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.

88.8% 206/232 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.

81.2 / 100
Cost $14.05
Tokens 577k / 583k input / output, all attempts
Duration 58m 0s
Filter:
Per-task results for run 403bab26-34a5-4af4-bd10-35e988d589b8
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK16.8s258 / 182
CG-AL-E006easy1100.0 / 1007/7OK31.8s305 / 534
CG-AL-E010easy2100.0 / 1005/5OK17.7s717 / 628
CG-AL-E050easy2100.0 / 10013/13OK17.5s1.8k / 1.4k
CG-AL-E052easy1100.0 / 10016/16OK10.9s352 / 387
CG-AL-E054easy20.0 / 1000/0FAIL9.9s1.0k / 970
CG-AL-E056easy2100.0 / 10015/15OK11.6s1.7k / 1.6k
CG-AL-H007hard1100.0 / 10011/11OK11.0s545 / 2.0k
CG-AL-H011hard20.0 / 1000/0FAIL4.0s940 / 2.8k
CG-AL-H014hard20.0 / 1000/0FAIL9.5s1.6k / 2.1k
CG-AL-H017hard1100.0 / 1005/5OK15.9s357 / 1.2k
CG-AL-H020hard2100.0 / 10010/10OK11.0s1.8k / 3.1k
CG-AL-H021hard262.5 / 1006/20OK11.3s1.9k / 1.7k
CG-AL-H023hard2100.0 / 10025/25OK11.7s6.7k / 13k
CG-AL-H027hard262.5 / 1002/4OK12.7s2.2k / 3.5k
CG-AL-H029hard2100.0 / 10018/18OK12.0s2.6k / 4.5k
CG-AL-H030hard2100.0 / 10010/10OK11.1s2.6k / 5.1k
CG-AL-H031hard1100.0 / 10022/22OK11.2s939 / 3.4k
CG-AL-H034hard1100.0 / 1003/3OK11.2s431 / 648
CG-AL-H036hard20.0 / 1000/0FAIL5.7s944 / 2.4k
CG-AL-H037hard1100.0 / 1003/3OK10.9s497 / 1.5k
CG-AL-H041hard1100.0 / 1003/3OK10.7s565 / 1.9k
CG-AL-H050hard262.5 / 1002/3OK11.2s1.4k / 2.4k
CG-AL-H054hard20.0 / 1000/0FAIL3.9s1.8k / 926
CG-AL-H056hard20.0 / 1000/0FAIL4.1s1.4k / 2.5k
CG-AL-M001medium20.0 / 1000/0FAIL4.2s1.4k / 3.1k
CG-AL-M003medium1100.0 / 1009/9OK11.4s419 / 2.8k
CG-AL-M004medium1100.0 / 10012/12OK29.2s449 / 2.7k
CG-AL-M006medium2100.0 / 10018/18OK11.7s3.4k / 7.1k
CG-AL-M007medium262.5 / 10013/15OK13.0s5.4k / 13k
CG-AL-M008medium262.5 / 1004/12OK11.9s6.5k / 14k
CG-AL-M009medium1100.0 / 10011/11OK11.2s429 / 6.3k
CG-AL-M010medium1100.0 / 10021/21OK25.0s596 / 4.1k
CG-AL-M020medium2100.0 / 10017/17OK11.4s2.1k / 3.7k
CG-AL-M023medium1100.0 / 10011/11OK12.2s482 / 831
CG-AL-M025medium2100.0 / 1008/8OK11.7s2.8k / 1.4k
CG-AL-M026medium1100.0 / 1008/8OK10.7s370 / 1.2k
CG-AL-M027medium2100.0 / 10018/18OK10.7s3.4k / 4.3k
CG-AL-M028medium2100.0 / 1003/3OK26.5s1.1k / 1.2k
CG-AL-M031medium2100.0 / 1002/2OK11.0s2.0k / 1.6k
CG-AL-M034medium1100.0 / 1002/2OK10.9s415 / 691
