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.

94.0% 218/232 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.

83.5 / 100
Cost $41.73
Tokens 1.0M / 1.5M input / output, all attempts
Duration 1h 0m
Filter:
Per-task results for run ae78164d-4412-4329-81e6-f6de6a8f0c7c
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy2100.0 / 1007/7OK17.3s1.4k / 954
CG-AL-E006easy2100.0 / 1007/7OK32.9s1.9k / 1.8k
CG-AL-E010easy1100.0 / 1005/5OK25.6s466 / 232
CG-AL-E050easy2100.0 / 10013/13OK16.9s3.4k / 4.1k
CG-AL-E052easy1100.0 / 10016/16OK23.4s610 / 901
CG-AL-E054easy2100.0 / 1009/9OK17.5s2.1k / 2.4k
CG-AL-E056easy2100.0 / 10015/15OK17.5s3.7k / 3.0k
CG-AL-H007hard1100.0 / 10011/11OK16.6s947 / 2.1k
CG-AL-H011hard20.0 / 1000/0FAIL3.8s1.7k / 2.0k
CG-AL-H014hard20.0 / 1000/0FAIL4.0s3.0k / 4.2k
CG-AL-H017hard2100.0 / 1005/5OK11.2s1.8k / 2.0k
CG-AL-H020hard2100.0 / 10010/10OK10.4s3.5k / 4.4k
CG-AL-H021hard1100.0 / 10020/20OK11.2s1.0k / 1.9k
CG-AL-H023hard2100.0 / 10025/25OK11.0s14k / 40k
CG-AL-H027hard1100.0 / 1004/4OK11.4s1.1k / 1.8k
CG-AL-H029hard1100.0 / 10018/18OK13.7s1.3k / 3.1k
CG-AL-H030hard1100.0 / 10010/10OK10.8s1.1k / 4.0k
CG-AL-H031hard1100.0 / 10022/22OK11.5s1.6k / 2.4k
CG-AL-H034hard1100.0 / 1003/3OK10.7s720 / 1.6k
CG-AL-H036hard2100.0 / 1005/5OK10.2s1.6k / 2.4k
CG-AL-H037hard1100.0 / 1003/3OK10.5s805 / 714
CG-AL-H041hard1100.0 / 1003/3OK10.4s923 / 2.9k
CG-AL-H050hard262.5 / 1002/3OK10.6s2.5k / 4.3k
CG-AL-H054hard2100.0 / 1005/5OK10.2s3.4k / 2.8k
CG-AL-H056hard2100.0 / 1004/4OK10.2s2.6k / 2.9k
CG-AL-M001medium2100.0 / 10010/10OK23.6s2.4k / 11k
CG-AL-M003medium262.5 / 1000/1OK26.5s4.0k / 7.2k
CG-AL-M004medium2100.0 / 10012/12OK33.5s4.6k / 6.8k
CG-AL-M006medium2100.0 / 10018/18OK11.3s6.2k / 12k
CG-AL-M007medium20.0 / 1000/0FAIL4.2s9.5k / 30k
CG-AL-M008medium262.5 / 1003/12OK12.6s14k / 46k
CG-AL-M009medium2100.0 / 10011/11OK10.3s12k / 26k
CG-AL-M010medium1100.0 / 10021/21OK48.1s958 / 8.4k
CG-AL-M020medium2100.0 / 10017/17OK10.7s3.7k / 4.3k
CG-AL-M023medium1100.0 / 10011/11OK11.2s803 / 951
CG-AL-M025medium1100.0 / 1008/8OK10.5s655 / 1.5k
CG-AL-M026medium1100.0 / 1008/8OK10.6s624 / 1.5k
CG-AL-M027medium2100.0 / 10018/18OK10.3s6.8k / 5.6k
CG-AL-M028medium2100.0 / 1003/3OK49.2s1.8k / 1.4k
CG-AL-M031medium2100.0 / 1002/2OK10.4s3.4k / 2.9k
CG-AL-M034medium1100.0 / 1002/2OK10.3s695 / 747
