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.

64.2% 149/232 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.

60.5 / 100
Cost $3.02
Tokens 703k / 2.3M input / output, all attempts
Duration 57m 19s
Filter:
Per-task results for run c7cc50ad-0d94-4581-bc65-5f3a84b26651
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK12.2s427 / 572
CG-AL-E006easy20.0 / 1000/0FAIL9.8s1.4k / 4.5k
CG-AL-E010easy2100.0 / 1005/5OK34.1s1.0k / 2.5k
CG-AL-E050easy20.0 / 1000/0FAIL9.7s2.1k / 2.7k
CG-AL-E052easy1100.0 / 10016/16OK11.0s521 / 620
CG-AL-E054easy20.0 / 1000/0FAIL8.5s1.4k / 1.9k
CG-AL-E056easy262.5 / 10014/15OK27.1s3.0k / 10k
CG-AL-H007hard20.0 / 1000/0FAIL4.2s2.2k / 6.1k
CG-AL-H011hard20.0 / 1000/0FAIL3.7s1.4k / 6.0k
CG-AL-H014hard20.0 / 1000/0FAIL3.8s1.9k / 3.1k
CG-AL-H017hard1100.0 / 1005/5OK16.2s526 / 3.0k
CG-AL-H020hard2100.0 / 10010/10OK12.3s2.5k / 15k
CG-AL-H021hard2100.0 / 10020/20OK29.5s15k / 9.0k
CG-AL-H023hard20.0 / 1000/0FAIL3.9s5.8k / 27k
CG-AL-H027hard20.0 / 1000/0FAIL4.4s2.0k / 7.9k
CG-AL-H029hard20.0 / 1000/0FAIL3.9s3.2k / 18k
CG-AL-H030hard20.0 / 1000/0FAIL3.8s2.2k / 19k
CG-AL-H031hard20.0 / 1000/0FAIL4.0s3.1k / 11k
CG-AL-H034hard2100.0 / 1003/3OK12.1s1.6k / 4.6k
CG-AL-H036hard1100.0 / 1005/5OK17.9s553 / 5.9k
CG-AL-H037hard20.0 / 1000/0FAIL4.3s1.5k / 1.9k
CG-AL-H041hard2100.0 / 1003/3OK11.5s1.8k / 15k
CG-AL-H050hard20.0 / 1000/0FAIL0ms669 / 6.1k
CG-AL-H054hard2100.0 / 1005/5OK11.5s2.4k / 5.8k
CG-AL-H056hard20.0 / 1000/0FAIL4.0s1.8k / 11k
CG-AL-M001medium262.5 / 1008/10OK26.2s1.7k / 10.0k
CG-AL-M003medium1100.0 / 1009/9OK12.3s588 / 6.1k
CG-AL-M004medium1100.0 / 10012/12OK35.0s623 / 2.8k
CG-AL-M006medium1100.0 / 10018/18OK11.4s577 / 6.1k
CG-AL-M007medium20.0 / 1000/0FAIL3.9s3.2k / 30k
CG-AL-M008medium20.0 / 1000/0FAIL4.4s4.4k / 25k
CG-AL-M009medium20.0 / 1000/0FAIL9.3s3.4k / 13k
CG-AL-M010medium1100.0 / 10021/21OK22.6s767 / 8.9k
CG-AL-M020medium20.0 / 1000/0FAIL4.1s2.4k / 4.5k
CG-AL-M023medium1100.0 / 10011/11OK11.6s650 / 1.3k
CG-AL-M025medium262.5 / 1002/8OK11.3s3.2k / 3.6k
CG-AL-M026medium262.5 / 1006/8OK11.2s1.4k / 2.4k
CG-AL-M027medium2100.0 / 10018/18OK11.0s3.9k / 7.0k
CG-AL-M028medium2100.0 / 1003/3OK28.9s1.4k / 4.8k
CG-AL-M031medium20.0 / 1000/0FAIL3.8s2.7k / 7.3k
CG-AL-M034medium266.7 / 1000/2OK11.1s1.9k / 4.3k
