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.

87.9% 204/232 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.

78.8 / 100
Cost $5.68
Tokens 579k / 452k input / output, all attempts
Duration 52m 22s
Filter:
Per-task results for run 910691d7-27bc-4ab0-9017-6dfc644eeb0e
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK14.9s258 / 438
CG-AL-E006easy262.5 / 1000/1OK26.3s946 / 1.1k
CG-AL-E010easy1100.0 / 1005/5OK15.3s280 / 284
CG-AL-E050easy2100.0 / 10013/13OK16.4s1.8k / 1.8k
CG-AL-E052easy1100.0 / 10016/16OK9.9s352 / 301
CG-AL-E054easy2100.0 / 1009/9OK16.2s1.0k / 975
CG-AL-E056easy2100.0 / 10015/15OK10.6s1.7k / 835
CG-AL-H007hard1100.0 / 10011/11OK10.1s545 / 1.0k
CG-AL-H011hard20.0 / 1000/0FAIL4.0s940 / 1.5k
CG-AL-H014hard20.0 / 1000/0FAIL3.9s1.5k / 1.5k
CG-AL-H017hard1100.0 / 1005/5OK9.7s357 / 737
CG-AL-H020hard2100.0 / 10010/10OK10.4s1.7k / 2.4k
CG-AL-H021hard20.0 / 1000/0FAIL3.9s2.0k / 1.7k
CG-AL-H023hard20.0 / 1000/0FAIL3.9s7.0k / 12k
CG-AL-H027hard1100.0 / 1004/4OK10.0s738 / 942
CG-AL-H029hard2100.0 / 10018/18OK10.4s2.6k / 3.5k
CG-AL-H030hard262.5 / 1008/10OK10.2s2.0k / 2.5k
CG-AL-H031hard1100.0 / 10022/22OK10.2s939 / 1.9k
CG-AL-H034hard1100.0 / 1003/3OK9.8s431 / 721
CG-AL-H036hard20.0 / 1000/0FAIL9.0s1.0k / 1.4k
CG-AL-H037hard20.0 / 1000/0FAIL5.1s1.2k / 1.0k
CG-AL-H041hard1100.0 / 1003/3OK9.8s565 / 1.1k
CG-AL-H050hard2100.0 / 1003/3OK10.7s1.4k / 1.6k
CG-AL-H054hard20.0 / 1000/0FAIL4.2s1.8k / 1.3k
CG-AL-H056hard20.0 / 1000/0FAIL4.1s1.4k / 925
CG-AL-M001medium20.0 / 1000/0FAIL4.2s1.4k / 1.9k
CG-AL-M003medium1100.0 / 1009/9OK10.0s419 / 1.6k
CG-AL-M004medium1100.0 / 10012/12OK28.0s449 / 1.6k
CG-AL-M006medium262.5 / 10017/18OK10.9s3.0k / 4.9k
CG-AL-M007medium20.0 / 1000/0FAIL4.1s3.7k / 8.5k
CG-AL-M008medium262.5 / 1001/12OK12.3s4.5k / 9.6k
CG-AL-M009medium1100.0 / 10011/11OK9.3s429 / 5.5k
CG-AL-M010medium1100.0 / 10021/21OK21.0s596 / 3.1k
CG-AL-M020medium2100.0 / 10017/17OK16.2s2.1k / 2.2k
CG-AL-M023medium1100.0 / 10011/11OK10.3s482 / 741
CG-AL-M025medium2100.0 / 1008/8OK12.0s1.3k / 2.7k
CG-AL-M026medium2100.0 / 1008/8OK11.4s1.2k / 1.3k
CG-AL-M027medium2100.0 / 10018/18OK10.4s3.7k / 3.5k
CG-AL-M028medium2100.0 / 1003/3OK24.2s1.0k / 674
CG-AL-M031medium2100.0 / 1002/2OK10.1s2.0k / 1.4k
CG-AL-M034medium1100.0 / 1002/2OK10.0s415 / 530