CG-AL-M036medium2100.0 / 1002/2OK10.5s1.5k / 1.0k
CG-AL-M040medium1100.0 / 1002/2OK10.4s311 / 633
CG-AL-M042medium1100.0 / 1008/8OK10.7s498 / 1.3k
CG-AL-X001hard1100.0 / 1002/2OK11.6s308 / 425
CG-AL-X002hard1100.0 / 1004/4OK11.0s488 / 3.4k
CG-AL-X003hard2100.0 / 1003/3OK11.2s816 / 2.0k
CG-AL-X004medium1100.0 / 1003/3OK10.8s358 / 710
CG-AL-X005hard1100.0 / 1002/2OK10.7s327 / 348
CG-AL-X006hard1100.0 / 1003/3OK10.5s383 / 503
CG-AL-X007hard1100.0 / 1002/2OK1m 48s372 / 568
CG-AL-X008hard1100.0 / 1001/1OK10.8s417 / 3.1k
CG-AL-X009medium1100.0 / 1002/2OK10.8s313 / 524
CG-AL-X010medium1100.0 / 1003/3OK10.5s284 / 249
CG-AL-X011medium1100.0 / 1002/2OK11.6s360 / 349
CG-AL-X012hard1100.0 / 1001/1OK10.7s380 / 511
CG-AL-X013hard1100.0 / 1002/2OK11.3s263 / 172
CG-AL-X014medium1100.0 / 1004/4OK11.0s291 / 207
CG-AL-X017medium2100.0 / 1003/3OK10.7s1.4k / 406
CG-AL-X018medium1100.0 / 1003/3OK11.8s384 / 339
CG-AL-X019medium2100.0 / 1003/3OK10.7s1.8k / 1.2k
CG-AL-X022medium2100.0 / 1003/3OK11.2s1.3k / 793
CG-AL-X024medium1100.0 / 1003/3OK12.5s333 / 735
CG-AL-X025medium1100.0 / 1001/1OK10.8s371 / 532
CG-AL-X026medium1100.0 / 1003/3OK11.5s327 / 396
CG-AL-X027medium1100.0 / 1004/4OK11.4s258 / 403
CG-AL-X029medium1100.0 / 1002/2OK16.8s276 / 599
CG-AL-X030medium1100.0 / 1002/2OK11.7s239 / 316
CG-AL-X031medium1100.0 / 1003/3OK11.0s297 / 309
CG-AL-X033hard1100.0 / 1002/2OK11.0s348 / 315
CG-AL-X034hard1100.0 / 1003/3OK11.1s304 / 1.1k
CG-AL-X035hard1100.0 / 1003/3OK10.7s331 / 1.1k
CG-AL-X037hard2100.0 / 1004/4OK11.1s1.0k / 3.0k
CG-AL-X040hard1100.0 / 1004/4OK11.8s550 / 1.8k
CG-AL-X041hard1100.0 / 1005/5OK12.0s446 / 1.8k
CG-AL-X043hard2100.0 / 1001/1OK15.7s1.7k / 7.6k
CG-AL-X044hard262.5 / 1001/3OK11.2s1.7k / 6.2k
CG-AL-X045hard1100.0 / 1003/3OK11.7s371 / 358
CG-AL-X046hard1100.0 / 1002/2OK11.7s369 / 391
CG-AL-X047hard1100.0 / 1002/2OK11.3s390 / 2.2k
CG-AL-X050hard1100.0 / 1002/2OK11.8s405 / 511
CG-AL-X051hard1100.0 / 1002/2OK11.3s509 / 684
CG-AL-X052hard1100.0 / 1003/3OK11.9s358 / 332
CG-AL-X055hard1100.0 / 1005/5OK11.0s344 / 474
CG-AL-X056hard1100.0 / 1005/5OK11.3s280 / 926
CG-AL-X057hard1100.0 / 1005/5OK11.1s250 / 221
CG-AL-X058hard1100.0 / 1005/5OK11.2s314 / 1.2k
CG-AL-X059hard1100.0 / 1003/3OK11.1s327 / 142
CG-AL-X060hard1100.0 / 1003/3OK10.9s302 / 591
