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.

90.1% 209/232 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.

79.4 / 100
Cost $43.03
Tokens 1.0M / 1.5M input / output, all attempts
Duration 56m 44s
Filter:
Per-task results for run 587bcd89-9bcd-4160-9791-3e15910ed072
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK10.9s413 / 843
CG-AL-E006easy2100.0 / 1007/7OK33.6s1.7k / 1.7k
CG-AL-E010easy1100.0 / 1005/5OK11.3s466 / 294
CG-AL-E050easy2100.0 / 10013/13OK17.6s3.0k / 2.2k
CG-AL-E052easy1100.0 / 10016/16OK11.1s610 / 911
CG-AL-E054easy2100.0 / 1009/9OK17.6s2.0k / 2.3k
CG-AL-E056easy2100.0 / 10015/15OK17.5s3.7k / 3.2k
CG-AL-H007hard1100.0 / 10011/11OK10.7s947 / 3.0k
CG-AL-H011hard20.0 / 1000/0FAIL9.0s1.7k / 3.2k
CG-AL-H014hard20.0 / 1000/0FAIL4.4s3.3k / 4.0k
CG-AL-H017hard2100.0 / 1005/5OK10.6s1.9k / 2.5k
CG-AL-H020hard2100.0 / 10010/10OK12.1s3.5k / 3.4k
CG-AL-H021hard1100.0 / 10020/20OK11.4s1.0k / 2.0k
CG-AL-H023hard1100.0 / 10025/25OK11.5s2.0k / 24k
CG-AL-H027hard1100.0 / 1004/4OK11.1s1.1k / 1.5k
CG-AL-H029hard1100.0 / 10018/18OK11.1s1.3k / 7.3k
CG-AL-H030hard2100.0 / 10010/10OK10.9s4.3k / 4.9k
CG-AL-H031hard1100.0 / 10022/22OK11.3s1.6k / 3.1k
CG-AL-H034hard1100.0 / 1003/3OK10.7s720 / 3.7k
CG-AL-H036hard2100.0 / 1005/5OK10.9s1.6k / 2.3k
CG-AL-H037hard1100.0 / 1003/3OK11.1s805 / 818
CG-AL-H041hard1100.0 / 1003/3OK10.6s923 / 3.1k
CG-AL-H050hard2100.0 / 1003/3OK10.8s2.7k / 6.4k
CG-AL-H054hard2100.0 / 1005/5OK10.6s3.4k / 3.1k
CG-AL-H056hard20.0 / 1000/0FAIL4.1s2.4k / 603
CG-AL-M001medium20.0 / 1000/0FAIL4.7s2.3k / 2.5k
CG-AL-M003medium262.5 / 1000/1OK26.3s4.0k / 7.5k
CG-AL-M004medium262.5 / 10010/12OK28.7s4.8k / 7.4k
CG-AL-M006medium2100.0 / 10018/18OK11.6s6.5k / 15k
CG-AL-M007medium262.5 / 10013/15OK13.1s9.0k / 22k
CG-AL-M008medium2100.0 / 10012/12OK12.0s23k / 66k
CG-AL-M009medium1100.0 / 10011/11OK10.9s746 / 17k
CG-AL-M010medium1100.0 / 10021/21OK52.6s958 / 6.8k
CG-AL-M020medium2100.0 / 10017/17OK10.5s3.7k / 3.9k
CG-AL-M023medium1100.0 / 10011/11OK11.2s803 / 1.2k
CG-AL-M025medium262.5 / 1002/8OK11.4s5.2k / 7.2k
CG-AL-M026medium1100.0 / 1008/8OK10.6s624 / 949
CG-AL-M027medium2100.0 / 10018/18OK10.5s6.9k / 6.5k
CG-AL-M028medium211.1 / 1000/0FAIL3.8s1.8k / 1.5k
CG-AL-M031medium2100.0 / 1002/2OK10.2s3.5k / 2.4k
CG-AL-M034medium1100.0 / 1002/2OK11.2s695 / 1.4k