CG-AL-M036medium211.1 / 1000/0FAIL3.9s1.7k / 4.7k
CG-AL-M040medium20.0 / 1000/0FAIL3.6s1.1k / 8.4k
CG-AL-M042medium1100.0 / 1008/8OK10.5s667 / 2.4k
CG-AL-X001hard2100.0 / 1002/2OK11.0s1.3k / 2.2k
CG-AL-X002hard1100.0 / 1004/4OK11.9s655 / 13k
CG-AL-X003hard20.0 / 1000/0FAIL4.2s1.0k / 9.2k
CG-AL-X004medium1100.0 / 1003/3OK10.8s528 / 2.0k
CG-AL-X005hard1100.0 / 1002/2OK10.7s496 / 974
CG-AL-X006hard1100.0 / 1003/3OK11.1s553 / 2.5k
CG-AL-X007hard1100.0 / 1002/2OK1m 28s541 / 1.4k
CG-AL-X008hard20.0 / 1000/0FAIL3.9s1.7k / 7.8k
CG-AL-X009medium1100.0 / 1002/2OK10.9s482 / 2.5k
CG-AL-X010medium1100.0 / 1003/3OK10.8s453 / 1.1k
CG-AL-X011medium1100.0 / 1002/2OK10.5s532 / 465
CG-AL-X012hard1100.0 / 1001/1OK10.8s549 / 4.6k
CG-AL-X013hard2100.0 / 1002/2OK10.4s1.2k / 706
CG-AL-X014medium1100.0 / 1004/4OK11.5s461 / 945
CG-AL-X017medium2100.0 / 1003/3OK11.3s1.8k / 867
CG-AL-X018medium1100.0 / 1003/3OK10.9s554 / 1.1k
CG-AL-X019medium2100.0 / 1003/3OK11.0s2.1k / 4.3k
CG-AL-X022medium20.0 / 1000/0FAIL0ms445 / 600
CG-AL-X024medium2100.0 / 1003/3OK11.2s1.8k / 2.4k
CG-AL-X025medium1100.0 / 1001/1OK10.9s539 / 2.1k
CG-AL-X026medium1100.0 / 1003/3OK11.3s496 / 722
CG-AL-X027medium1100.0 / 1004/4OK11.0s427 / 1.3k
CG-AL-X029medium1100.0 / 1002/2OK10.7s446 / 1.5k
CG-AL-X030medium1100.0 / 1002/2OK10.7s408 / 191
CG-AL-X031medium1100.0 / 1003/3OK10.9s467 / 1.1k
CG-AL-X033hard1100.0 / 1002/2OK11.4s517 / 557
CG-AL-X034hard262.5 / 1000/3OK11.0s1.6k / 2.9k
CG-AL-X035hard2100.0 / 1003/3OK11.1s1.9k / 4.9k
CG-AL-X037hard2100.0 / 1004/4OK11.3s2.4k / 16k
CG-AL-X040hard262.5 / 1000/4OK11.4s1.7k / 7.4k
CG-AL-X041hard262.5 / 1000/5OK10.8s1.5k / 8.8k
CG-AL-X043hard20.0 / 1000/0FAIL3.8s2.0k / 21k
CG-AL-X044hard20.0 / 1000/0FAIL4.0s1.4k / 7.2k
CG-AL-X045hard1100.0 / 1003/3OK10.9s540 / 2.3k
CG-AL-X046hard2100.0 / 1002/2OK11.1s1.8k / 2.6k
CG-AL-X047hard20.0 / 1000/0FAIL4.1s1.7k / 15k
CG-AL-X050hard20.0 / 1000/0FAIL0ms575 / 1.0k
CG-AL-X051hard20.0 / 1000/0FAIL0ms679 / 3.4k
CG-AL-X052hard1100.0 / 1003/3OK10.5s531 / 6.9k
CG-AL-X055hard1100.0 / 1005/5OK10.5s513 / 759
CG-AL-X056hard2100.0 / 1005/5OK11.1s1.1k / 8.4k
CG-AL-X057hard1100.0 / 1005/5OK10.6s419 / 780
CG-AL-X058hard1100.0 / 1005/5OK10.7s481 / 1.1k
CG-AL-X059hard1100.0 / 1003/3OK11.1s496 / 476
CG-AL-X060hard262.5 / 1002/3OK11.0s1.3k / 11k