CG-AL-X061hard1100.0 / 1004/4OK10.7s364 / 92
CG-AL-X062hard1100.0 / 1004/4OK10.9s358 / 595
CG-AL-X063hard1100.0 / 1003/3OK10.4s360 / 452
CG-AL-X064hard1100.0 / 1007/7OK10.5s277 / 509
CG-AL-X065hard1100.0 / 1006/6OK10.5s709 / 597
CG-AL-X066hard1100.0 / 10014/14OK11.1s1.2k / 1.1k
CG-AL-X067hard1100.0 / 1007/7OK11.0s611 / 500
CG-AL-X068hard1100.0 / 10012/12OK11.1s1.2k / 1.0k
CG-AL-X069hard1100.0 / 1008/8OK10.9s1.1k / 2.7k
CG-AL-X070hard1100.0 / 10012/12OK10.7s1.2k / 995
CG-AL-X071hard1100.0 / 1008/8OK10.9s1.4k / 1.1k
CG-AL-X072hard1100.0 / 1007/7OK10.4s1.1k / 808
CG-AL-X073hard1100.0 / 1008/8OK12.8s1.4k / 1.4k
CG-AL-X074hard2100.0 / 1007/7OK11.1s3.4k / 4.2k
CG-AL-X075hard1100.0 / 1007/7OK11.7s810 / 2.7k
CG-AL-X076hard1100.0 / 10014/14OK10.8s954 / 3.0k
CG-AL-X077hard1100.0 / 10022/22OK11.0s1.5k / 1.3k
CG-AL-X078hard1100.0 / 10017/17OK10.9s1.2k / 875
CG-AL-X079hard1100.0 / 10011/11OK10.9s1.2k / 1.9k
CG-AL-X080hard20.0 / 1000/0FAIL4.1s2.4k / 2.3k
CG-AL-X081hard1100.0 / 1008/8OK11.0s902 / 519
CG-AL-X082hard1100.0 / 10015/15OK11.1s1.2k / 955
CG-AL-X083hard1100.0 / 1009/9OK10.5s1.5k / 1.2k
CG-AL-X084hard1100.0 / 10010/10OK11.6s1.4k / 3.8k
CG-AL-X085hard1100.0 / 1007/7OK11.2s980 / 622
CG-AL-X086hard1100.0 / 1006/6OK11.7s1.4k / 1.3k
CG-AL-X087hard1100.0 / 1003/3OK11.6s1.0k / 853
CG-AL-X088hard1100.0 / 1006/6OK11.5s974 / 1.1k
CG-AL-X089hard1100.0 / 10011/11OK11.5s1.1k / 1.9k
CG-AL-X090hard1100.0 / 10010/10OK11.4s889 / 1.6k
CG-AL-X091hard1100.0 / 1006/6OK11.5s569 / 319
CG-AL-X092hard1100.0 / 10015/15OK11.4s444 / 417
CG-AL-X093hard1100.0 / 10010/10OK11.4s989 / 856
CG-AL-X094hard1100.0 / 1007/7OK11.6s754 / 553
CG-AL-X095hard262.5 / 1002/5OK11.1s2.8k / 2.7k
CG-AL-X096hard1100.0 / 10049/49OK12.2s3.3k / 3.1k
CG-AL-X097hard1100.0 / 10046/46OK12.5s3.4k / 3.1k
CG-AL-X098hard1100.0 / 10029/29OK11.9s2.6k / 2.2k
CG-AL-X099hard1100.0 / 10039/39OK13.8s3.6k / 3.9k
CG-AL-X100hard1100.0 / 10035/35OK11.2s3.5k / 3.3k
CG-AL-X101hard1100.0 / 10010/10OK10.7s1.1k / 962
CG-AL-X102hard1100.0 / 1008/8OK10.8s531 / 1.7k
CG-AL-X103hard1100.0 / 1007/7OK10.4s725 / 458
CG-AL-X104hard1100.0 / 1006/6OK10.8s1.1k / 912
CG-AL-X105hard1100.0 / 1006/6OK10.8s777 / 443
CG-AL-X106hard1100.0 / 1005/5OK10.6s878 / 1.0k
CG-AL-X107hard1100.0 / 1004/4OK10.7s805 / 721
CG-AL-X108hard1100.0 / 1006/6OK11.6s729 / 395
