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.

79.2% 183/231 of 231 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.

71.6 / 100
Cost $20.39
Tokens 1.1M / 1.8M input / output, all attempts
Duration 1h 3m
Filter:
Per-task results for run ae125a12-0b60-4149-9874-aa6a280b87d3
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK32.7s413 / 319
CG-AL-E006easy20.0 / 1000/0FAIL9.7s1.8k / 1.8k
CG-AL-E010easy1100.0 / 1005/5OK15.4s466 / 249
CG-AL-E050easy20.0 / 1000/0FAIL9.3s3.0k / 1.4k
CG-AL-E052easy1100.0 / 10016/16OK13.4s610 / 380
CG-AL-E054easy2100.0 / 1009/9OK19.1s1.7k / 919
CG-AL-E056easy20.0 / 1000/0FAIL9.5s2.8k / 1.3k
CG-AL-H007hard1100.0 / 10011/11OK13.6s947 / 1.0k
CG-AL-H011hard20.0 / 1000/0FAIL4.3s1.9k / 2.1k
CG-AL-H014hard2100.0 / 1007/7OK19.5s4.3k / 3.4k
CG-AL-H017hard20.0 / 1000/0FAIL4.1s1.7k / 1.5k
CG-AL-H020hard2100.0 / 10010/10OK11.2s3.6k / 2.6k
CG-AL-H021hard2100.0 / 10020/20OK14.2s30k / 2.9k
CG-AL-H023hard20.0 / 1000/0FAIL4.8s10k / 41k
CG-AL-H027hard2100.0 / 1004/4OK12.0s3.4k / 14k
CG-AL-H029hard20.0 / 1000/0FAIL4.3s4.6k / 14k
CG-AL-H030hard1100.0 / 10010/10OK12.4s1.1k / 3.6k
CG-AL-H031hard2100.0 / 10022/22OK11.6s4.9k / 5.1k
CG-AL-H034hard1100.0 / 1003/3OK12.0s720 / 1.6k
CG-AL-H036hard20.0 / 1000/0FAIL4.1s1.6k / 1.2k
CG-AL-H037hard20.0 / 1000/0FAIL4.6s1.9k / 2.4k
CG-AL-H041hard2100.0 / 1003/3OK11.6s3.7k / 15k
CG-AL-H050hard262.5 / 1002/3OK11.8s2.4k / 27k
CG-AL-H054hard20.0 / 1000/0FAIL4.0s3.0k / 1.3k
CG-AL-H056hard20.0 / 1000/0FAIL4.0s2.4k / 488
CG-AL-M001medium2100.0 / 10010/10OK25.3s2.2k / 1.7k
CG-AL-M003medium20.0 / 1000/0FAIL4.2s2.8k / 2.5k
CG-AL-M004medium2100.0 / 10012/12OK35.1s2.9k / 3.3k
CG-AL-M006medium2100.0 / 10018/18OK12.3s3.8k / 11k
CG-AL-M007medium20.0 / 1000/0FAIL4.3s5.6k / 22k
CG-AL-M008medium262.5 / 10011/12OK12.9s8.8k / 30k
CG-AL-M009medium1100.0 / 10011/11OK12.1s746 / 4.2k
CG-AL-M010medium1100.0 / 10021/21OK31.2s958 / 7.0k
CG-AL-M020medium2100.0 / 10017/17OK11.6s3.2k / 4.7k
CG-AL-M023medium1100.0 / 10011/11OK13.5s803 / 906
CG-AL-M025medium2100.0 / 1008/8OK11.7s4.7k / 1.2k
CG-AL-M026medium1100.0 / 1008/8OK11.7s624 / 614
CG-AL-M027medium2100.0 / 10018/18OK11.4s6.3k / 4.5k
CG-AL-M028medium2100.0 / 1003/3OK26.0s1.9k / 4.7k
CG-AL-M031medium211.1 / 1000/0FAIL4.2s3.5k / 2.1k
CG-AL-M034medium1100.0 / 1002/2OK12.3s695 / 1.2k