CG-AL-X061hard2100.0 / 1004/4OK10.8s1.7k / 771
CG-AL-X062hard1100.0 / 1004/4OK12.1s527 / 2.3k
CG-AL-X063hard1100.0 / 1003/3OK10.8s529 / 1.3k
CG-AL-X064hard1100.0 / 1007/7OK10.8s446 / 4.1k
CG-AL-X065hard1100.0 / 1006/6OK10.8s885 / 2.1k
CG-AL-X066hard1100.0 / 10014/14OK11.0s1.4k / 2.6k
CG-AL-X067hard262.5 / 1006/7OK10.6s2.2k / 7.8k
CG-AL-X068hard20.0 / 1000/0FAIL3.9s2.8k / 12k
CG-AL-X069hard1100.0 / 1008/8OK10.7s1.3k / 7.5k
CG-AL-X070hard1100.0 / 10012/12OK11.3s1.4k / 2.1k
CG-AL-X071hard20.0 / 1000/0FAIL0ms1.5k / 2.1k
CG-AL-X072hard1100.0 / 1007/7OK10.8s1.3k / 1.3k
CG-AL-X073hard1100.0 / 1008/8OK11.0s1.6k / 2.2k
CG-AL-X074hard20.0 / 1000/0FAIL3.8s521 / 1.5k
CG-AL-X075hard1100.0 / 1007/7OK15.6s988 / 1.4k
CG-AL-X076hard20.0 / 1000/0FAIL4.3s542 / 786
CG-AL-X077hard1100.0 / 10022/22OK10.9s1.7k / 4.5k
CG-AL-X078hard1100.0 / 10017/17OK11.2s1.4k / 1.1k
CG-AL-X079hard20.0 / 1000/0FAIL3.9s3.5k / 20k
CG-AL-X080hard262.5 / 1006/7OK11.0s2.8k / 8.0k
CG-AL-X081hard1100.0 / 1008/8OK16.8s1.1k / 1.2k
CG-AL-X082hard1100.0 / 10015/15OK11.1s1.4k / 1.2k
CG-AL-X083hard1100.0 / 1009/9OK10.8s1.7k / 2.1k
CG-AL-X084hard2100.0 / 10010/10OK11.8s3.6k / 13k
CG-AL-X085hard1100.0 / 1007/7OK10.9s1.2k / 1.7k
CG-AL-X086hard1100.0 / 1006/6OK11.3s1.6k / 2.5k
CG-AL-X087hard1100.0 / 1003/3OK10.8s1.2k / 2.5k
CG-AL-X088hard1100.0 / 1006/6OK11.1s1.2k / 5.2k
CG-AL-X089hard20.0 / 1000/0FAIL3.8s2.7k / 28k
CG-AL-X090hard20.0 / 1000/0FAIL3.6s3.2k / 28k
CG-AL-X091hard1100.0 / 1006/6OK10.8s744 / 1.2k
CG-AL-X092hard1100.0 / 10015/15OK10.8s615 / 5.7k
CG-AL-X093hard262.5 / 1008/10OK10.7s2.7k / 22k
CG-AL-X094hard1100.0 / 1007/7OK10.9s932 / 991
CG-AL-X095hard2100.0 / 1005/5OK11.4s2.5k / 5.4k
CG-AL-X096hard20.0 / 1000/0FAIL3.8s7.5k / 17k
CG-AL-X097hard1100.0 / 10046/46OK12.1s3.6k / 4.1k
CG-AL-X098hard1100.0 / 10029/29OK11.6s2.8k / 3.3k
CG-AL-X099hard1100.0 / 10039/39OK12.9s3.8k / 17k
CG-AL-X100hard1100.0 / 10035/35OK11.3s3.7k / 4.7k
CG-AL-X101hard1100.0 / 10010/10OK10.8s1.3k / 8.3k
CG-AL-X102hard2100.0 / 1008/8OK11.3s2.6k / 19k
CG-AL-X103hard1100.0 / 1007/7OK10.7s897 / 992
CG-AL-X104hard1100.0 / 1006/6OK10.7s1.2k / 2.0k
CG-AL-X105hard1100.0 / 1006/6OK11.2s950 / 553
CG-AL-X106hard1100.0 / 1005/5OK10.8s1.1k / 3.3k
CG-AL-X107hard1100.0 / 1004/4OK10.8s980 / 827
CG-AL-X108hard1100.0 / 1006/6OK12.0s906 / 868
