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.

65.5% 152/232 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.

60.7 / 100
Cost $2.99
Tokens 688k / 2.3M input / output, all attempts
Duration 55m 30s
Filter:
Per-task results for run a0348e3b-5093-4757-b00e-7ffb87d71495
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK16.5s427 / 1.0k
CG-AL-E006easy1100.0 / 1007/7OK31.0s474 / 1.4k
CG-AL-E010easy1100.0 / 1005/5OK16.2s448 / 690
CG-AL-E050easy20.0 / 1000/0FAIL8.8s2.1k / 8.1k
CG-AL-E052easy1100.0 / 10016/16OK11.6s521 / 849
CG-AL-E054easy2100.0 / 1009/9OK16.7s1.4k / 1.6k
CG-AL-E056easy2100.0 / 10015/15OK17.0s2.0k / 3.2k
CG-AL-H007hard2100.0 / 10011/11OK16.1s2.0k / 6.1k
CG-AL-H011hard20.0 / 1000/0FAIL3.8s1.4k / 10k
CG-AL-H014hard20.0 / 1000/0FAIL3.9s1.7k / 3.3k
CG-AL-H017hard1100.0 / 1005/5OK10.5s526 / 1.3k
CG-AL-H020hard20.0 / 1000/0FAIL3.7s2.4k / 14k
CG-AL-H021hard20.0 / 1000/0FAIL3.7s2.2k / 3.4k
CG-AL-H023hard20.0 / 1000/0FAIL4.4s6.0k / 25k
CG-AL-H027hard1100.0 / 1004/4OK11.2s901 / 13k
CG-AL-H029hard20.0 / 1000/0FAIL4.0s3.0k / 18k
CG-AL-H030hard20.0 / 1000/0FAIL0ms838 / 5.1k
CG-AL-H031hard2100.0 / 10022/22OK11.3s3.1k / 10k
CG-AL-H034hard2100.0 / 1003/3OK11.2s1.6k / 3.7k
CG-AL-H036hard20.0 / 1000/0FAIL4.0s1.3k / 16k
CG-AL-H037hard20.0 / 1000/0FAIL4.4s1.5k / 2.2k
CG-AL-H041hard2100.0 / 1003/3OK11.8s1.8k / 11k
CG-AL-H050hard20.0 / 1000/0FAIL0ms669 / 16k
CG-AL-H054hard20.0 / 1000/0FAIL3.9s2.1k / 5.2k
CG-AL-H056hard20.0 / 1000/0FAIL0ms796 / 834
CG-AL-M001medium20.0 / 1000/0FAIL4.2s1.7k / 10k
CG-AL-M003medium20.0 / 1000/0FAIL0ms588 / 4.6k
CG-AL-M004medium1100.0 / 10012/12OK32.8s623 / 3.1k
CG-AL-M006medium2100.0 / 10018/18OK11.7s2.7k / 16k
CG-AL-M007medium20.0 / 1000/0FAIL3.8s3.4k / 15k
CG-AL-M008medium20.0 / 1000/0FAIL4.0s4.4k / 34k
CG-AL-M009medium2100.0 / 10011/11OK11.1s2.8k / 12k
CG-AL-M010medium1100.0 / 10021/21OK25.0s767 / 8.7k
CG-AL-M020medium20.0 / 1000/0FAIL3.9s2.2k / 2.4k
CG-AL-M023medium1100.0 / 10011/11OK10.9s650 / 1.2k
CG-AL-M025medium262.5 / 1002/8OK11.2s3.2k / 2.4k
CG-AL-M026medium2100.0 / 1008/8OK11.3s2.0k / 11k
CG-AL-M027medium2100.0 / 10018/18OK10.7s4.2k / 6.1k
CG-AL-M028medium20.0 / 1000/0FAIL3.6s1.4k / 8.6k
CG-AL-M031medium20.0 / 1000/0FAIL3.9s2.7k / 13k
CG-AL-M034medium211.1 / 1000/0FAIL4.1s1.9k / 6.3k