CG-AL-M036medium211.1 / 1000/0FAIL4.3s2.6k / 6.7k
CG-AL-M040medium20.0 / 1000/0FAIL4.2s1.3k / 770
CG-AL-M042medium1100.0 / 1008/8OK12.1s753 / 545
CG-AL-X001hard1100.0 / 1002/2OK12.0s499 / 202
CG-AL-X002hard262.5 / 1000/4OK12.0s4.0k / 7.1k
CG-AL-X003hard20.0 / 1000/0FAIL4.1s1.4k / 5.3k
CG-AL-X004medium1100.0 / 1003/3OK12.1s551 / 420
CG-AL-X005hard1100.0 / 1002/2OK12.2s515 / 213
CG-AL-X006hard2100.0 / 1003/3OK11.7s2.0k / 781
CG-AL-X007hard1100.0 / 1002/2OK2m 3s575 / 264
CG-AL-X008hard1100.0 / 1001/1OK13.1s641 / 1.0k
CG-AL-X009medium1100.0 / 1002/2OK12.4s493 / 232
CG-AL-X010medium1100.0 / 1003/3OK12.1s449 / 238
CG-AL-X011medium1100.0 / 1002/2OK12.1s557 / 208
CG-AL-X012hard1100.0 / 1001/1OK12.0s589 / 1.6k
CG-AL-X013hard1100.0 / 1002/2OK11.4s423 / 148
CG-AL-X014medium1100.0 / 1004/4OK11.9s458 / 163
CG-AL-X017medium2100.0 / 1003/3OK11.6s2.4k / 479
CG-AL-X018medium1100.0 / 1003/3OK11.6s606 / 272
CG-AL-X019medium2100.0 / 1003/3OK11.5s2.9k / 1.7k
CG-AL-X022medium2100.0 / 1003/3OK11.2s2.1k / 9.6k
CG-AL-X024medium1100.0 / 1003/3OK11.6s541 / 515
CG-AL-X025medium1100.0 / 1001/1OK11.4s601 / 533
CG-AL-X026medium1100.0 / 1003/3OK11.5s524 / 199
CG-AL-X027medium1100.0 / 1004/4OK11.5s424 / 387
CG-AL-X030medium1100.0 / 1002/2OK11.8s408 / 143
CG-AL-X031medium1100.0 / 1003/3OK11.6s465 / 197
CG-AL-X033hard1100.0 / 1002/2OK11.4s558 / 222
CG-AL-X034hard1100.0 / 1003/3OK11.6s486 / 362
CG-AL-X035hard262.5 / 1001/3OK11.7s2.5k / 2.6k
CG-AL-X037hard20.0 / 1000/0FAIL4.5s1.6k / 13k
CG-AL-X040hard20.0 / 1000/0FAIL4.5s2.2k / 4.9k
CG-AL-X041hard20.0 / 1000/0FAIL4.4s1.9k / 8.8k
CG-AL-X043hard20.0 / 1000/0FAIL4.6s2.6k / 22k
CG-AL-X044hard20.0 / 1000/0FAIL4.5s2.1k / 20k
CG-AL-X045hard1100.0 / 1003/3OK11.3s602 / 302
CG-AL-X046hard262.5 / 1000/2OK11.8s2.5k / 9.5k
CG-AL-X047hard262.5 / 1001/2OK11.9s2.1k / 6.9k
CG-AL-X050hard1100.0 / 1002/2OK12.2s658 / 997
CG-AL-X051hard262.5 / 1000/2OK11.7s2.0k / 686
CG-AL-X052hard1100.0 / 1003/3OK11.7s582 / 462
CG-AL-X055hard1100.0 / 1005/5OK12.5s546 / 512
CG-AL-X056hard1100.0 / 1005/5OK11.8s447 / 282
CG-AL-X057hard1100.0 / 1005/5OK11.0s411 / 153
CG-AL-X058hard1100.0 / 1005/5OK11.3s500 / 462
CG-AL-X059hard1100.0 / 1003/3OK11.7s511 / 121
CG-AL-X060hard1100.0 / 1003/3OK12.5s487 / 145
CG-AL-X061hard1100.0 / 1004/4OK12.1s572 / 201