CG-AL-M036medium2100.0 / 1002/2OK9.9s1.5k / 1.1k
CG-AL-M040medium1100.0 / 1002/2OK10.0s311 / 619
CG-AL-M042medium1100.0 / 1008/8OK9.6s498 / 566
CG-AL-X001hard1100.0 / 1002/2OK13.1s308 / 257
CG-AL-X002hard1100.0 / 1004/4OK9.5s488 / 1.3k
CG-AL-X003hard2100.0 / 1003/3OK10.3s870 / 1.2k
CG-AL-X004medium1100.0 / 1003/3OK9.6s358 / 757
CG-AL-X005hard1100.0 / 1002/2OK10.2s327 / 420
CG-AL-X006hard1100.0 / 1003/3OK10.1s383 / 535
CG-AL-X007hard1100.0 / 1002/2OK1m 16s372 / 577
CG-AL-X008hard1100.0 / 1001/1OK11.7s417 / 831
CG-AL-X009medium1100.0 / 1002/2OK10.2s313 / 328
CG-AL-X010medium1100.0 / 1003/3OK10.5s284 / 274
CG-AL-X011medium1100.0 / 1002/2OK9.5s360 / 315
CG-AL-X012hard1100.0 / 1001/1OK9.6s380 / 332
CG-AL-X013hard1100.0 / 1002/2OK10.7s263 / 212
CG-AL-X014medium1100.0 / 1004/4OK10.4s291 / 125
CG-AL-X017medium2100.0 / 1003/3OK10.3s1.4k / 296
CG-AL-X018medium1100.0 / 1003/3OK10.1s384 / 303
CG-AL-X019medium2100.0 / 1003/3OK10.3s1.7k / 684
CG-AL-X022medium2100.0 / 1003/3OK10.1s1.2k / 510
CG-AL-X024medium1100.0 / 1003/3OK9.5s333 / 626
CG-AL-X025medium1100.0 / 1001/1OK9.5s371 / 584
CG-AL-X026medium1100.0 / 1003/3OK10.0s327 / 170
CG-AL-X027medium1100.0 / 1004/4OK11.0s258 / 609
CG-AL-X029medium1100.0 / 1002/2OK9.6s276 / 1.1k
CG-AL-X030medium1100.0 / 1002/2OK9.7s239 / 177
CG-AL-X031medium1100.0 / 1003/3OK9.8s297 / 216
CG-AL-X033hard1100.0 / 1002/2OK9.8s348 / 197
CG-AL-X034hard1100.0 / 1003/3OK10.1s304 / 318
CG-AL-X035hard1100.0 / 1003/3OK9.9s331 / 497
CG-AL-X037hard1100.0 / 1004/4OK11.3s408 / 989
CG-AL-X040hard1100.0 / 1004/4OK11.9s550 / 1.3k
CG-AL-X041hard1100.0 / 1005/5OK10.8s446 / 948
CG-AL-X043hard2100.0 / 1001/1OK10.8s1.6k / 5.7k
CG-AL-X044hard20.0 / 1000/0FAIL3.9s1.6k / 3.2k
CG-AL-X045hard1100.0 / 1003/3OK12.1s371 / 188
CG-AL-X046hard1100.0 / 1002/2OK10.1s369 / 246
CG-AL-X047hard1100.0 / 1002/2OK10.0s390 / 1.4k
CG-AL-X050hard1100.0 / 1002/2OK9.9s405 / 631
CG-AL-X051hard1100.0 / 1002/2OK9.7s509 / 407
CG-AL-X052hard1100.0 / 1003/3OK9.9s358 / 456
CG-AL-X055hard1100.0 / 1005/5OK9.6s344 / 469
CG-AL-X056hard1100.0 / 1005/5OK9.6s280 / 582
CG-AL-X057hard1100.0 / 1005/5OK9.7s250 / 141
CG-AL-X058hard1100.0 / 1005/5OK9.6s314 / 828
CG-AL-X059hard1100.0 / 1003/3OK9.8s327 / 122
CG-AL-X060hard1100.0 / 1003/3OK9.8s302 / 208
CG-AL-X061hard1100.0 / 1004/4OK9.9s364 / 92