CG-AL-M036medium2100.0 / 1002/2OK10.2s2.7k / 1.5k
CG-AL-M040medium20.0 / 1000/0FAIL3.9s1.3k / 1.6k
CG-AL-M042medium1100.0 / 1008/8OK12.3s753 / 2.7k
CG-AL-X001hard2100.0 / 1002/2OK10.6s1.4k / 703
CG-AL-X002hard1100.0 / 1004/4OK11.1s728 / 2.4k
CG-AL-X003hard2100.0 / 1003/3OK10.4s1.9k / 3.8k
CG-AL-X004medium1100.0 / 1003/3OK12.1s551 / 1.3k
CG-AL-X005hard1100.0 / 1002/2OK11.0s515 / 569
CG-AL-X006hard1100.0 / 1003/3OK11.1s603 / 671
CG-AL-X007hard1100.0 / 1002/2OK1m 22s575 / 575
CG-AL-X008hard1100.0 / 1001/1OK10.8s641 / 2.2k
CG-AL-X009medium1100.0 / 1002/2OK11.0s493 / 309
CG-AL-X010medium1100.0 / 1003/3OK10.9s449 / 200
CG-AL-X011medium1100.0 / 1002/2OK11.2s557 / 490
CG-AL-X012hard1100.0 / 1001/1OK11.0s589 / 847
CG-AL-X013hard1100.0 / 1002/2OK10.7s423 / 270
CG-AL-X014medium1100.0 / 1004/4OK10.9s458 / 295
CG-AL-X017medium2100.0 / 1003/3OK10.5s2.4k / 524
CG-AL-X018medium1100.0 / 1003/3OK10.5s606 / 419
CG-AL-X019medium2100.0 / 1003/3OK10.5s2.9k / 4.1k
CG-AL-X022medium1100.0 / 1003/3OK10.7s441 / 710
CG-AL-X024medium1100.0 / 1003/3OK10.7s541 / 603
CG-AL-X025medium1100.0 / 1001/1OK11.0s601 / 799
CG-AL-X026medium1100.0 / 1003/3OK10.6s524 / 226
CG-AL-X027medium1100.0 / 1004/4OK10.6s424 / 377
CG-AL-X029medium2100.0 / 1002/2OK10.4s844 / 2.0k
CG-AL-X030medium1100.0 / 1002/2OK10.4s408 / 1.0k
CG-AL-X031medium1100.0 / 1003/3OK10.8s465 / 182
CG-AL-X033hard1100.0 / 1002/2OK10.8s558 / 278
CG-AL-X034hard1100.0 / 1003/3OK10.5s486 / 716
CG-AL-X035hard1100.0 / 1003/3OK10.5s523 / 495
CG-AL-X037hard1100.0 / 1004/4OK10.9s646 / 4.5k
CG-AL-X040hard262.5 / 1000/4OK10.4s2.7k / 11k
CG-AL-X041hard262.5 / 1000/5OK10.7s1.9k / 5.7k
CG-AL-X043hard2100.0 / 1001/1OK15.5s2.5k / 31k
CG-AL-X044hard262.5 / 1001/3OK10.6s2.2k / 9.3k
CG-AL-X045hard1100.0 / 1003/3OK10.7s602 / 471
CG-AL-X046hard1100.0 / 1002/2OK10.7s569 / 1.1k
CG-AL-X047hard1100.0 / 1002/2OK10.7s650 / 2.5k
CG-AL-X050hard1100.0 / 1002/2OK11.4s658 / 1.3k
CG-AL-X051hard2100.0 / 1002/2OK10.3s2.9k / 7.5k
CG-AL-X052hard1100.0 / 1003/3OK10.7s582 / 1.3k
CG-AL-X055hard2100.0 / 1005/5OK10.2s3.3k / 1.6k
CG-AL-X056hard1100.0 / 1005/5OK10.5s447 / 383
CG-AL-X057hard1100.0 / 1005/5OK10.5s411 / 253
CG-AL-X058hard1100.0 / 1005/5OK10.8s500 / 484
CG-AL-X059hard1100.0 / 1003/3OK10.9s511 / 130
CG-AL-X060hard2100.0 / 1003/3OK10.6s1.2k / 608