CG-AL-X062hard1100.0 / 1004/4OK12.0s601 / 611
CG-AL-X063hard1100.0 / 1003/3OK11.9s559 / 952
CG-AL-X064hard1100.0 / 1007/7OK11.8s457 / 382
CG-AL-X065hard1100.0 / 1006/6OK12.2s1.2k / 1.3k
CG-AL-X066hard1100.0 / 10014/14OK12.4s2.2k / 1.9k
CG-AL-X067hard262.5 / 1006/7OK11.4s2.7k / 52k
CG-AL-X068hard2100.0 / 10012/12OK11.8s9.1k / 6.1k
CG-AL-X069hard1100.0 / 1008/8OK12.8s1.9k / 2.1k
CG-AL-X070hard1100.0 / 10012/12OK12.1s1.9k / 1.8k
CG-AL-X071hard1100.0 / 1008/8OK12.0s2.2k / 1.9k
CG-AL-X072hard1100.0 / 1007/7OK13.6s2.1k / 1.7k
CG-AL-X073hard1100.0 / 1008/8OK11.8s2.5k / 2.3k
CG-AL-X074hard2100.0 / 1007/7OK11.5s5.9k / 26k
CG-AL-X075hard1100.0 / 1007/7OK13.2s1.4k / 5.9k
CG-AL-X076hard2100.0 / 10014/14OK11.9s5.8k / 39k
CG-AL-X077hard1100.0 / 10022/22OK12.0s2.6k / 2.4k
CG-AL-X078hard1100.0 / 10017/17OK13.3s2.0k / 1.6k
CG-AL-X079hard2100.0 / 10011/11OK11.8s5.6k / 17k
CG-AL-X080hard262.5 / 1006/7OK11.6s4.3k / 8.7k
CG-AL-X081hard1100.0 / 1008/8OK12.3s1.5k / 1.1k
CG-AL-X082hard1100.0 / 10015/15OK12.0s2.1k / 1.7k
CG-AL-X083hard1100.0 / 1009/9OK11.7s2.8k / 2.5k
CG-AL-X084hard1100.0 / 10010/10OK12.6s2.5k / 2.6k
CG-AL-X085hard1100.0 / 1007/7OK11.6s1.6k / 1.7k
CG-AL-X086hard1100.0 / 1006/6OK11.7s2.4k / 7.6k
CG-AL-X087hard1100.0 / 1003/3OK12.3s1.8k / 2.0k
CG-AL-X088hard1100.0 / 1006/6OK12.1s1.7k / 2.1k
CG-AL-X089hard1100.0 / 10011/11OK13.0s1.8k / 8.3k
CG-AL-X090hard20.0 / 1000/0FAIL3.9s3.6k / 9.3k
CG-AL-X091hard1100.0 / 1006/6OK11.3s941 / 763
CG-AL-X092hard1100.0 / 10015/15OK12.1s716 / 360
CG-AL-X093hard1100.0 / 10010/10OK12.4s1.7k / 1.5k
CG-AL-X094hard1100.0 / 1007/7OK11.7s1.3k / 1.1k
CG-AL-X095hard1100.0 / 1005/5OK11.6s1.3k / 1.0k
CG-AL-X096hard2100.0 / 10049/49OK12.0s13k / 14k
CG-AL-X097hard1100.0 / 10046/46OK12.4s6.0k / 5.6k
CG-AL-X098hard1100.0 / 10029/29OK12.3s4.8k / 4.7k
CG-AL-X099hard1100.0 / 10039/39OK15.0s6.4k / 27k
CG-AL-X100hard20.0 / 1000/0FAIL4.3s14k / 22k
CG-AL-X101hard1100.0 / 10010/10OK11.5s1.9k / 3.2k
CG-AL-X102hard2100.0 / 1008/8OK11.6s3.8k / 1.8k
CG-AL-X103hard1100.0 / 1007/7OK11.4s1.2k / 916
CG-AL-X104hard1100.0 / 1006/6OK11.5s1.7k / 1.4k
CG-AL-X105hard1100.0 / 1006/6OK11.7s1.3k / 830
CG-AL-X106hard1100.0 / 1005/5OK12.1s1.5k / 2.1k
CG-AL-X107hard1100.0 / 1004/4OK11.5s1.4k / 1.3k
CG-AL-X108hard1100.0 / 1006/6OK12.2s1.2k / 660