CG-AL-X062hard1100.0 / 1004/4OK10.0s358 / 421
CG-AL-X063hard1100.0 / 1003/3OK9.8s360 / 670
CG-AL-X064hard1100.0 / 1007/7OK9.8s277 / 456
CG-AL-X065hard1100.0 / 1006/6OK9.8s709 / 644
CG-AL-X066hard1100.0 / 10014/14OK10.0s1.2k / 1.0k
CG-AL-X067hard2100.0 / 1007/7OK10.4s1.6k / 1.5k
CG-AL-X068hard1100.0 / 10012/12OK10.5s1.2k / 1.0k
CG-AL-X069hard1100.0 / 1008/8OK10.2s1.1k / 2.6k
CG-AL-X070hard1100.0 / 10012/12OK10.1s1.2k / 812
CG-AL-X071hard1100.0 / 1008/8OK10.1s1.4k / 1.1k
CG-AL-X072hard1100.0 / 1007/7OK10.0s1.1k / 793
CG-AL-X073hard1100.0 / 1008/8OK10.3s1.4k / 1.3k
CG-AL-X074hard2100.0 / 1007/7OK10.8s3.4k / 3.6k
CG-AL-X075hard1100.0 / 1007/7OK9.8s810 / 1.3k
CG-AL-X076hard1100.0 / 10014/14OK9.9s954 / 1.2k
CG-AL-X077hard1100.0 / 10022/22OK10.4s1.5k / 1.2k
CG-AL-X078hard1100.0 / 10017/17OK9.9s1.2k / 946
CG-AL-X079hard1100.0 / 10011/11OK9.9s1.2k / 1.4k
CG-AL-X080hard20.0 / 1000/0FAIL4.6s2.4k / 1.9k
CG-AL-X081hard1100.0 / 1008/8OK10.0s902 / 587
CG-AL-X082hard1100.0 / 10015/15OK9.8s1.2k / 944
CG-AL-X083hard1100.0 / 1009/9OK9.5s1.5k / 1.2k
CG-AL-X084hard1100.0 / 10010/10OK10.2s1.4k / 1.9k
CG-AL-X085hard1100.0 / 1007/7OK9.8s980 / 606
CG-AL-X086hard1100.0 / 1006/6OK9.6s1.4k / 1.2k
CG-AL-X087hard1100.0 / 1003/3OK10.0s1.0k / 1.1k
CG-AL-X088hard1100.0 / 1006/6OK9.6s974 / 843
CG-AL-X089hard1100.0 / 10011/11OK9.9s1.1k / 2.3k
CG-AL-X090hard1100.0 / 10010/10OK9.9s889 / 1.2k
CG-AL-X091hard1100.0 / 1006/6OK9.9s569 / 332
CG-AL-X092hard1100.0 / 10015/15OK9.7s444 / 241
CG-AL-X093hard1100.0 / 10010/10OK10.1s989 / 883
CG-AL-X094hard1100.0 / 1007/7OK9.7s754 / 533
CG-AL-X095hard262.5 / 1003/5OK10.9s2.4k / 1.7k
CG-AL-X096hard1100.0 / 10049/49OK10.3s3.3k / 2.9k
CG-AL-X097hard1100.0 / 10046/46OK10.6s3.4k / 3.0k
CG-AL-X098hard1100.0 / 10029/29OK10.1s2.6k / 2.1k
CG-AL-X099hard1100.0 / 10039/39OK11.6s3.6k / 4.3k
CG-AL-X100hard1100.0 / 10035/35OK10.5s3.5k / 3.5k
CG-AL-X101hard1100.0 / 10010/10OK10.9s1.1k / 994
CG-AL-X102hard1100.0 / 1008/8OK10.3s531 / 1.6k
CG-AL-X103hard1100.0 / 1007/7OK10.2s725 / 480
CG-AL-X104hard1100.0 / 1006/6OK10.0s1.1k / 869
CG-AL-X105hard1100.0 / 1006/6OK10.2s777 / 464
CG-AL-X106hard1100.0 / 1005/5OK10.1s878 / 997
CG-AL-X107hard1100.0 / 1004/4OK9.6s805 / 883
CG-AL-X108hard1100.0 / 1006/6OK10.4s729 / 390
CG-AL-X109hard1100.0 / 1005/5OK10.0s548 / 365