CG-AL-M036medium211.1 / 1000/0FAIL3.8s1.8k / 2.7k
CG-AL-M040medium20.0 / 1000/0FAIL8.7s1.1k / 11k
CG-AL-M042medium1100.0 / 1008/8OK10.7s667 / 2.4k
CG-AL-X001hard2100.0 / 1002/2OK11.0s1.3k / 846
CG-AL-X002hard2100.0 / 1004/4OK10.9s2.7k / 15k
CG-AL-X003hard20.0 / 1000/0FAIL6.0s944 / 4.6k
CG-AL-X004medium1100.0 / 1003/3OK10.7s528 / 1.1k
CG-AL-X005hard1100.0 / 1002/2OK10.6s496 / 542
CG-AL-X006hard1100.0 / 1003/3OK11.0s553 / 1.7k
CG-AL-X007hard1100.0 / 1002/2OK1m 40s541 / 1.7k
CG-AL-X008hard2100.0 / 1001/1OK11.0s1.7k / 17k
CG-AL-X009medium1100.0 / 1002/2OK10.6s482 / 494
CG-AL-X010medium1100.0 / 1003/3OK10.9s453 / 939
CG-AL-X011medium1100.0 / 1002/2OK10.7s532 / 463
CG-AL-X012hard1100.0 / 1001/1OK10.5s549 / 2.5k
CG-AL-X013hard1100.0 / 1002/2OK10.2s431 / 389
CG-AL-X014medium1100.0 / 1004/4OK11.2s461 / 444
CG-AL-X017medium2100.0 / 1003/3OK10.6s1.8k / 6.7k
CG-AL-X018medium1100.0 / 1003/3OK12.7s554 / 971
CG-AL-X019medium2100.0 / 1003/3OK11.0s2.1k / 948
CG-AL-X022medium20.0 / 1000/0FAIL0ms445 / 1.1k
CG-AL-X024medium1100.0 / 1003/3OK11.0s502 / 998
CG-AL-X025medium1100.0 / 1001/1OK10.8s539 / 1.9k
CG-AL-X026medium1100.0 / 1003/3OK11.0s496 / 812
CG-AL-X027medium2100.0 / 1004/4OK10.4s1.0k / 1.9k
CG-AL-X029medium1100.0 / 1002/2OK11.1s446 / 3.2k
CG-AL-X030medium1100.0 / 1002/2OK10.8s408 / 181
CG-AL-X031medium1100.0 / 1003/3OK10.8s467 / 485
CG-AL-X033hard1100.0 / 1002/2OK10.9s517 / 593
CG-AL-X034hard262.5 / 1000/3OK10.6s1.6k / 2.3k
CG-AL-X035hard2100.0 / 1003/3OK10.9s1.9k / 7.6k
CG-AL-X037hard262.5 / 1000/4OK11.1s1.4k / 14k
CG-AL-X040hard1100.0 / 1004/4OK11.1s719 / 15k
CG-AL-X041hard20.0 / 1000/0FAIL4.3s1.6k / 11k
CG-AL-X043hard20.0 / 1000/0FAIL4.4s1.9k / 20k
CG-AL-X044hard262.5 / 1000/3OK11.4s1.4k / 15k
CG-AL-X045hard1100.0 / 1003/3OK10.5s540 / 1.3k
CG-AL-X046hard2100.0 / 1002/2OK11.2s1.9k / 2.6k
CG-AL-X047hard2100.0 / 1002/2OK11.5s2.0k / 13k
CG-AL-X050hard262.5 / 1000/2OK11.0s2.0k / 8.1k
CG-AL-X051hard262.5 / 1000/2OK11.0s2.1k / 4.1k
CG-AL-X052hard1100.0 / 1003/3OK10.7s531 / 3.5k
CG-AL-X055hard1100.0 / 1005/5OK10.7s513 / 815
CG-AL-X056hard20.0 / 1000/0FAIL3.9s1.1k / 1.9k
CG-AL-X057hard1100.0 / 1005/5OK10.7s419 / 651
CG-AL-X058hard1100.0 / 1005/5OK10.8s481 / 1.5k
CG-AL-X059hard1100.0 / 1003/3OK11.3s496 / 3.1k
CG-AL-X060hard1100.0 / 1003/3OK10.5s471 / 590
