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.

89.2% 207/232 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.

80.2 / 100
Cost $14.28
Tokens 601k / 592k input / output, all attempts
Duration 1h 2m
Filter:
Per-task results for run 527c20ec-42ad-4111-bf0c-a10702e602a0
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK31.1s258 / 182
CG-AL-E006easy1100.0 / 1007/7OK41.9s305 / 698
CG-AL-E010easy2100.0 / 1005/5OK20.6s705 / 405
CG-AL-E050easy2100.0 / 10013/13OK20.4s1.8k / 1.9k
CG-AL-E052easy1100.0 / 10016/16OK18.7s352 / 496
CG-AL-E054easy20.0 / 1000/0FAIL10.7s1.0k / 796
CG-AL-E056easy2100.0 / 10015/15OK11.0s1.7k / 1.3k
CG-AL-H007hard1100.0 / 10011/11OK12.8s545 / 1.6k
CG-AL-H011hard20.0 / 1000/0FAIL3.7s943 / 1.2k
CG-AL-H014hard20.0 / 1000/0FAIL9.1s1.4k / 1.2k
CG-AL-H017hard1100.0 / 1005/5OK12.2s357 / 1.8k
CG-AL-H020hard2100.0 / 10010/10OK11.0s1.9k / 4.6k
CG-AL-H021hard2100.0 / 10020/20OK11.2s14k / 2.2k
CG-AL-H023hard20.0 / 1000/0FAIL4.3s7.2k / 16k
CG-AL-H027hard2100.0 / 1004/4OK12.2s2.2k / 3.2k
CG-AL-H029hard2100.0 / 10018/18OK11.1s2.6k / 3.8k
CG-AL-H030hard262.5 / 1008/10OK11.0s2.6k / 4.6k
CG-AL-H031hard1100.0 / 10022/22OK11.5s939 / 3.0k
CG-AL-H034hard1100.0 / 1003/3OK11.7s431 / 958
CG-AL-H036hard20.0 / 1000/0FAIL3.9s940 / 1.8k
CG-AL-H037hard1100.0 / 1003/3OK10.8s497 / 1.2k
CG-AL-H041hard1100.0 / 1003/3OK11.6s565 / 2.1k
CG-AL-H050hard2100.0 / 1003/3OK10.6s1.4k / 3.4k
CG-AL-H054hard20.0 / 1000/0FAIL3.9s1.8k / 1.1k
CG-AL-H056hard20.0 / 1000/0FAIL4.0s1.4k / 1.9k
CG-AL-M001medium20.0 / 1000/0FAIL4.0s1.4k / 2.4k
CG-AL-M003medium262.5 / 1000/1OK27.7s1.6k / 2.7k
CG-AL-M004medium1100.0 / 10012/12OK36.4s449 / 4.2k
CG-AL-M006medium2100.0 / 10018/18OK11.5s3.3k / 7.4k
CG-AL-M007medium20.0 / 1000/0FAIL3.8s5.6k / 14k
CG-AL-M008medium20.0 / 1000/0FAIL4.0s6.3k / 15k
CG-AL-M009medium1100.0 / 10011/11OK11.5s429 / 7.1k
CG-AL-M010medium1100.0 / 10021/21OK28.6s596 / 5.6k
CG-AL-M020medium2100.0 / 10017/17OK11.0s2.1k / 2.8k
CG-AL-M023medium1100.0 / 10011/11OK13.6s482 / 743
CG-AL-M025medium2100.0 / 1008/8OK10.8s2.9k / 2.0k
CG-AL-M026medium1100.0 / 1008/8OK11.8s370 / 1.0k
CG-AL-M027medium2100.0 / 10018/18OK10.8s3.4k / 5.8k
CG-AL-M028medium2100.0 / 1003/3OK28.8s1.0k / 748
CG-AL-M031medium2100.0 / 1002/2OK10.8s2.0k / 1.6k
CG-AL-M034medium1100.0 / 1002/2OK11.5s415 / 1.6k