CG-AL-M036medium2100.0 / 1002/2OK10.3s2.8k / 1.8k
CG-AL-M040medium20.0 / 1000/0FAIL3.8s1.4k / 2.1k
CG-AL-M042medium1100.0 / 1008/8OK10.5s753 / 1.1k
CG-AL-X001hard2100.0 / 1002/2OK10.4s2.0k / 723
CG-AL-X002hard1100.0 / 1004/4OK10.5s728 / 2.2k
CG-AL-X003hard2100.0 / 1003/3OK10.3s1.8k / 3.5k
CG-AL-X004medium1100.0 / 1003/3OK10.5s551 / 1.5k
CG-AL-X005hard1100.0 / 1002/2OK10.6s515 / 1.4k
CG-AL-X006hard1100.0 / 1003/3OK10.8s603 / 574
CG-AL-X007hard1100.0 / 1002/2OK1m 22s575 / 1.2k
CG-AL-X008hard1100.0 / 1001/1OK10.7s641 / 2.4k
CG-AL-X009medium1100.0 / 1002/2OK10.5s493 / 464
CG-AL-X010medium1100.0 / 1003/3OK10.9s449 / 172
CG-AL-X011medium1100.0 / 1002/2OK10.3s557 / 497
CG-AL-X012hard1100.0 / 1001/1OK10.5s589 / 3.6k
CG-AL-X013hard1100.0 / 1002/2OK10.3s423 / 298
CG-AL-X014medium1100.0 / 1004/4OK10.3s458 / 331
CG-AL-X017medium2100.0 / 1003/3OK10.0s2.4k / 603
CG-AL-X018medium1100.0 / 1003/3OK10.3s606 / 616
CG-AL-X019medium2100.0 / 1003/3OK10.7s2.9k / 2.2k
CG-AL-X022medium1100.0 / 1003/3OK10.3s441 / 904
CG-AL-X024medium2100.0 / 1003/3OK10.2s1.3k / 863
CG-AL-X025medium1100.0 / 1001/1OK10.5s601 / 811
CG-AL-X026medium1100.0 / 1003/3OK10.4s524 / 210
CG-AL-X027medium1100.0 / 1004/4OK10.1s424 / 425
CG-AL-X029medium2100.0 / 1002/2OK10.2s844 / 1.5k
CG-AL-X030medium1100.0 / 1002/2OK11.0s408 / 697
CG-AL-X031medium1100.0 / 1003/3OK10.2s465 / 192
CG-AL-X033hard1100.0 / 1002/2OK10.4s558 / 257
CG-AL-X034hard2100.0 / 1003/3OK10.6s2.7k / 1.2k
CG-AL-X035hard1100.0 / 1003/3OK10.6s523 / 1.6k
CG-AL-X037hard2100.0 / 1004/4OK10.4s3.6k / 8.6k
CG-AL-X040hard2100.0 / 1004/4OK10.4s5.1k / 20k
CG-AL-X041hard2100.0 / 1005/5OK10.6s4.2k / 5.7k
CG-AL-X043hard2100.0 / 1001/1OK14.5s2.6k / 29k
CG-AL-X044hard2100.0 / 1003/3OK10.4s2.8k / 16k
CG-AL-X045hard1100.0 / 1003/3OK10.5s602 / 313
CG-AL-X046hard1100.0 / 1002/2OK10.5s569 / 1.3k
CG-AL-X047hard1100.0 / 1002/2OK10.6s650 / 3.1k
CG-AL-X050hard1100.0 / 1002/2OK10.3s658 / 1.3k
CG-AL-X051hard1100.0 / 1002/2OK10.3s800 / 1.4k
CG-AL-X052hard1100.0 / 1003/3OK10.2s582 / 1.3k
CG-AL-X055hard1100.0 / 1005/5OK10.2s546 / 795
CG-AL-X056hard1100.0 / 1005/5OK10.0s447 / 236
CG-AL-X057hard1100.0 / 1005/5OK10.1s411 / 241
CG-AL-X058hard1100.0 / 1005/5OK10.3s500 / 494
CG-AL-X059hard1100.0 / 1003/3OK10.3s511 / 149
CG-AL-X060hard1100.0 / 1003/3OK10.2s487 / 275