CG-AL-X061hard1100.0 / 1004/4OK12.4s533 / 477
CG-AL-X062hard1100.0 / 1004/4OK10.5s527 / 1.7k
CG-AL-X063hard2100.0 / 1003/3OK10.9s1.2k / 2.0k
CG-AL-X064hard1100.0 / 1007/7OK10.4s446 / 1.5k
CG-AL-X065hard1100.0 / 1006/6OK11.0s885 / 2.2k
CG-AL-X066hard1100.0 / 10014/14OK10.8s1.4k / 2.8k
CG-AL-X067hard262.5 / 1006/7OK10.6s2.1k / 8.4k
CG-AL-X068hard20.0 / 1000/0FAIL0ms1.3k / 7.7k
CG-AL-X069hard2100.0 / 1008/8OK11.0s2.9k / 8.1k
CG-AL-X070hard1100.0 / 10012/12OK10.5s1.4k / 3.3k
CG-AL-X071hard20.0 / 1000/0FAIL0ms1.5k / 1.9k
CG-AL-X072hard1100.0 / 1007/7OK11.0s1.3k / 1.3k
CG-AL-X073hard1100.0 / 1008/8OK12.7s1.6k / 2.1k
CG-AL-X074hard20.0 / 1000/0FAIL3.8s521 / 3.2k
CG-AL-X075hard1100.0 / 1007/7OK10.8s988 / 1.6k
CG-AL-X076hard20.0 / 1000/0FAIL3.8s542 / 2.5k
CG-AL-X077hard1100.0 / 10022/22OK13.1s1.7k / 3.7k
CG-AL-X078hard1100.0 / 10017/17OK11.6s1.4k / 1.1k
CG-AL-X079hard2100.0 / 10011/11OK11.2s4.9k / 30k
CG-AL-X080hard20.0 / 1000/0FAIL3.9s2.8k / 5.3k
CG-AL-X081hard1100.0 / 1008/8OK10.9s1.1k / 897
CG-AL-X082hard1100.0 / 10015/15OK11.4s1.4k / 1.1k
CG-AL-X083hard1100.0 / 1009/9OK14.4s1.7k / 3.7k
CG-AL-X084hard2100.0 / 10010/10OK11.0s3.5k / 7.0k
CG-AL-X085hard1100.0 / 1007/7OK12.8s1.2k / 1.7k
CG-AL-X086hard1100.0 / 1006/6OK10.8s1.6k / 3.8k
CG-AL-X087hard1100.0 / 1003/3OK12.9s1.2k / 3.2k
CG-AL-X088hard1100.0 / 1006/6OK10.6s1.2k / 8.4k
CG-AL-X089hard20.0 / 1000/0FAIL3.8s2.8k / 28k
CG-AL-X090hard262.5 / 1006/10OK11.2s2.6k / 10.0k
CG-AL-X091hard1100.0 / 1006/6OK10.6s744 / 442
CG-AL-X092hard1100.0 / 10015/15OK10.7s615 / 559
CG-AL-X093hard262.5 / 1009/10OK11.2s2.7k / 8.9k
CG-AL-X094hard1100.0 / 1007/7OK10.4s932 / 832
CG-AL-X095hard1100.0 / 1005/5OK10.7s973 / 869
CG-AL-X096hard2100.0 / 10049/49OK11.3s7.5k / 21k
CG-AL-X097hard1100.0 / 10046/46OK11.4s3.6k / 4.5k
CG-AL-X098hard1100.0 / 10029/29OK10.9s2.8k / 2.7k
CG-AL-X099hard20.0 / 1000/0FAIL3.6s7.9k / 20k
CG-AL-X100hard1100.0 / 10035/35OK11.3s3.7k / 7.0k
CG-AL-X101hard1100.0 / 10010/10OK10.9s1.3k / 5.8k
CG-AL-X102hard20.0 / 1000/0FAIL3.8s2.6k / 7.1k
CG-AL-X103hard1100.0 / 1007/7OK10.6s897 / 1.0k
CG-AL-X104hard1100.0 / 1006/6OK10.4s1.2k / 1.1k
CG-AL-X105hard1100.0 / 1006/6OK10.7s950 / 1.0k
CG-AL-X106hard1100.0 / 1005/5OK10.8s1.1k / 3.2k
CG-AL-X107hard1100.0 / 1004/4OK11.1s980 / 881
CG-AL-X108hard1100.0 / 1006/6OK11.2s906 / 624