CG-AL-M036medium2100.0 / 1002/2OK10.8s1.5k / 1.1k
CG-AL-M040medium1100.0 / 1002/2OK11.3s311 / 360
CG-AL-M042medium1100.0 / 1008/8OK12.4s498 / 841
CG-AL-X001hard1100.0 / 1002/2OK11.6s308 / 516
CG-AL-X002hard1100.0 / 1004/4OK12.0s488 / 2.4k
CG-AL-X003hard2100.0 / 1003/3OK11.3s816 / 2.2k
CG-AL-X004medium1100.0 / 1003/3OK11.0s358 / 1.4k
CG-AL-X005hard1100.0 / 1002/2OK11.4s327 / 296
CG-AL-X006hard1100.0 / 1003/3OK11.8s383 / 708
CG-AL-X007hard1100.0 / 1002/2OK2m 6s372 / 622
CG-AL-X008hard1100.0 / 1001/1OK11.9s417 / 1.9k
CG-AL-X009medium1100.0 / 1002/2OK11.9s313 / 274
CG-AL-X010medium1100.0 / 1003/3OK12.0s284 / 341
CG-AL-X011medium1100.0 / 1002/2OK12.0s360 / 380
CG-AL-X012hard1100.0 / 1001/1OK12.2s380 / 1.7k
CG-AL-X013hard1100.0 / 1002/2OK11.3s263 / 238
CG-AL-X014medium1100.0 / 1004/4OK12.3s291 / 192
CG-AL-X017medium2100.0 / 1003/3OK11.4s1.4k / 430
CG-AL-X018medium1100.0 / 1003/3OK12.5s384 / 534
CG-AL-X019medium2100.0 / 1003/3OK11.9s1.8k / 1.1k
CG-AL-X022medium2100.0 / 1003/3OK11.3s1.3k / 886
CG-AL-X024medium1100.0 / 1003/3OK12.2s333 / 699
CG-AL-X025medium1100.0 / 1001/1OK14.6s371 / 657
CG-AL-X026medium1100.0 / 1003/3OK12.8s327 / 384
CG-AL-X027medium1100.0 / 1004/4OK11.1s258 / 543
CG-AL-X029medium1100.0 / 1002/2OK11.5s276 / 670
CG-AL-X030medium1100.0 / 1002/2OK11.3s239 / 326
CG-AL-X031medium1100.0 / 1003/3OK12.1s297 / 227
CG-AL-X033hard1100.0 / 1002/2OK11.9s348 / 231
CG-AL-X034hard1100.0 / 1003/3OK11.8s304 / 1.1k
CG-AL-X035hard1100.0 / 1003/3OK11.6s331 / 982
CG-AL-X037hard20.0 / 1000/0FAIL5.8s1.0k / 3.7k
CG-AL-X040hard1100.0 / 1004/4OK11.6s550 / 3.3k
CG-AL-X041hard2100.0 / 1005/5OK10.9s1.1k / 2.4k
CG-AL-X043hard20.0 / 1000/0FAIL4.3s1.4k / 7.1k
CG-AL-X044hard20.0 / 1000/0FAIL3.9s1.5k / 6.8k
CG-AL-X045hard1100.0 / 1003/3OK11.8s371 / 304
CG-AL-X046hard1100.0 / 1002/2OK11.5s369 / 623
CG-AL-X047hard1100.0 / 1002/2OK11.3s390 / 2.2k
CG-AL-X050hard1100.0 / 1002/2OK11.3s405 / 1.2k
CG-AL-X051hard1100.0 / 1002/2OK11.0s509 / 695
CG-AL-X052hard1100.0 / 1003/3OK11.3s358 / 435
CG-AL-X055hard1100.0 / 1005/5OK10.7s344 / 350
CG-AL-X056hard1100.0 / 1005/5OK10.8s280 / 423
CG-AL-X057hard1100.0 / 1005/5OK10.8s250 / 371
CG-AL-X058hard2100.0 / 1005/5OK11.0s925 / 1.5k
CG-AL-X059hard1100.0 / 1003/3OK11.0s327 / 59
CG-AL-X060hard1100.0 / 1003/3OK11.2s302 / 301
CG-AL-X061hard1100.0 / 1004/4OK11.2s364 / 92