CG-AL-X109hard1100.0 / 1005/5OK11.8s916 / 522
CG-AL-X110hard1100.0 / 10017/17OK11.4s2.1k / 1.7k
CG-AL-X111hard1100.0 / 1008/8OK11.6s2.0k / 3.2k
CG-AL-X112hard262.5 / 10010/12OK12.0s4.2k / 16k
CG-AL-X113hard1100.0 / 10013/13OK11.9s1.3k / 3.9k
CG-AL-X114hard1100.0 / 1007/7OK12.2s1.2k / 926
CG-AL-X115hard1100.0 / 10013/13OK11.3s793 / 698
CG-AL-X116hard1100.0 / 10017/17OK11.5s1.5k / 3.0k
CG-AL-X117hard1100.0 / 1008/8OK11.3s1.7k / 1.6k
CG-AL-X118hard2100.0 / 10017/17OK12.1s10k / 9.9k
CG-AL-X119hard1100.0 / 10015/15OK11.7s2.8k / 2.7k
CG-AL-X120hard1100.0 / 10012/12OK11.6s2.2k / 2.0k
CG-AL-X121hard1100.0 / 1006/6OK11.3s1.7k / 1.4k
CG-AL-X122hard1100.0 / 10010/10OK11.8s2.6k / 3.9k
CG-AL-X123hard1100.0 / 1005/5OK11.6s981 / 541
CG-AL-X124hard1100.0 / 10010/10OK11.6s1.7k / 1.5k
CG-AL-X125hard1100.0 / 1008/8OK11.5s2.3k / 3.4k
CG-AL-X126hard1100.0 / 10014/14OK11.7s1.2k / 2.1k
CG-AL-X127hard1100.0 / 1005/5OK11.6s1.1k / 729
CG-AL-X128hard1100.0 / 1008/8OK11.4s2.0k / 1.5k
CG-AL-X129hard1100.0 / 10014/14OK11.5s2.0k / 1.8k
CG-AL-X130hard2100.0 / 1005/5OK11.4s2.4k / 11k
CG-AL-X131hard1100.0 / 10013/13OK11.4s1.6k / 1.7k
CG-AL-X132hard1100.0 / 10010/10OK11.9s1.2k / 778
CG-AL-X133hard20.0 / 1000/0FAIL4.1s5.9k / 29k
CG-AL-X134hard1100.0 / 1006/6OK12.6s2.0k / 2.0k
CG-AL-X135hard1100.0 / 1004/4OK11.4s1.4k / 984
CG-AL-X136hard1100.0 / 1007/7OK11.5s1.2k / 895
CG-AL-X137hard1100.0 / 1004/4OK12.0s1.5k / 2.5k
CG-AL-X138hard1100.0 / 1009/9OK12.0s2.4k / 2.8k
CG-AL-X139hard1100.0 / 10011/11OK12.0s2.8k / 2.7k
CG-AL-X140hard1100.0 / 1007/7OK12.2s2.5k / 14k
CG-AL-X141hard1100.0 / 10039/39OK14.4s6.1k / 7.1k
CG-AL-X142hard2100.0 / 10048/48OK12.8s16k / 30k
CG-AL-X143hard1100.0 / 10035/35OK17.3s7.2k / 7.2k
CG-AL-X144hard1100.0 / 10043/43OK12.3s6.4k / 6.6k
CG-AL-X145hard1100.0 / 10032/32OK12.7s7.4k / 7.4k
CG-AL-X146hard1100.0 / 1009/9OK12.2s2.9k / 11k
CG-AL-X147hard1100.0 / 1008/8OK11.7s2.2k / 1.8k
CG-AL-X148hard1100.0 / 1006/6OK11.7s1.9k / 1.4k
CG-AL-X149hard1100.0 / 1007/7OK12.0s1.9k / 1.8k
CG-AL-X150hard1100.0 / 1009/9OK12.0s3.2k / 10k
CG-AL-X151hard1100.0 / 1006/6OK11.6s1.4k / 972
CG-AL-X152hard1100.0 / 1008/8OK11.4s1.9k / 1.4k
CG-AL-X153hard1100.0 / 1009/9OK16.4s1.5k / 2.2k
CG-AL-X154hard1100.0 / 1009/9OK11.6s2.1k / 1.9k
CG-AL-X155hard1100.0 / 10011/11OK12.5s1.5k / 1.3k