CG-AL-X109hard1100.0 / 1005/5OK11.5s722 / 1.3k
CG-AL-X110hard1100.0 / 10017/17OK10.9s1.4k / 1.4k
CG-AL-X111hard1100.0 / 1008/8OK11.3s1.4k / 8.5k
CG-AL-X112hard1100.0 / 10012/12OK11.3s1.1k / 6.2k
CG-AL-X113hard1100.0 / 10013/13OK11.9s899 / 3.4k
CG-AL-X114hard1100.0 / 1007/7OK11.2s915 / 1.2k
CG-AL-X115hard2100.0 / 10013/13OK11.0s2.2k / 2.3k
CG-AL-X116hard262.5 / 10015/17OK11.3s4.6k / 14k
CG-AL-X117hard1100.0 / 1008/8OK11.2s1.2k / 1.1k
CG-AL-X118hard1100.0 / 10017/17OK11.3s1.6k / 5.9k
CG-AL-X119hard1100.0 / 10015/15OK12.0s2.0k / 1.8k
CG-AL-X120hard1100.0 / 10012/12OK11.2s1.5k / 2.8k
CG-AL-X121hard1100.0 / 1006/6OK11.3s1.2k / 948
CG-AL-X122hard20.0 / 1000/0FAIL0ms1.7k / 2.3k
CG-AL-X123hard1100.0 / 1005/5OK10.9s788 / 591
CG-AL-X124hard1100.0 / 10010/10OK11.0s1.2k / 1.1k
CG-AL-X125hard1100.0 / 1008/8OK11.0s1.6k / 7.4k
CG-AL-X126hard2100.0 / 10014/14OK10.8s6.5k / 13k
CG-AL-X127hard1100.0 / 1005/5OK11.5s863 / 796
CG-AL-X128hard1100.0 / 1008/8OK10.5s1.4k / 1.1k
CG-AL-X129hard1100.0 / 10014/14OK11.2s1.4k / 1.4k
CG-AL-X130hard262.5 / 1002/5OK11.1s1.8k / 10k
CG-AL-X131hard1100.0 / 10013/13OK11.6s1.1k / 3.6k
CG-AL-X132hard1100.0 / 10010/10OK12.3s902 / 666
CG-AL-X133hard20.0 / 1000/0FAIL0ms1.8k / 7.1k
CG-AL-X134hard1100.0 / 1006/6OK11.9s1.4k / 2.3k
CG-AL-X135hard1100.0 / 1004/4OK11.0s1.1k / 925
CG-AL-X136hard1100.0 / 1007/7OK10.8s943 / 2.8k
CG-AL-X137hard1100.0 / 1004/4OK11.8s1.1k / 3.5k
CG-AL-X138hard262.5 / 1004/9OK11.0s3.5k / 6.6k
CG-AL-X139hard1100.0 / 10011/11OK11.5s1.8k / 2.0k
CG-AL-X140hard262.5 / 1004/7OK10.9s4.5k / 35k
CG-AL-X141hard1100.0 / 10039/39OK12.2s3.9k / 5.2k
CG-AL-X142hard2100.0 / 10048/48OK12.3s9.8k / 38k
CG-AL-X143hard1100.0 / 10035/35OK16.3s4.4k / 6.2k
CG-AL-X144hard1100.0 / 10043/43OK11.4s4.0k / 4.3k
CG-AL-X145hard1100.0 / 10032/32OK11.8s4.6k / 5.0k
CG-AL-X146hard1100.0 / 1009/9OK10.9s1.9k / 23k
CG-AL-X147hard1100.0 / 1008/8OK10.8s1.5k / 1.4k
CG-AL-X148hard1100.0 / 1006/6OK11.9s1.3k / 1.0k
CG-AL-X149hard1100.0 / 1007/7OK11.0s1.4k / 1.9k
CG-AL-X150hard20.0 / 1000/0FAIL0ms2.2k / 18k
CG-AL-X151hard1100.0 / 1006/6OK10.7s1.0k / 615
CG-AL-X152hard1100.0 / 1008/8OK11.6s1.3k / 1.3k
CG-AL-X153hard262.5 / 1007/9OK14.5s2.1k / 9.2k
CG-AL-X154hard1100.0 / 1009/9OK10.9s1.5k / 1.5k
CG-AL-X155hard1100.0 / 10011/11OK11.2s1.1k / 1.7k