CG-AL-X110hard1100.0 / 10017/17OK10.0s1.2k / 981
CG-AL-X111hard1100.0 / 1008/8OK9.6s1.2k / 2.2k
CG-AL-X112hard1100.0 / 10012/12OK10.3s906 / 1.6k
CG-AL-X113hard1100.0 / 10013/13OK10.4s705 / 2.6k
CG-AL-X114hard1100.0 / 1007/7OK9.6s718 / 456
CG-AL-X115hard1100.0 / 10013/13OK9.6s478 / 523
CG-AL-X116hard1100.0 / 10017/17OK10.2s926 / 932
CG-AL-X117hard1100.0 / 1008/8OK10.3s1.0k / 934
CG-AL-X118hard1100.0 / 10017/17OK13.1s1.4k / 1.2k
CG-AL-X119hard1100.0 / 10015/15OK10.0s1.7k / 1.6k
CG-AL-X120hard1100.0 / 10012/12OK10.1s1.2k / 1.1k
CG-AL-X121hard1100.0 / 1006/6OK10.2s1.0k / 827
CG-AL-X122hard1100.0 / 10010/10OK9.7s1.5k / 1.5k
CG-AL-X123hard1100.0 / 1005/5OK10.3s603 / 494
CG-AL-X124hard1100.0 / 10010/10OK10.0s994 / 731
CG-AL-X125hard1100.0 / 1008/8OK10.4s1.4k / 1.3k
CG-AL-X126hard1100.0 / 10014/14OK9.7s711 / 366
CG-AL-X127hard1100.0 / 1005/5OK9.6s666 / 649
CG-AL-X128hard1100.0 / 1008/8OK10.1s1.1k / 832
CG-AL-X129hard1100.0 / 10014/14OK10.1s1.2k / 1.1k
CG-AL-X130hard1100.0 / 1005/5OK9.7s529 / 451
CG-AL-X131hard1100.0 / 10013/13OK10.7s941 / 663
CG-AL-X132hard1100.0 / 10010/10OK10.4s709 / 429
CG-AL-X133hard1100.0 / 1008/8OK11.3s1.6k / 3.1k
CG-AL-X134hard1100.0 / 1006/6OK10.5s1.2k / 1.2k
CG-AL-X135hard2100.0 / 1004/4OK10.7s1.8k / 1.2k
CG-AL-X136hard1100.0 / 1007/7OK10.3s754 / 370
CG-AL-X137hard1100.0 / 1004/4OK10.1s915 / 668
CG-AL-X138hard1100.0 / 1009/9OK10.9s1.4k / 1.4k
CG-AL-X139hard1100.0 / 10011/11OK10.5s1.6k / 1.4k
CG-AL-X140hard20.0 / 1000/0FAIL3.8s4.1k / 5.7k
CG-AL-X141hard1100.0 / 10039/39OK11.4s3.5k / 3.1k
CG-AL-X142hard2100.0 / 10048/48OK11.4s9.1k / 9.1k
CG-AL-X143hard1100.0 / 10035/35OK15.5s4.0k / 3.7k
CG-AL-X144hard2100.0 / 10043/43OK11.4s7.9k / 6.4k
CG-AL-X145hard1100.0 / 10032/32OK11.2s4.2k / 3.9k
CG-AL-X146hard1100.0 / 1009/9OK12.3s1.7k / 2.6k
CG-AL-X147hard1100.0 / 1008/8OK12.9s1.3k / 1.0k
CG-AL-X148hard1100.0 / 1006/6OK12.3s1.1k / 806
CG-AL-X149hard1100.0 / 1007/7OK10.9s1.1k / 952
CG-AL-X150hard1100.0 / 1009/9OK10.3s1.9k / 3.5k
CG-AL-X151hard1100.0 / 1006/6OK9.9s818 / 538
CG-AL-X152hard1100.0 / 1008/8OK9.7s1.1k / 774
CG-AL-X153hard2100.0 / 1009/9OK15.0s2.6k / 4.0k
CG-AL-X154hard1100.0 / 1009/9OK9.8s1.2k / 1.1k
CG-AL-X155hard2100.0 / 10011/11OK10.4s2.0k / 2.2k
CG-AL-X156hard1100.0 / 1007/7OK9.8s884 / 563