CG-AL-X061hard1100.0 / 1004/4OK10.3s572 / 176
CG-AL-X062hard1100.0 / 1004/4OK10.7s601 / 961
CG-AL-X063hard1100.0 / 1003/3OK10.4s559 / 798
CG-AL-X064hard1100.0 / 1007/7OK10.2s457 / 628
CG-AL-X065hard1100.0 / 1006/6OK10.4s1.2k / 1.3k
CG-AL-X066hard1100.0 / 10014/14OK10.4s2.2k / 1.9k
CG-AL-X067hard2100.0 / 1007/7OK10.2s2.7k / 4.3k
CG-AL-X068hard1100.0 / 10012/12OK10.5s1.9k / 2.6k
CG-AL-X069hard1100.0 / 1008/8OK10.4s1.9k / 2.0k
CG-AL-X070hard1100.0 / 10012/12OK10.8s1.9k / 3.4k
CG-AL-X071hard1100.0 / 1008/8OK10.8s2.2k / 2.1k
CG-AL-X072hard1100.0 / 1007/7OK10.3s2.1k / 1.8k
CG-AL-X073hard1100.0 / 1008/8OK10.9s2.5k / 3.0k
CG-AL-X074hard2100.0 / 1007/7OK10.3s5.9k / 9.4k
CG-AL-X075hard1100.0 / 1007/7OK10.5s1.4k / 1.7k
CG-AL-X076hard1100.0 / 10014/14OK10.5s1.6k / 4.9k
CG-AL-X077hard1100.0 / 10022/22OK10.2s2.6k / 2.3k
CG-AL-X078hard1100.0 / 10017/17OK10.4s2.0k / 1.6k
CG-AL-X079hard1100.0 / 10011/11OK10.8s2.0k / 2.9k
CG-AL-X080hard2100.0 / 1007/7OK10.3s4.3k / 5.1k
CG-AL-X081hard1100.0 / 1008/8OK10.8s1.5k / 1.5k
CG-AL-X082hard1100.0 / 10015/15OK10.7s2.1k / 1.8k
CG-AL-X083hard1100.0 / 1009/9OK10.8s2.8k / 2.4k
CG-AL-X084hard1100.0 / 10010/10OK10.9s2.5k / 3.2k
CG-AL-X085hard1100.0 / 1007/7OK10.6s1.6k / 1.4k
CG-AL-X086hard1100.0 / 1006/6OK10.5s2.4k / 3.2k
CG-AL-X087hard1100.0 / 1003/3OK10.3s1.8k / 2.0k
CG-AL-X088hard1100.0 / 1006/6OK10.5s1.7k / 1.8k
CG-AL-X089hard1100.0 / 10011/11OK10.9s1.8k / 2.8k
CG-AL-X090hard262.5 / 1009/10OK11.0s3.8k / 21k
CG-AL-X091hard1100.0 / 1006/6OK10.3s941 / 816
CG-AL-X092hard1100.0 / 10015/15OK10.2s716 / 362
CG-AL-X093hard1100.0 / 10010/10OK10.3s1.7k / 1.5k
CG-AL-X094hard1100.0 / 1007/7OK10.3s1.3k / 1.1k
CG-AL-X095hard1100.0 / 1005/5OK12.0s1.3k / 1.1k
CG-AL-X096hard1100.0 / 10049/49OK11.3s6.0k / 5.5k
CG-AL-X097hard1100.0 / 10046/46OK11.1s6.0k / 5.5k
CG-AL-X098hard1100.0 / 10029/29OK11.0s4.8k / 4.2k
CG-AL-X099hard1100.0 / 10039/39OK12.6s6.4k / 7.7k
CG-AL-X100hard1100.0 / 10035/35OK11.2s6.0k / 5.5k
CG-AL-X101hard1100.0 / 10010/10OK10.6s1.9k / 1.9k
CG-AL-X102hard1100.0 / 1008/8OK11.2s884 / 1.3k
CG-AL-X103hard1100.0 / 1007/7OK11.4s1.2k / 826
CG-AL-X104hard1100.0 / 1006/6OK11.7s1.7k / 1.4k
CG-AL-X105hard1100.0 / 1006/6OK11.0s1.3k / 826
CG-AL-X106hard1100.0 / 1005/5OK10.6s1.5k / 1.3k
CG-AL-X107hard1100.0 / 1004/4OK11.0s1.4k / 1.7k
CG-AL-X108hard1100.0 / 1006/6OK11.9s1.2k / 743