CG-AL-X062hard1100.0 / 1004/4OK11.3s358 / 681
CG-AL-X063hard1100.0 / 1003/3OK11.7s360 / 505
CG-AL-X064hard1100.0 / 1007/7OK11.2s277 / 569
CG-AL-X065hard1100.0 / 1006/6OK12.1s709 / 626
CG-AL-X066hard1100.0 / 10014/14OK12.0s1.2k / 1.1k
CG-AL-X067hard1100.0 / 1007/7OK11.5s611 / 996
CG-AL-X068hard1100.0 / 10012/12OK11.6s1.2k / 1.2k
CG-AL-X069hard1100.0 / 1008/8OK11.8s1.1k / 3.2k
CG-AL-X070hard1100.0 / 10012/12OK11.5s1.2k / 763
CG-AL-X071hard1100.0 / 1008/8OK11.5s1.4k / 1.1k
CG-AL-X072hard1100.0 / 1007/7OK12.2s1.1k / 806
CG-AL-X073hard1100.0 / 1008/8OK12.0s1.4k / 1.4k
CG-AL-X074hard2100.0 / 1007/7OK12.3s3.4k / 4.0k
CG-AL-X075hard1100.0 / 1007/7OK12.8s810 / 1.0k
CG-AL-X076hard1100.0 / 10014/14OK12.1s954 / 1.4k
CG-AL-X077hard1100.0 / 10022/22OK12.4s1.5k / 1.3k
CG-AL-X078hard1100.0 / 10017/17OK11.5s1.2k / 905
CG-AL-X079hard1100.0 / 10011/11OK11.3s1.2k / 2.0k
CG-AL-X080hard20.0 / 1000/0FAIL3.9s2.4k / 1.9k
CG-AL-X081hard1100.0 / 1008/8OK11.3s902 / 564
CG-AL-X082hard1100.0 / 10015/15OK11.6s1.2k / 920
CG-AL-X083hard1100.0 / 1009/9OK12.0s1.5k / 1.2k
CG-AL-X084hard1100.0 / 10010/10OK11.6s1.4k / 1.7k
CG-AL-X085hard1100.0 / 1007/7OK11.0s980 / 602
CG-AL-X086hard1100.0 / 1006/6OK11.3s1.4k / 1.6k
CG-AL-X087hard1100.0 / 1003/3OK11.1s1.0k / 834
CG-AL-X088hard1100.0 / 1006/6OK11.9s974 / 972
CG-AL-X089hard1100.0 / 10011/11OK12.2s1.1k / 3.0k
CG-AL-X090hard1100.0 / 10010/10OK12.4s889 / 2.3k
CG-AL-X091hard1100.0 / 1006/6OK11.3s569 / 331
CG-AL-X092hard1100.0 / 10015/15OK11.2s444 / 250
CG-AL-X093hard1100.0 / 10010/10OK11.1s989 / 811
CG-AL-X094hard1100.0 / 1007/7OK11.1s754 / 558
CG-AL-X095hard262.5 / 1003/5OK11.1s2.8k / 2.6k
CG-AL-X096hard1100.0 / 10049/49OK11.8s3.3k / 3.1k
CG-AL-X097hard1100.0 / 10046/46OK12.6s3.4k / 3.1k
CG-AL-X098hard1100.0 / 10029/29OK12.4s2.6k / 2.2k
CG-AL-X099hard1100.0 / 10039/39OK13.8s3.6k / 4.0k
CG-AL-X100hard1100.0 / 10035/35OK11.7s3.5k / 3.9k
CG-AL-X101hard1100.0 / 10010/10OK10.9s1.1k / 933
CG-AL-X102hard1100.0 / 1008/8OK10.9s531 / 2.0k
CG-AL-X103hard1100.0 / 1007/7OK11.3s725 / 518
CG-AL-X104hard1100.0 / 1006/6OK11.6s1.1k / 905
CG-AL-X105hard1100.0 / 1006/6OK10.9s777 / 400
CG-AL-X106hard1100.0 / 1005/5OK11.2s878 / 1.1k
CG-AL-X107hard1100.0 / 1004/4OK11.0s805 / 777
CG-AL-X108hard1100.0 / 1006/6OK11.9s729 / 418