CG-AL-X109hard1100.0 / 1005/5OK11.1s548 / 425
CG-AL-X110hard1100.0 / 10017/17OK11.9s1.2k / 1.0k
CG-AL-X111hard1100.0 / 1008/8OK10.8s1.2k / 1.3k
CG-AL-X112hard1100.0 / 10012/12OK10.7s906 / 2.3k
CG-AL-X113hard1100.0 / 10013/13OK11.1s705 / 836
CG-AL-X114hard1100.0 / 1007/7OK10.5s718 / 478
CG-AL-X115hard1100.0 / 10013/13OK10.7s478 / 592
CG-AL-X116hard1100.0 / 10017/17OK10.8s926 / 2.1k
CG-AL-X117hard1100.0 / 1008/8OK10.7s1.0k / 876
CG-AL-X118hard1100.0 / 10017/17OK11.0s1.4k / 1.1k
CG-AL-X119hard1100.0 / 10015/15OK11.0s1.7k / 1.6k
CG-AL-X120hard1100.0 / 10012/12OK10.9s1.2k / 1.1k
CG-AL-X121hard1100.0 / 1006/6OK10.6s1.0k / 835
CG-AL-X122hard1100.0 / 10010/10OK10.8s1.5k / 1.5k
CG-AL-X123hard1100.0 / 1005/5OK10.6s603 / 323
CG-AL-X124hard1100.0 / 10010/10OK10.6s994 / 906
CG-AL-X125hard1100.0 / 1008/8OK10.7s1.4k / 1.1k
CG-AL-X126hard1100.0 / 10014/14OK10.8s711 / 553
CG-AL-X127hard1100.0 / 1005/5OK10.8s666 / 675
CG-AL-X128hard1100.0 / 1008/8OK10.8s1.1k / 811
CG-AL-X129hard1100.0 / 10014/14OK10.8s1.2k / 1.0k
CG-AL-X130hard2100.0 / 1005/5OK11.5s1.1k / 757
CG-AL-X131hard1100.0 / 10013/13OK10.5s941 / 937
CG-AL-X132hard1100.0 / 10010/10OK10.5s709 / 410
CG-AL-X133hard20.0 / 1000/0FAIL4.1s3.5k / 7.3k
CG-AL-X134hard1100.0 / 1006/6OK11.1s1.2k / 1.4k
CG-AL-X135hard1100.0 / 1004/4OK10.8s866 / 554
CG-AL-X136hard1100.0 / 1007/7OK10.9s754 / 409
CG-AL-X137hard1100.0 / 1004/4OK10.7s915 / 1.1k
CG-AL-X138hard1100.0 / 1009/9OK11.4s1.4k / 3.0k
CG-AL-X139hard1100.0 / 10011/11OK11.3s1.6k / 1.5k
CG-AL-X140hard1100.0 / 1007/7OK11.5s1.5k / 4.9k
CG-AL-X141hard1100.0 / 10039/39OK12.0s3.5k / 3.5k
CG-AL-X142hard262.5 / 10045/48OK12.1s8.4k / 9.8k
CG-AL-X143hard1100.0 / 10035/35OK16.2s4.0k / 4.3k
CG-AL-X144hard1100.0 / 10043/43OK11.9s3.6k / 3.3k
CG-AL-X145hard1100.0 / 10032/32OK12.8s4.2k / 3.9k
CG-AL-X146hard1100.0 / 1009/9OK11.5s1.7k / 3.2k
CG-AL-X147hard1100.0 / 1008/8OK11.4s1.3k / 1.1k
CG-AL-X148hard1100.0 / 1006/6OK10.8s1.1k / 788
CG-AL-X149hard1100.0 / 1007/7OK12.3s1.1k / 937
CG-AL-X150hard1100.0 / 1009/9OK12.6s1.9k / 4.6k
CG-AL-X151hard1100.0 / 1006/6OK10.8s818 / 511
CG-AL-X152hard1100.0 / 1008/8OK11.1s1.1k / 899
CG-AL-X153hard1100.0 / 1009/9OK15.8s888 / 1.1k
CG-AL-X154hard1100.0 / 1009/9OK11.4s1.2k / 1.1k
CG-AL-X155hard1100.0 / 10011/11OK10.9s923 / 905
CG-AL-X156hard1100.0 / 1007/7OK11.3s884 / 541
