1007/11OK11.1s5.8k / 40k
CG-AL-X173hard2100.0 / 10019/19OK12.5s7.4k / 16k
CG-AL-X174hard1100.0 / 10016/16OK11.7s4.2k / 15k
CG-AL-X185hard20.0 / 1000/0FAIL4.1s7.3k / 14k
CG-AL-X187hard262.5 / 10030/33OK11.5s9.6k / 21k
CG-AL-X194hard262.5 / 10043/50OK11.8s13k / 30k
CG-AL-X211hard262.5 / 10035/43OK12.0s13k / 45k
CG-AL-X214hard262.5 / 10031/34OK12.1s8.6k / 35k
CG-AL-X218hard262.5 / 10024/27OK11.6s8.4k / 37k
CG-AL-X234hard2100.0 / 10035/35OK11.4s9.8k / 40k
CG-AL-X239hard2100.0 / 10037/37OK12.0s12k / 50k
CG-AL-X244hard2100.0 / 10038/38OK11.5s12k / 54k
CG-AL-X245hard20.0 / 1000/0FAIL0ms4.7k / 19k
CG-AL-X248hard262.5 / 10048/66OK12.2s15k / 35k
CG-AL-X249hard20.0 / 1000/0FAIL0ms4.8k / 16k
CG-AL-X254hard2100.0 / 10070/70OK12.2s17k / 21k
CG-AL-X257hard20.0 / 1000/0FAIL3.9s8.8k / 62k
CG-AL-X263hard2100.0 / 10061/61OK12.5s11k / 25k
CG-AL-X264hard262.5 / 10063/65OK12.2s14k / 43k
CG-AL-X270hard262.5 / 10060/63OK12.5s22k / 58k
CG-AL-X271hard20.0 / 1000/0FAIL4.0s1.1k / 29k
CG-AL-X272hard262.5 / 10078/79OK12.7s15k / 26k
CG-AL-X274hard20.0 / 1000/0FAIL0ms6.2k / 13k
CG-AL-X276hard20.0 / 1000/0FAIL4.1s1.1k / 28k
CG-AL-X278hard262.5 / 10062/71OK12.7s14k / 20k
CG-AL-X283hard262.5 / 10071/76OK12.5s16k / 47k
CG-AL-X289hard20.0 / 1000/0FAIL3.9s987 / 28k
CG-AL-X290hard262.5 / 10041/47OK12.4s15k / 38k
CG-AL-X292hard2100.0 / 10057/57OK12.1s13k / 31k
CG-AL-X293hard2100.0 / 10049/49OK12.2s12k / 16k
CG-AL-X296hard262.5 / 10027/47OK12.0s17k / 51k
CG-AL-X298hard262.5 / 10038/55OK12.3s15k / 37k