CG-AL-X109hard1100.0 / 1005/5OK11.2s916 / 681
CG-AL-X110hard1100.0 / 10017/17OK11.2s2.1k / 1.7k
CG-AL-X111hard1100.0 / 1008/8OK11.0s2.0k / 2.4k
CG-AL-X112hard1100.0 / 10012/12OK11.0s1.5k / 2.5k
CG-AL-X113hard1100.0 / 10013/13OK10.9s1.3k / 1.0k
CG-AL-X114hard1100.0 / 1007/7OK10.4s1.2k / 884
CG-AL-X115hard1100.0 / 10013/13OK10.4s793 / 2.2k
CG-AL-X116hard1100.0 / 10017/17OK10.6s1.5k / 1.8k
CG-AL-X117hard1100.0 / 1008/8OK10.8s1.7k / 1.6k
CG-AL-X118hard1100.0 / 10017/17OK10.9s2.4k / 3.3k
CG-AL-X119hard1100.0 / 10015/15OK11.2s2.8k / 2.7k
CG-AL-X120hard1100.0 / 10012/12OK11.1s2.2k / 2.0k
CG-AL-X121hard1100.0 / 1006/6OK11.0s1.7k / 1.4k
CG-AL-X122hard1100.0 / 10010/10OK11.0s2.6k / 2.7k
CG-AL-X123hard1100.0 / 1005/5OK10.9s981 / 678
CG-AL-X124hard1100.0 / 10010/10OK11.5s1.7k / 1.3k
CG-AL-X125hard1100.0 / 1008/8OK11.2s2.3k / 2.1k
CG-AL-X126hard1100.0 / 10014/14OK11.2s1.2k / 1.1k
CG-AL-X127hard1100.0 / 1005/5OK10.8s1.1k / 662
CG-AL-X128hard1100.0 / 1008/8OK10.6s2.0k / 1.5k
CG-AL-X129hard1100.0 / 10014/14OK11.1s2.0k / 1.8k
CG-AL-X130hard1100.0 / 1005/5OK10.6s845 / 1.0k
CG-AL-X131hard1100.0 / 10013/13OK10.7s1.6k / 1.7k
CG-AL-X132hard1100.0 / 10010/10OK10.7s1.2k / 847
CG-AL-X133hard2100.0 / 1008/8OK10.4s6.1k / 17k
CG-AL-X134hard1100.0 / 1006/6OK11.4s2.0k / 2.2k
CG-AL-X135hard1100.0 / 1004/4OK10.8s1.4k / 969
CG-AL-X136hard1100.0 / 1007/7OK11.0s1.2k / 830
CG-AL-X137hard1100.0 / 1004/4OK11.2s1.5k / 1.4k
CG-AL-X138hard1100.0 / 1009/9OK11.4s2.4k / 3.5k
CG-AL-X139hard1100.0 / 10011/11OK11.3s2.8k / 2.7k
CG-AL-X140hard262.5 / 1004/7OK10.4s5.8k / 23k
CG-AL-X141hard1100.0 / 10039/39OK11.7s6.1k / 5.6k
CG-AL-X142hard1100.0 / 10048/48OK13.8s6.8k / 16k
CG-AL-X143hard1100.0 / 10035/35OK17.8s7.2k / 7.0k
CG-AL-X144hard1100.0 / 10043/43OK14.4s6.4k / 6.3k
CG-AL-X145hard1100.0 / 10032/32OK14.6s7.4k / 7.1k
CG-AL-X146hard1100.0 / 1009/9OK13.5s2.9k / 7.7k
CG-AL-X147hard1100.0 / 1008/8OK12.8s2.2k / 1.9k
CG-AL-X148hard1100.0 / 1006/6OK11.7s1.9k / 1.4k
CG-AL-X149hard1100.0 / 1007/7OK12.4s1.9k / 1.7k
CG-AL-X150hard1100.0 / 1009/9OK13.3s3.2k / 8.5k
CG-AL-X151hard1100.0 / 1006/6OK11.9s1.4k / 970
CG-AL-X152hard1100.0 / 1008/8OK13.4s1.9k / 1.6k
CG-AL-X153hard1100.0 / 1009/9OK16.5s1.5k / 2.1k
CG-AL-X154hard1100.0 / 1009/9OK11.7s2.1k / 2.4k
CG-AL-X155hard1100.0 / 10011/11OK11.9s1.5k / 1.4k