CG-AL-X156hard1100.0 / 1007/7OK11.9s1.5k / 958
CG-AL-X157hard1100.0 / 10010/10OK11.9s2.2k / 1.7k
CG-AL-X158hard1100.0 / 1007/7OK11.7s1.3k / 788
CG-AL-X159hard1100.0 / 1007/7OK12.6s1.4k / 970
CG-AL-X160hard1100.0 / 10013/13OK11.8s2.0k / 2.1k
CG-AL-X161hard1100.0 / 10010/10OK13.6s2.4k / 2.4k
CG-AL-X162hard1100.0 / 1007/7OK12.2s1.6k / 1.3k
CG-AL-X163hard1100.0 / 1007/7OK12.1s1.7k / 1.4k
CG-AL-X164hard1100.0 / 1007/7OK11.9s1.5k / 1.2k
CG-AL-X165hard20.0 / 1000/0FAIL4.1s11k / 27k
CG-AL-X166hard1100.0 / 10014/14OK12.9s2.7k / 2.2k
CG-AL-X167hard262.5 / 10010/13OK11.8s5.1k / 17k
CG-AL-X168hard1100.0 / 1009/9OK12.1s2.2k / 9.0k
CG-AL-X169hard1100.0 / 10011/11OK12.7s2.8k / 9.2k
CG-AL-X170hard1100.0 / 10011/11OK12.4s5.2k / 9.5k
CG-AL-X171hard262.5 / 1008/9OK12.1s6.6k / 31k
CG-AL-X172hard1100.0 / 10011/11OK33.7s3.8k / 12k
CG-AL-X173hard1100.0 / 10019/19OK14.0s5.4k / 25k
CG-AL-X174hard2100.0 / 10016/16OK12.1s15k / 16k
CG-AL-X185hard262.5 / 10041/43OK11.9s12k / 11k
CG-AL-X187hard262.5 / 10030/33OK12.1s11k / 8.3k
CG-AL-X194hard2100.0 / 10050/50OK12.4s18k / 12k
CG-AL-X211hard262.5 / 10039/43OK12.5s14k / 15k
CG-AL-X214hard2100.0 / 10034/34OK12.6s14k / 16k
CG-AL-X218hard2100.0 / 10027/27OK12.4s13k / 12k
CG-AL-X234hard2100.0 / 10035/35OK12.4s16k / 12k
CG-AL-X239hard2100.0 / 10037/37OK13.0s19k / 18k
CG-AL-X244hard262.5 / 10035/38OK12.4s20k / 25k
CG-AL-X245hard2100.0 / 10063/63OK13.0s20k / 15k
CG-AL-X248hard2100.0 / 10066/66OK13.0s16k / 13k
CG-AL-X249hard262.5 / 10036/37OK12.5s17k / 16k
CG-AL-X254hard2100.0 / 10070/70OK12.8s23k / 25k
CG-AL-X257hard20.0 / 1000/0FAIL0ms18k / 88k
CG-AL-X263hard2100.0 / 10061/61OK12.9s21k / 22k
CG-AL-X264hard2100.0 / 10065/65OK13.0s22k / 27k
CG-AL-X270hard262.5 / 10062/63OK13.3s32k / 27k
CG-AL-X271hard262.5 / 10063/70OK13.4s28k / 25k
CG-AL-X272hard2100.0 / 10079/79OK13.2s23k / 23k
CG-AL-X274hard2100.0 / 10064/64OK13.7s23k / 27k
CG-AL-X276hard2100.0 / 10078/78OK13.5s25k / 28k
CG-AL-X278hard2100.0 / 10071/71OK13.6s26k / 37k
CG-AL-X283hard2100.0 / 10076/76OK13.3s30k / 33k
CG-AL-X289hard2100.0 / 10057/57OK13.3s20k / 28k
CG-AL-X290hard2100.0 / 10047/47OK13.4s21k / 20k
CG-AL-X292hard2100.0 / 10057/57OK13.0s21k / 28k
CG-AL-X293hard2100.0 / 10049/49OK12.4s18k / 19k
CG-AL-X296hard262.5 / 10046/47OK13.1s29k / 30k
CG-AL-X298hard262.5 / 10054/55OK12.6s16k / 76k