CG-AL-X109hard1100.0 / 1005/5OK11.3s548 / 424
CG-AL-X110hard1100.0 / 10017/17OK11.2s1.2k / 959
CG-AL-X111hard1100.0 / 1008/8OK11.2s1.2k / 2.2k
CG-AL-X112hard1100.0 / 10012/12OK11.0s906 / 3.4k
CG-AL-X113hard1100.0 / 10013/13OK11.6s705 / 967
CG-AL-X114hard1100.0 / 1007/7OK11.3s718 / 477
CG-AL-X115hard1100.0 / 10013/13OK11.5s478 / 443
CG-AL-X116hard1100.0 / 10017/17OK11.5s926 / 1.5k
CG-AL-X117hard1100.0 / 1008/8OK11.6s1.0k / 919
CG-AL-X118hard1100.0 / 10017/17OK11.3s1.4k / 1.3k
CG-AL-X119hard1100.0 / 10015/15OK11.0s1.7k / 1.7k
CG-AL-X120hard1100.0 / 10012/12OK11.0s1.2k / 1.1k
CG-AL-X121hard1100.0 / 1006/6OK11.3s1.0k / 866
CG-AL-X122hard1100.0 / 10010/10OK11.4s1.5k / 1.5k
CG-AL-X123hard1100.0 / 1005/5OK11.7s603 / 434
CG-AL-X124hard1100.0 / 10010/10OK11.7s994 / 798
CG-AL-X125hard1100.0 / 1008/8OK11.7s1.4k / 1.3k
CG-AL-X126hard1100.0 / 10014/14OK12.1s711 / 425
CG-AL-X127hard1100.0 / 1005/5OK12.5s666 / 475
CG-AL-X128hard1100.0 / 1008/8OK12.6s1.1k / 811
CG-AL-X129hard1100.0 / 10014/14OK12.6s1.2k / 1.0k
CG-AL-X130hard2100.0 / 1005/5OK11.0s1.1k / 746
CG-AL-X131hard1100.0 / 10013/13OK12.8s941 / 691
CG-AL-X132hard1100.0 / 10010/10OK12.3s709 / 410
CG-AL-X133hard2100.0 / 1008/8OK11.2s5.9k / 6.2k
CG-AL-X134hard1100.0 / 1006/6OK14.2s1.2k / 2.0k
CG-AL-X135hard1100.0 / 1004/4OK13.8s866 / 554
CG-AL-X136hard1100.0 / 1007/7OK14.4s754 / 433
CG-AL-X137hard1100.0 / 1004/4OK13.4s915 / 985
CG-AL-X138hard1100.0 / 1009/9OK13.9s1.4k / 2.1k
CG-AL-X139hard1100.0 / 10011/11OK13.9s1.6k / 1.5k
CG-AL-X140hard2100.0 / 1007/7OK11.2s4.2k / 6.7k
CG-AL-X141hard1100.0 / 10039/39OK30.4s3.5k / 3.4k
CG-AL-X142hard2100.0 / 10048/48OK12.2s9.2k / 9.9k
CG-AL-X143hard1100.0 / 10035/35OK18.9s4.0k / 4.0k
CG-AL-X144hard1100.0 / 10043/43OK13.4s3.6k / 3.4k
CG-AL-X145hard1100.0 / 10032/32OK13.2s4.2k / 3.9k
CG-AL-X146hard1100.0 / 1009/9OK12.3s1.7k / 4.3k
CG-AL-X147hard1100.0 / 1008/8OK11.1s1.3k / 1.1k
CG-AL-X148hard1100.0 / 1006/6OK10.9s1.1k / 788
CG-AL-X149hard1100.0 / 1007/7OK11.4s1.1k / 1.0k
CG-AL-X150hard1100.0 / 1009/9OK11.9s1.9k / 4.5k
CG-AL-X151hard1100.0 / 1006/6OK11.8s818 / 511
CG-AL-X152hard1100.0 / 1008/8OK12.3s1.1k / 761
CG-AL-X153hard2100.0 / 1009/9OK15.2s2.1k / 5.5k
CG-AL-X154hard1100.0 / 1009/9OK12.1s1.2k / 1.3k
CG-AL-X155hard1100.0 / 10011/11OK12.7s923 / 939
CG-AL-X156hard1100.0 / 1007/7OK12.2s884 / 541