CG-AL-X109hard1100.0 / 1005/5OK10.7s722 / 2.0k
CG-AL-X110hard1100.0 / 10017/17OK11.1s1.4k / 1.4k
CG-AL-X111hard1100.0 / 1008/8OK11.2s1.4k / 3.6k
CG-AL-X112hard20.0 / 1000/0FAIL3.8s2.9k / 15k
CG-AL-X113hard2100.0 / 10013/13OK11.0s2.1k / 7.4k
CG-AL-X114hard1100.0 / 1007/7OK11.5s915 / 1.3k
CG-AL-X115hard2100.0 / 10013/13OK10.7s1.5k / 3.5k
CG-AL-X116hard262.5 / 1007/17OK11.4s8.1k / 20k
CG-AL-X117hard1100.0 / 1008/8OK12.6s1.2k / 1.2k
CG-AL-X118hard1100.0 / 10017/17OK11.2s1.6k / 4.6k
CG-AL-X119hard2100.0 / 10015/15OK11.0s4.4k / 4.5k
CG-AL-X120hard1100.0 / 10012/12OK10.9s1.5k / 1.5k
CG-AL-X121hard1100.0 / 1006/6OK10.7s1.2k / 1.2k
CG-AL-X122hard262.5 / 1006/10OK10.9s3.7k / 19k
CG-AL-X123hard1100.0 / 1005/5OK11.1s788 / 619
CG-AL-X124hard1100.0 / 10010/10OK11.6s1.2k / 1.2k
CG-AL-X125hard1100.0 / 1008/8OK11.6s1.6k / 5.1k
CG-AL-X126hard1100.0 / 10014/14OK11.5s897 / 4.1k
CG-AL-X127hard1100.0 / 1005/5OK11.2s863 / 793
CG-AL-X128hard1100.0 / 1008/8OK13.3s1.4k / 1.3k
CG-AL-X129hard1100.0 / 10014/14OK11.1s1.4k / 1.4k
CG-AL-X130hard20.0 / 1000/0FAIL0ms721 / 2.8k
CG-AL-X131hard1100.0 / 10013/13OK10.6s1.1k / 2.6k
CG-AL-X132hard1100.0 / 10010/10OK10.9s902 / 613
CG-AL-X133hard20.0 / 1000/0FAIL0ms1.8k / 11k
CG-AL-X134hard1100.0 / 1006/6OK11.2s1.4k / 5.3k
CG-AL-X135hard1100.0 / 1004/4OK10.7s1.1k / 914
CG-AL-X136hard1100.0 / 1007/7OK10.3s943 / 2.3k
CG-AL-X137hard1100.0 / 1004/4OK12.7s1.1k / 3.3k
CG-AL-X138hard2100.0 / 1009/9OK10.9s4.9k / 5.5k
CG-AL-X139hard1100.0 / 10011/11OK11.1s1.8k / 1.7k
CG-AL-X140hard262.5 / 1002/7OK11.6s4.5k / 28k
CG-AL-X141hard2100.0 / 10039/39OK11.6s8.9k / 16k
CG-AL-X142hard262.5 / 10044/48OK11.7s9.8k / 53k
CG-AL-X143hard1100.0 / 10035/35OK15.7s4.4k / 5.1k
CG-AL-X144hard1100.0 / 10043/43OK12.2s4.0k / 5.0k
CG-AL-X145hard1100.0 / 10032/32OK12.0s4.6k / 5.0k
CG-AL-X146hard20.0 / 1000/0FAIL0ms1.9k / 22k
CG-AL-X147hard1100.0 / 1008/8OK11.4s1.5k / 1.4k
CG-AL-X148hard1100.0 / 1006/6OK10.6s1.3k / 994
CG-AL-X149hard1100.0 / 1007/7OK10.4s1.4k / 1.9k
CG-AL-X150hard20.0 / 1000/0FAIL3.5s5.4k / 32k
CG-AL-X151hard1100.0 / 1006/6OK11.1s1.0k / 598
CG-AL-X152hard1100.0 / 1008/8OK10.8s1.3k / 1.5k
CG-AL-X153hard262.5 / 1007/9OK13.5s2.1k / 9.5k
CG-AL-X154hard1100.0 / 1009/9OK11.6s1.5k / 2.0k
CG-AL-X155hard1100.0 / 10011/11OK10.9s1.1k / 1.4k