CG-AL-X061hard1100.0 / 1004/4OK10.6s572 / 174
CG-AL-X062hard1100.0 / 1004/4OK10.7s601 / 840
CG-AL-X063hard1100.0 / 1003/3OK10.7s559 / 1.0k
CG-AL-X064hard1100.0 / 1007/7OK10.4s457 / 624
CG-AL-X065hard1100.0 / 1006/6OK10.5s1.2k / 1.5k
CG-AL-X066hard1100.0 / 10014/14OK10.8s2.2k / 1.9k
CG-AL-X067hard2100.0 / 1007/7OK10.7s2.9k / 12k
CG-AL-X068hard1100.0 / 10012/12OK11.1s1.9k / 2.3k
CG-AL-X069hard1100.0 / 1008/8OK10.9s1.9k / 2.6k
CG-AL-X070hard1100.0 / 10012/12OK11.6s1.9k / 2.9k
CG-AL-X071hard1100.0 / 1008/8OK11.3s2.2k / 2.1k
CG-AL-X072hard1100.0 / 1007/7OK10.9s2.1k / 1.6k
CG-AL-X073hard1100.0 / 1008/8OK11.1s2.5k / 2.8k
CG-AL-X074hard2100.0 / 1007/7OK10.3s6.3k / 25k
CG-AL-X075hard1100.0 / 1007/7OK11.0s1.4k / 1.8k
CG-AL-X076hard1100.0 / 10014/14OK11.4s1.6k / 3.9k
CG-AL-X077hard1100.0 / 10022/22OK10.9s2.6k / 2.3k
CG-AL-X078hard1100.0 / 10017/17OK11.2s2.0k / 1.6k
CG-AL-X079hard1100.0 / 10011/11OK11.3s2.0k / 1.9k
CG-AL-X080hard2100.0 / 1007/7OK10.2s4.0k / 4.3k
CG-AL-X081hard1100.0 / 1008/8OK10.9s1.5k / 1.3k
CG-AL-X082hard1100.0 / 10015/15OK10.9s2.1k / 1.9k
CG-AL-X083hard1100.0 / 1009/9OK10.7s2.8k / 2.4k
CG-AL-X084hard1100.0 / 10010/10OK11.0s2.5k / 3.4k
CG-AL-X085hard1100.0 / 1007/7OK10.5s1.6k / 1.5k
CG-AL-X086hard1100.0 / 1006/6OK10.7s2.4k / 2.9k
CG-AL-X087hard1100.0 / 1003/3OK10.7s1.8k / 2.0k
CG-AL-X088hard1100.0 / 1006/6OK10.9s1.7k / 1.9k
CG-AL-X089hard1100.0 / 10011/11OK11.0s1.8k / 2.6k
CG-AL-X090hard262.5 / 1009/10OK10.4s3.8k / 12k
CG-AL-X091hard1100.0 / 1006/6OK10.7s941 / 737
CG-AL-X092hard1100.0 / 10015/15OK10.7s716 / 413
CG-AL-X093hard1100.0 / 10010/10OK10.6s1.7k / 1.4k
CG-AL-X094hard1100.0 / 1007/7OK10.7s1.3k / 1.1k
CG-AL-X095hard1100.0 / 1005/5OK10.8s1.3k / 1.0k
CG-AL-X096hard20.0 / 1000/0FAIL4.0s6.7k / 4.1k
CG-AL-X097hard1100.0 / 10046/46OK10.9s6.0k / 5.5k
CG-AL-X098hard1100.0 / 10029/29OK11.2s4.8k / 4.2k
CG-AL-X099hard2100.0 / 10039/39OK12.5s14k / 14k
CG-AL-X100hard1100.0 / 10035/35OK10.7s6.0k / 5.7k
CG-AL-X101hard1100.0 / 10010/10OK10.4s1.9k / 2.1k
CG-AL-X102hard1100.0 / 1008/8OK10.4s884 / 1.2k
CG-AL-X103hard1100.0 / 1007/7OK10.2s1.2k / 826
CG-AL-X104hard1100.0 / 1006/6OK10.4s1.7k / 1.4k
CG-AL-X105hard1100.0 / 1006/6OK10.5s1.3k / 829
CG-AL-X106hard20.0 / 1000/0FAIL3.7s2.0k / 2.9k
CG-AL-X107hard1100.0 / 1004/4OK15.4s1.4k / 1.6k
CG-AL-X108hard1100.0 / 1006/6OK16.7s1.2k / 726