CG-AL-X156hard1100.0 / 1007/7OK11.7s1.5k / 942
CG-AL-X157hard1100.0 / 10010/10OK11.7s2.2k / 1.7k
CG-AL-X158hard1100.0 / 1007/7OK11.3s1.3k / 780
CG-AL-X159hard1100.0 / 1007/7OK12.3s1.4k / 1.1k
CG-AL-X160hard1100.0 / 10013/13OK11.5s2.0k / 2.2k
CG-AL-X161hard1100.0 / 10010/10OK11.6s2.4k / 2.4k
CG-AL-X162hard1100.0 / 1007/7OK11.6s1.6k / 1.3k
CG-AL-X163hard1100.0 / 1007/7OK11.4s1.7k / 1.4k
CG-AL-X164hard1100.0 / 1007/7OK11.6s1.5k / 1.2k
CG-AL-X165hard2100.0 / 10013/13OK13.1s11k / 14k
CG-AL-X166hard1100.0 / 10014/14OK12.6s2.7k / 2.4k
CG-AL-X167hard2100.0 / 10013/13OK10.8s6.5k / 8.1k
CG-AL-X168hard1100.0 / 1009/9OK12.1s2.2k / 10k
CG-AL-X169hard2100.0 / 10011/11OK11.2s6.6k / 8.3k
CG-AL-X170hard1100.0 / 10011/11OK13.6s5.2k / 15k
CG-AL-X171hard1100.0 / 1009/9OK11.8s2.5k / 4.0k
CG-AL-X172hard1100.0 / 10011/11OK12.0s3.8k / 9.3k
CG-AL-X173hard1100.0 / 10019/19OK13.0s5.4k / 14k
CG-AL-X174hard1100.0 / 10016/16OK11.8s6.8k / 6.4k
CG-AL-X185hard262.5 / 10041/43OK10.9s12k / 7.3k
CG-AL-X187hard2100.0 / 10033/33OK11.1s13k / 43k
CG-AL-X194hard2100.0 / 10050/50OK11.3s19k / 33k
CG-AL-X211hard1100.0 / 10043/43OK12.4s6.0k / 25k
CG-AL-X214hard2100.0 / 10034/34OK11.1s13k / 14k
CG-AL-X218hard262.5 / 10022/27OK11.3s14k / 25k
CG-AL-X234hard2100.0 / 10035/35OK11.4s16k / 12k
CG-AL-X239hard2100.0 / 10037/37OK11.3s19k / 21k
CG-AL-X244hard2100.0 / 10038/38OK11.8s20k / 28k
CG-AL-X245hard2100.0 / 10063/63OK11.5s17k / 13k
CG-AL-X248hard2100.0 / 10066/66OK11.6s17k / 11k
CG-AL-X249hard262.5 / 10036/37OK11.3s17k / 45k
CG-AL-X254hard2100.0 / 10070/70OK12.3s23k / 13k
CG-AL-X257hard2100.0 / 10053/53OK11.5s15k / 29k
CG-AL-X263hard2100.0 / 10061/61OK11.9s18k / 19k
CG-AL-X264hard262.5 / 10064/65OK12.0s18k / 42k
CG-AL-X270hard2100.0 / 10063/63OK12.2s30k / 35k
CG-AL-X271hard2100.0 / 10070/70OK12.4s29k / 25k
CG-AL-X272hard262.5 / 10078/79OK12.3s23k / 18k
CG-AL-X274hard2100.0 / 10064/64OK11.9s23k / 24k
CG-AL-X276hard2100.0 / 10078/78OK12.3s24k / 15k
CG-AL-X278hard2100.0 / 10071/71OK12.4s24k / 37k
CG-AL-X283hard2100.0 / 10076/76OK12.1s25k / 14k
CG-AL-X289hard2100.0 / 10057/57OK11.9s19k / 37k
CG-AL-X290hard2100.0 / 10047/47OK11.5s21k / 18k
CG-AL-X292hard2100.0 / 10057/57OK12.1s19k / 15k
CG-AL-X293hard2100.0 / 10049/49OK11.6s18k / 13k
CG-AL-X296hard2100.0 / 10047/47OK11.7s27k / 23k
CG-AL-X298hard1100.0 / 10055/55OK12.0s7.7k / 14k