CG-AL-X157hard1100.0 / 10010/10OK10.0s1.3k / 964
CG-AL-X158hard1100.0 / 1007/7OK10.5s801 / 462
CG-AL-X159hard1100.0 / 1007/7OK10.4s849 / 590
CG-AL-X160hard1100.0 / 10013/13OK9.9s1.2k / 1.2k
CG-AL-X161hard1100.0 / 10010/10OK10.1s1.4k / 1.3k
CG-AL-X162hard1100.0 / 1007/7OK9.8s956 / 748
CG-AL-X163hard1100.0 / 1007/7OK9.8s1.0k / 746
CG-AL-X164hard1100.0 / 1007/7OK10.1s945 / 953
CG-AL-X165hard1100.0 / 10013/13OK12.7s2.6k / 3.1k
CG-AL-X166hard1100.0 / 10014/14OK11.0s1.6k / 1.3k
CG-AL-X167hard2100.0 / 10013/13OK11.3s3.6k / 6.1k
CG-AL-X168hard2100.0 / 1009/9OK10.8s4.8k / 3.5k
CG-AL-X169hard2100.0 / 10011/11OK11.2s4.1k / 4.3k
CG-AL-X170hard1100.0 / 10011/11OK10.4s3.1k / 3.0k
CG-AL-X171hard1100.0 / 1009/9OK10.7s1.4k / 2.6k
CG-AL-X172hard1100.0 / 10011/11OK10.5s2.2k / 3.6k
CG-AL-X173hard262.5 / 10017/19OK12.1s7.1k / 7.7k
CG-AL-X174hard1100.0 / 10016/16OK10.9s3.9k / 4.7k
CG-AL-X185hard262.5 / 10041/43OK10.6s6.9k / 1.6k
CG-AL-X187hard262.5 / 10030/33OK11.3s7.5k / 4.1k
CG-AL-X194hard2100.0 / 10050/50OK11.2s9.9k / 3.6k
CG-AL-X211hard2100.0 / 10043/43OK11.1s9.1k / 4.7k
CG-AL-X214hard262.5 / 10031/34OK11.2s8.0k / 4.2k
CG-AL-X218hard2100.0 / 10027/27OK12.8s7.9k / 4.4k
CG-AL-X234hard1100.0 / 10035/35OK10.7s3.7k / 3.0k
CG-AL-X239hard262.5 / 10034/37OK11.1s11k / 3.4k
CG-AL-X244hard2100.0 / 10038/38OK10.8s11k / 5.0k
CG-AL-X245hard2100.0 / 10063/63OK11.3s9.9k / 3.1k
CG-AL-X248hard2100.0 / 10066/66OK11.2s9.7k / 2.6k
CG-AL-X249hard262.5 / 10034/37OK11.2s9.6k / 3.7k
CG-AL-X254hard262.5 / 10064/70OK11.9s13k / 5.7k
CG-AL-X257hard262.5 / 10050/53OK11.2s8.0k / 3.5k
CG-AL-X263hard2100.0 / 10061/61OK12.3s11k / 6.6k
CG-AL-X264hard2100.0 / 10065/65OK11.3s10k / 3.9k
CG-AL-X270hard2100.0 / 10063/63OK11.7s16k / 6.7k
CG-AL-X271hard2100.0 / 10070/70OK11.9s15k / 9.1k
CG-AL-X272hard2100.0 / 10079/79OK11.7s13k / 4.5k
CG-AL-X274hard2100.0 / 10064/64OK11.7s12k / 5.6k
CG-AL-X276hard2100.0 / 10078/78OK11.7s15k / 5.1k
CG-AL-X278hard2100.0 / 10071/71OK12.3s14k / 5.7k
CG-AL-X283hard2100.0 / 10076/76OK11.9s14k / 4.5k
CG-AL-X289hard262.5 / 10053/57OK11.9s10k / 6.1k
CG-AL-X290hard2100.0 / 10047/47OK11.8s12k / 4.0k
CG-AL-X292hard262.5 / 10051/57OK12.2s9.3k / 3.1k
CG-AL-X293hard2100.0 / 10049/49OK12.6s10k / 4.0k
CG-AL-X296hard2100.0 / 10047/47OK13.3s14k / 8.5k
CG-AL-X298hard1100.0 / 10055/55OK10.9s4.4k / 3.0k