CG-AL-X109hard1100.0 / 1005/5OK16.4s916 / 626
CG-AL-X110hard1100.0 / 10017/17OK16.5s2.1k / 1.7k
CG-AL-X111hard1100.0 / 1008/8OK16.5s2.0k / 2.5k
CG-AL-X112hard1100.0 / 10012/12OK11.0s1.5k / 3.1k
CG-AL-X113hard1100.0 / 10013/13OK11.7s1.3k / 1.0k
CG-AL-X114hard1100.0 / 1007/7OK11.5s1.2k / 891
CG-AL-X115hard1100.0 / 10013/13OK11.4s793 / 1.1k
CG-AL-X116hard1100.0 / 10017/17OK11.4s1.5k / 1.8k
CG-AL-X117hard1100.0 / 1008/8OK11.7s1.7k / 1.6k
CG-AL-X118hard1100.0 / 10017/17OK11.8s2.4k / 3.9k
CG-AL-X119hard1100.0 / 10015/15OK11.7s2.8k / 2.7k
CG-AL-X120hard1100.0 / 10012/12OK11.2s2.2k / 2.0k
CG-AL-X121hard1100.0 / 1006/6OK11.1s1.7k / 1.4k
CG-AL-X122hard1100.0 / 10010/10OK11.1s2.6k / 2.8k
CG-AL-X123hard1100.0 / 1005/5OK11.0s981 / 748
CG-AL-X124hard1100.0 / 10010/10OK10.9s1.7k / 1.3k
CG-AL-X125hard1100.0 / 1008/8OK10.6s2.3k / 2.1k
CG-AL-X126hard1100.0 / 10014/14OK11.2s1.2k / 1.1k
CG-AL-X127hard1100.0 / 1005/5OK10.5s1.1k / 661
CG-AL-X128hard1100.0 / 1008/8OK10.5s2.0k / 1.5k
CG-AL-X129hard1100.0 / 10014/14OK10.7s2.0k / 2.0k
CG-AL-X130hard1100.0 / 1005/5OK10.3s845 / 1.2k
CG-AL-X131hard1100.0 / 10013/13OK10.4s1.6k / 1.5k
CG-AL-X132hard1100.0 / 10010/10OK10.4s1.2k / 826
CG-AL-X133hard2100.0 / 1008/8OK10.4s6.2k / 14k
CG-AL-X134hard1100.0 / 1006/6OK11.6s2.0k / 2.2k
CG-AL-X135hard1100.0 / 1004/4OK10.8s1.4k / 969
CG-AL-X136hard1100.0 / 1007/7OK11.8s1.2k / 825
CG-AL-X137hard1100.0 / 1004/4OK11.0s1.5k / 1.6k
CG-AL-X138hard1100.0 / 1009/9OK11.1s2.4k / 2.8k
CG-AL-X139hard1100.0 / 10011/11OK11.2s2.8k / 2.7k
CG-AL-X140hard1100.0 / 1007/7OK10.9s2.5k / 11k
CG-AL-X141hard1100.0 / 10039/39OK11.6s6.1k / 5.5k
CG-AL-X142hard1100.0 / 10048/48OK12.0s6.8k / 13k
CG-AL-X143hard1100.0 / 10035/35OK16.1s7.2k / 6.9k
CG-AL-X144hard1100.0 / 10043/43OK11.7s6.4k / 6.2k
CG-AL-X145hard1100.0 / 10032/32OK11.7s7.4k / 7.2k
CG-AL-X146hard1100.0 / 1009/9OK10.8s2.9k / 6.7k
CG-AL-X147hard1100.0 / 1008/8OK10.6s2.2k / 1.9k
CG-AL-X148hard1100.0 / 1006/6OK10.9s1.9k / 1.4k
CG-AL-X149hard1100.0 / 1007/7OK10.9s1.9k / 1.6k
CG-AL-X150hard1100.0 / 1009/9OK11.1s3.2k / 8.6k
CG-AL-X151hard1100.0 / 1006/6OK10.5s1.4k / 951
CG-AL-X152hard1100.0 / 1008/8OK10.3s1.9k / 1.5k
CG-AL-X153hard1100.0 / 1009/9OK14.5s1.5k / 2.0k
CG-AL-X154hard1100.0 / 1009/9OK10.8s2.1k / 2.1k
CG-AL-X155hard1100.0 / 10011/11OK10.6s1.5k / 1.4k