CG-AL-X156hard1100.0 / 1007/7OK10.7s1.1k / 734
CG-AL-X157hard1100.0 / 10010/10OK10.8s1.5k / 1.4k
CG-AL-X158hard1100.0 / 1007/7OK10.7s1.0k / 601
CG-AL-X159hard1100.0 / 1007/7OK11.5s1.1k / 1.5k
CG-AL-X160hard1100.0 / 10013/13OK10.8s1.4k / 3.6k
CG-AL-X161hard1100.0 / 10010/10OK10.8s1.6k / 2.3k
CG-AL-X162hard1100.0 / 1007/7OK11.0s1.2k / 1.1k
CG-AL-X163hard1100.0 / 1007/7OK10.6s1.2k / 1.6k
CG-AL-X164hard1100.0 / 1007/7OK10.5s1.2k / 1.1k
CG-AL-X165hard1100.0 / 10013/13OK14.2s3.0k / 15k
CG-AL-X166hard2100.0 / 10014/14OK12.1s4.4k / 9.3k
CG-AL-X167hard1100.0 / 10013/13OK11.6s1.6k / 8.6k
CG-AL-X168hard262.5 / 1002/9OK11.1s5.5k / 35k
CG-AL-X169hard2100.0 / 10011/11OK11.8s4.5k / 21k
CG-AL-X170hard1100.0 / 10011/11OK11.6s3.4k / 18k
CG-AL-X171hard1100.0 / 1009/9OK11.4s1.6k / 24k
CG-AL-X172hard1100.0 / 10011/11OK11.4s2.5k / 22k
CG-AL-X173hard20.0 / 1000/0FAIL0ms3.4k / 13k
CG-AL-X174hard1100.0 / 10016/16OK11.8s4.2k / 13k
CG-AL-X185hard2100.0 / 10043/43OK11.4s7.3k / 11k
CG-AL-X187hard20.0 / 1000/0FAIL3.6s8.1k / 28k
CG-AL-X194hard262.5 / 10044/50OK11.5s13k / 35k
CG-AL-X211hard262.5 / 10034/43OK11.7s8.4k / 51k
CG-AL-X214hard262.5 / 10031/34OK11.8s8.7k / 20k
CG-AL-X218hard262.5 / 10024/27OK11.1s8.5k / 19k
CG-AL-X234hard2100.0 / 10035/35OK11.7s9.7k / 39k
CG-AL-X239hard2100.0 / 10037/37OK12.0s11k / 36k
CG-AL-X244hard262.5 / 10035/38OK11.8s14k / 37k
CG-AL-X245hard262.5 / 10047/63OK12.4s13k / 26k
CG-AL-X248hard262.5 / 10065/66OK11.9s15k / 37k
CG-AL-X249hard262.5 / 10032/37OK12.0s10k / 43k
CG-AL-X254hard20.0 / 1000/0FAIL3.8s1.1k / 19k
CG-AL-X257hard262.5 / 10045/53OK11.7s9.0k / 24k
CG-AL-X263hard262.5 / 10054/61OK12.2s10k / 47k
CG-AL-X264hard20.0 / 1000/0FAIL4.0s1.1k / 33k
CG-AL-X270hard262.5 / 10049/63OK12.9s21k / 38k
CG-AL-X271hard262.5 / 10058/70OK12.4s16k / 31k
CG-AL-X272hard262.5 / 10065/79OK12.7s13k / 65k
CG-AL-X274hard20.0 / 1000/0FAIL4.2s14k / 33k
CG-AL-X276hard262.5 / 10062/78OK12.3s16k / 36k
CG-AL-X278hard2100.0 / 10071/71OK12.8s15k / 40k
CG-AL-X283hard20.0 / 1000/0FAIL4.0s14k / 58k
CG-AL-X289hard20.0 / 1000/0FAIL4.5s974 / 39k
CG-AL-X290hard2100.0 / 10047/47OK12.7s14k / 23k
CG-AL-X292hard2100.0 / 10057/57OK12.7s13k / 19k
CG-AL-X293hard262.5 / 10045/49OK12.0s9.5k / 40k
CG-AL-X296hard262.5 / 10046/47OK12.2s17k / 44k
CG-AL-X298hard20.0 / 1000/0FAIL0ms4.7k / 27k