CG-AL-X156hard1100.0 / 1007/7OK10.8s1.1k / 774
CG-AL-X157hard1100.0 / 10010/10OK11.4s1.5k / 2.3k
CG-AL-X158hard1100.0 / 1007/7OK11.1s1.0k / 758
CG-AL-X159hard1100.0 / 1007/7OK11.3s1.1k / 998
CG-AL-X160hard1100.0 / 10013/13OK11.3s1.4k / 2.5k
CG-AL-X161hard1100.0 / 10010/10OK11.5s1.6k / 2.0k
CG-AL-X162hard1100.0 / 1007/7OK11.8s1.2k / 1.7k
CG-AL-X163hard1100.0 / 1007/7OK11.0s1.2k / 2.1k
CG-AL-X164hard1100.0 / 1007/7OK11.0s1.2k / 1.2k
CG-AL-X165hard1100.0 / 10013/13OK13.8s3.0k / 29k
CG-AL-X166hard1100.0 / 10014/14OK13.5s1.8k / 2.6k
CG-AL-X167hard1100.0 / 10013/13OK11.2s1.6k / 7.3k
CG-AL-X168hard262.5 / 1006/9OK11.6s3.9k / 33k
CG-AL-X169hard2100.0 / 10011/11OK12.0s4.3k / 9.2k
CG-AL-X170hard262.5 / 1007/11OK12.0s7.8k / 52k
CG-AL-X171hard262.5 / 1005/9OK11.4s4.9k / 27k
CG-AL-X172hard20.0 / 1000/0FAIL3.6s8.5k / 34k
CG-AL-X173hard262.5 / 10017/19OK12.3s7.4k / 23k
CG-AL-X174hard1100.0 / 10016/16OK11.7s4.2k / 18k
CG-AL-X185hard20.0 / 1000/0FAIL4.1s7.3k / 10k
CG-AL-X187hard262.5 / 10030/33OK12.2s7.3k / 20k
CG-AL-X194hard20.0 / 1000/0FAIL4.2s861 / 25k
CG-AL-X211hard2100.0 / 10043/43OK12.1s9.5k / 42k
CG-AL-X214hard262.5 / 10031/34OK12.1s8.6k / 30k
CG-AL-X218hard262.5 / 10024/27OK11.9s8.4k / 24k
CG-AL-X234hard2100.0 / 10035/35OK12.1s9.6k / 36k
CG-AL-X239hard262.5 / 10034/37OK12.3s11k / 35k
CG-AL-X244hard262.5 / 10035/38OK12.2s14k / 32k
CG-AL-X245hard262.5 / 10059/63OK12.2s15k / 28k
CG-AL-X248hard2100.0 / 10066/66OK12.4s13k / 28k
CG-AL-X249hard2100.0 / 10037/37OK11.9s10k / 49k
CG-AL-X254hard2100.0 / 10070/70OK12.5s13k / 20k
CG-AL-X257hard262.5 / 10046/53OK12.4s9.1k / 35k
CG-AL-X263hard2100.0 / 10061/61OK12.7s11k / 31k
CG-AL-X264hard20.0 / 1000/0FAIL3.6s13k / 50k
CG-AL-X270hard262.5 / 10056/63OK12.8s22k / 38k
CG-AL-X271hard20.0 / 1000/0FAIL4.0s1.1k / 26k
CG-AL-X272hard262.5 / 10063/79OK13.0s19k / 45k
CG-AL-X274hard20.0 / 1000/0FAIL4.1s1.1k / 34k
CG-AL-X276hard2100.0 / 10078/78OK13.5s16k / 36k
CG-AL-X278hard262.5 / 10068/71OK13.2s16k / 39k
CG-AL-X283hard20.0 / 1000/0FAIL4.2s18k / 55k
CG-AL-X289hard20.0 / 1000/0FAIL4.1s987 / 31k
CG-AL-X290hard262.5 / 10041/47OK12.4s14k / 42k
CG-AL-X292hard2100.0 / 10057/57OK12.5s11k / 27k
CG-AL-X293hard20.0 / 1000/0FAIL3.9s13k / 27k
CG-AL-X296hard262.5 / 10046/47OK12.6s17k / 40k
CG-AL-X298hard262.5 / 10034/55OK12.3s9.3k / 49k