CG-AL-X156hard1100.0 / 1007/7OK10.7s1.5k / 942
CG-AL-X157hard1100.0 / 10010/10OK11.0s2.2k / 1.6k
CG-AL-X158hard1100.0 / 1007/7OK10.5s1.3k / 761
CG-AL-X159hard1100.0 / 1007/7OK12.1s1.4k / 993
CG-AL-X160hard1100.0 / 10013/13OK12.0s2.0k / 2.4k
CG-AL-X161hard1100.0 / 10010/10OK11.1s2.4k / 2.4k
CG-AL-X162hard1100.0 / 1007/7OK11.1s1.6k / 1.3k
CG-AL-X163hard1100.0 / 1007/7OK11.3s1.7k / 1.4k
CG-AL-X164hard1100.0 / 1007/7OK11.0s1.5k / 1.1k
CG-AL-X165hard2100.0 / 10013/13OK13.4s11k / 15k
CG-AL-X166hard1100.0 / 10014/14OK11.7s2.7k / 2.2k
CG-AL-X167hard20.0 / 1000/0FAIL4.0s5.5k / 12k
CG-AL-X168hard1100.0 / 1009/9OK12.2s2.2k / 10k
CG-AL-X169hard2100.0 / 10011/11OK11.4s6.6k / 6.6k
CG-AL-X170hard1100.0 / 10011/11OK11.2s5.2k / 13k
CG-AL-X171hard1100.0 / 1009/9OK10.8s2.5k / 7.3k
CG-AL-X172hard1100.0 / 10011/11OK11.3s3.8k / 8.4k
CG-AL-X173hard2100.0 / 10019/19OK11.6s12k / 30k
CG-AL-X174hard1100.0 / 10016/16OK12.3s6.8k / 6.9k
CG-AL-X185hard262.5 / 10041/43OK10.9s12k / 9.1k
CG-AL-X187hard2100.0 / 10033/33OK11.2s13k / 49k
CG-AL-X194hard262.5 / 10049/50OK11.1s18k / 18k
CG-AL-X211hard2100.0 / 10043/43OK11.4s14k / 22k
CG-AL-X214hard2100.0 / 10034/34OK11.3s13k / 18k
CG-AL-X218hard262.5 / 10022/27OK11.2s14k / 33k
CG-AL-X234hard2100.0 / 10035/35OK11.2s16k / 13k
CG-AL-X239hard2100.0 / 10037/37OK11.6s19k / 28k
CG-AL-X244hard262.5 / 10037/38OK11.3s21k / 46k
CG-AL-X245hard2100.0 / 10063/63OK11.6s20k / 12k
CG-AL-X248hard2100.0 / 10066/66OK11.7s17k / 9.9k
CG-AL-X249hard2100.0 / 10037/37OK11.3s17k / 39k
CG-AL-X254hard2100.0 / 10070/70OK11.9s23k / 13k
CG-AL-X257hard2100.0 / 10053/53OK11.0s15k / 38k
CG-AL-X263hard2100.0 / 10061/61OK11.9s18k / 16k
CG-AL-X264hard2100.0 / 10065/65OK11.7s20k / 29k
CG-AL-X270hard2100.0 / 10063/63OK12.1s28k / 39k
CG-AL-X271hard2100.0 / 10070/70OK12.6s30k / 37k
CG-AL-X272hard262.5 / 10078/79OK11.6s23k / 18k
CG-AL-X274hard2100.0 / 10064/64OK12.1s24k / 21k
CG-AL-X276hard2100.0 / 10078/78OK12.0s24k / 14k
CG-AL-X278hard2100.0 / 10071/71OK12.6s24k / 30k
CG-AL-X283hard2100.0 / 10076/76OK11.7s25k / 14k
CG-AL-X289hard2100.0 / 10057/57OK11.6s21k / 43k
CG-AL-X290hard2100.0 / 10047/47OK11.8s21k / 16k
CG-AL-X292hard2100.0 / 10057/57OK12.0s19k / 17k
CG-AL-X293hard2100.0 / 10049/49OK11.4s18k / 13k
CG-AL-X296hard2100.0 / 10047/47OK11.6s25k / 35k
CG-AL-X298hard20.0 / 1000/0FAIL3.5s15k / 29k