CG-AL-X157hard1100.0 / 10010/10OK12.9s1.3k / 996
CG-AL-X158hard1100.0 / 1007/7OK13.6s801 / 446
CG-AL-X159hard1100.0 / 1007/7OK13.7s849 / 574
CG-AL-X160hard1100.0 / 10013/13OK13.7s1.2k / 1.2k
CG-AL-X161hard1100.0 / 10010/10OK14.4s1.4k / 1.3k
CG-AL-X162hard1100.0 / 1007/7OK14.6s956 / 738
CG-AL-X163hard1100.0 / 1007/7OK13.5s1.0k / 809
CG-AL-X164hard1100.0 / 1007/7OK13.0s945 / 701
CG-AL-X165hard2100.0 / 10013/13OK13.7s6.1k / 7.1k
CG-AL-X166hard1100.0 / 10014/14OK14.3s1.6k / 1.3k
CG-AL-X167hard2100.0 / 10013/13OK11.8s3.7k / 7.2k
CG-AL-X168hard1100.0 / 1009/9OK12.0s1.3k / 4.0k
CG-AL-X169hard2100.0 / 10011/11OK12.2s4.0k / 6.1k
CG-AL-X170hard1100.0 / 10011/11OK12.1s3.1k / 5.0k
CG-AL-X171hard1100.0 / 1009/9OK11.9s1.4k / 3.1k
CG-AL-X172hard1100.0 / 10011/11OK12.4s2.2k / 4.1k
CG-AL-X173hard2100.0 / 10019/19OK12.6s6.9k / 8.8k
CG-AL-X174hard1100.0 / 10016/16OK12.1s3.9k / 5.0k
CG-AL-X185hard262.5 / 10041/43OK12.3s6.9k / 3.6k
CG-AL-X187hard2100.0 / 10033/33OK11.9s7.6k / 5.2k
CG-AL-X194hard2100.0 / 10050/50OK12.3s10k / 6.6k
CG-AL-X211hard2100.0 / 10043/43OK12.5s9.9k / 8.2k
CG-AL-X214hard2100.0 / 10034/34OK11.6s8.0k / 6.2k
CG-AL-X218hard262.5 / 10024/27OK11.7s7.9k / 4.1k
CG-AL-X234hard2100.0 / 10035/35OK11.8s9.1k / 5.0k
CG-AL-X239hard262.5 / 10034/37OK12.0s11k / 5.1k
CG-AL-X244hard262.5 / 10035/38OK11.9s11k / 6.5k
CG-AL-X245hard2100.0 / 10063/63OK12.0s10.0k / 4.6k
CG-AL-X248hard2100.0 / 10066/66OK12.0s9.7k / 3.9k
CG-AL-X249hard2100.0 / 10037/37OK11.9s9.6k / 5.9k
CG-AL-X254hard262.5 / 10064/70OK12.0s15k / 7.9k
CG-AL-X257hard20.0 / 1000/0FAIL4.2s9.8k / 6.1k
CG-AL-X263hard2100.0 / 10061/61OK12.7s11k / 6.2k
CG-AL-X264hard2100.0 / 10065/65OK12.3s12k / 5.1k
CG-AL-X270hard2100.0 / 10063/63OK12.8s17k / 10k
CG-AL-X271hard2100.0 / 10070/70OK12.7s17k / 8.8k
CG-AL-X272hard1100.0 / 10079/79OK13.6s6.0k / 5.8k
CG-AL-X274hard2100.0 / 10064/64OK12.5s12k / 8.6k
CG-AL-X276hard262.5 / 10074/78OK13.0s14k / 7.0k
CG-AL-X278hard2100.0 / 10071/71OK12.8s15k / 9.3k
CG-AL-X283hard2100.0 / 10076/76OK12.3s14k / 6.3k
CG-AL-X289hard2100.0 / 10057/57OK12.3s12k / 6.9k
CG-AL-X290hard262.5 / 10041/47OK11.9s14k / 9.2k
CG-AL-X292hard1100.0 / 10057/57OK13.8s4.8k / 3.9k
CG-AL-X293hard2100.0 / 10049/49OK11.8s10k / 5.1k
CG-AL-X296hard1100.0 / 10047/47OK15.0s6.6k / 7.4k
CG-AL-X298hard2100.0 / 10055/55OK11.1s9.1k / 5.8k