CG-AL-X157hard1100.0 / 10010/10OK10.9s1.3k / 962
CG-AL-X158hard1100.0 / 1007/7OK10.6s801 / 446
CG-AL-X159hard1100.0 / 1007/7OK11.2s849 / 623
CG-AL-X160hard1100.0 / 10013/13OK10.8s1.2k / 1.6k
CG-AL-X161hard1100.0 / 10010/10OK11.1s1.4k / 1.4k
CG-AL-X162hard1100.0 / 1007/7OK10.9s956 / 781
CG-AL-X163hard1100.0 / 1007/7OK17.1s1.0k / 792
CG-AL-X164hard1100.0 / 1007/7OK11.1s945 / 770
CG-AL-X165hard1100.0 / 10013/13OK14.0s2.6k / 4.8k
CG-AL-X166hard1100.0 / 10014/14OK13.0s1.6k / 1.4k
CG-AL-X167hard2100.0 / 10013/13OK11.7s3.6k / 6.4k
CG-AL-X168hard1100.0 / 1009/9OK11.2s1.3k / 3.9k
CG-AL-X169hard2100.0 / 10011/11OK12.3s3.9k / 4.9k
CG-AL-X170hard1100.0 / 10011/11OK11.7s3.1k / 4.8k
CG-AL-X171hard1100.0 / 1009/9OK11.2s1.4k / 3.3k
CG-AL-X172hard1100.0 / 10011/11OK11.7s2.2k / 4.4k
CG-AL-X173hard2100.0 / 10019/19OK13.6s6.9k / 9.7k
CG-AL-X174hard2100.0 / 10016/16OK12.0s8.6k / 8.8k
CG-AL-X185hard262.5 / 10041/43OK11.4s6.9k / 2.5k
CG-AL-X187hard2100.0 / 10033/33OK12.0s7.5k / 5.6k
CG-AL-X194hard2100.0 / 10050/50OK12.5s10k / 6.7k
CG-AL-X211hard2100.0 / 10043/43OK12.0s9.6k / 6.6k
CG-AL-X214hard2100.0 / 10034/34OK12.0s8.0k / 6.3k
CG-AL-X218hard2100.0 / 10027/27OK11.9s7.9k / 5.9k
CG-AL-X234hard2100.0 / 10035/35OK11.8s9.1k / 4.5k
CG-AL-X239hard2100.0 / 10037/37OK12.3s11k / 7.4k
CG-AL-X244hard2100.0 / 10038/38OK11.7s11k / 7.9k
CG-AL-X245hard2100.0 / 10063/63OK12.1s9.8k / 3.7k
CG-AL-X248hard1100.0 / 10066/66OK14.1s4.3k / 3.5k
CG-AL-X249hard262.5 / 10034/37OK11.8s9.6k / 5.7k
CG-AL-X254hard262.5 / 10064/70OK12.8s15k / 8.7k
CG-AL-X257hard262.5 / 10050/53OK11.9s8.0k / 4.0k
CG-AL-X263hard2100.0 / 10061/61OK12.3s11k / 7.3k
CG-AL-X264hard2100.0 / 10065/65OK11.9s10k / 6.7k
CG-AL-X270hard262.5 / 10060/63OK12.4s16k / 7.7k
CG-AL-X271hard262.5 / 10063/70OK12.6s17k / 9.6k
CG-AL-X272hard2100.0 / 10079/79OK12.1s12k / 6.9k
CG-AL-X274hard2100.0 / 10064/64OK12.5s14k / 8.2k
CG-AL-X276hard262.5 / 10074/78OK12.9s15k / 7.0k
CG-AL-X278hard2100.0 / 10071/71OK12.9s15k / 11k
CG-AL-X283hard2100.0 / 10076/76OK12.8s14k / 6.1k
CG-AL-X289hard262.5 / 10053/57OK12.5s11k / 7.8k
CG-AL-X290hard262.5 / 10041/47OK12.3s13k / 10k
CG-AL-X292hard2100.0 / 10057/57OK12.7s11k / 4.4k
CG-AL-X293hard2100.0 / 10049/49OK11.3s10k / 5.7k
CG-AL-X296hard1100.0 / 10047/47OK13.3s6.6k / 6.9k
CG-AL-X298hard1100.0 / 10055/55OK12.4s4.4k / 4.5k