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.

91.4% 212/232 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.

82.2 / 100
Cost $14.05
Tokens 598k / 582k input / output, all attempts
Duration 59m 35s
Filter:
Per-task results for run 55ca6e8d-94c5-4bf3-98a5-9b31487386f2
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.2s258 / 182
CG-AL-E006easy1100.0 / 1007/7OK31.3s305 / 839
CG-AL-E010easy2100.0 / 1005/5OK19.0s717 / 551
CG-AL-E050easy20.0 / 1000/0FAIL9.0s1.8k / 2.2k
CG-AL-E052easy1100.0 / 10016/16OK16.4s352 / 461
CG-AL-E054easy20.0 / 1000/0FAIL9.4s961 / 802
CG-AL-E056easy2100.0 / 10015/15OK17.8s1.7k / 1.2k
CG-AL-H007hard1100.0 / 10011/11OK12.1s545 / 1.6k
CG-AL-H011hard20.0 / 1000/0FAIL4.0s939 / 1.3k
CG-AL-H014hard20.0 / 1000/0FAIL9.0s1.6k / 1.9k
CG-AL-H017hard1100.0 / 1005/5OK12.3s357 / 1.3k
CG-AL-H020hard1100.0 / 10010/10OK11.6s467 / 1.4k
CG-AL-H021hard2100.0 / 10020/20OK11.2s14k / 1.9k
CG-AL-H023hard2100.0 / 10025/25OK11.3s6.5k / 13k
CG-AL-H027hard2100.0 / 1004/4OK11.4s2.2k / 4.1k
CG-AL-H029hard2100.0 / 10018/18OK11.6s2.6k / 4.8k
CG-AL-H030hard1100.0 / 10010/10OK11.4s669 / 3.1k
CG-AL-H031hard1100.0 / 10022/22OK11.2s939 / 2.5k
CG-AL-H034hard1100.0 / 1003/3OK12.4s431 / 630
CG-AL-H036hard20.0 / 1000/0FAIL3.8s945 / 3.3k
CG-AL-H037hard1100.0 / 1003/3OK11.4s497 / 1.3k
CG-AL-H041hard1100.0 / 1003/3OK11.2s565 / 3.5k
CG-AL-H050hard262.5 / 1002/3OK10.7s1.4k / 1.5k
CG-AL-H054hard2100.0 / 1005/5OK10.7s1.9k / 1.2k
CG-AL-H056hard20.0 / 1000/0FAIL3.9s1.4k / 971
CG-AL-M001medium20.0 / 1000/0FAIL3.9s1.4k / 2.9k
CG-AL-M003medium1100.0 / 1009/9OK11.2s419 / 2.7k
CG-AL-M004medium1100.0 / 10012/12OK30.1s449 / 3.8k
CG-AL-M006medium2100.0 / 10018/18OK11.8s3.0k / 7.6k
CG-AL-M007medium262.5 / 10013/15OK12.5s4.8k / 12k
CG-AL-M008medium262.5 / 1002/12OK12.5s6.4k / 14k
CG-AL-M009medium1100.0 / 10011/11OK10.7s429 / 5.9k
CG-AL-M010medium1100.0 / 10021/21OK24.4s596 / 5.4k
CG-AL-M020medium2100.0 / 10017/17OK11.6s2.1k / 2.7k
CG-AL-M023medium1100.0 / 10011/11OK17.5s482 / 931
CG-AL-M025medium1100.0 / 1008/8OK11.8s400 / 2.5k
CG-AL-M026medium1100.0 / 1008/8OK11.8s370 / 810
CG-AL-M027medium2100.0 / 10018/18OK11.3s3.4k / 3.7k
CG-AL-M028medium2100.0 / 1003/3OK26.2s1.0k / 1.1k
CG-AL-M031medium2100.0 / 1002/2OK10.9s2.0k / 1.9k
CG-AL-M034medium1100.0 / 1002/2OK11.0s415 / 711
CG-AL-M036medium2100.0 / 1002/2OK10.9s1.5k / 1.0k
CG-AL-M040medium1100.0 / 1002/2OK10.7s311 / 436
CG-AL-M042medium1100.0 / 1008/8OK11.1s498 / 1.1k
CG-AL-X001hard1100.0 / 1002/2OK11.1s308 / 562
CG-AL-X002hard1100.0 / 1004/4OK11.4s488 / 2.2k
CG-AL-X003hard262.5 / 1002/3OK11.2s605 / 2.7k
CG-AL-X004medium1100.0 / 1003/3OK11.5s358 / 994
CG-AL-X005hard1100.0 / 1002/2OK11.9s327 / 344
CG-AL-X006hard1100.0 / 1003/3OK11.5s383 / 566
CG-AL-X007hard1100.0 / 1002/2OK1m 32s372 / 633
CG-AL-X008hard2100.0 / 1001/1OK10.8s1.3k / 2.8k
CG-AL-X009medium1100.0 / 1002/2OK12.5s313 / 245
CG-AL-X010medium1100.0 / 1003/3OK16.3s284 / 297
CG-AL-X011medium1100.0 / 1002/2OK11.6s360 / 334
CG-AL-X012hard1100.0 / 1001/1OK13.3s380 / 644
CG-AL-X013hard1100.0 / 1002/2OK23.4s263 / 382
CG-AL-X014medium1100.0 / 1004/4OK22.1s291 / 233
CG-AL-X017medium2100.0 / 1003/3OK11.7s1.4k / 586
CG-AL-X018medium1100.0 / 1003/3OK11.7s384 / 678
CG-AL-X019medium2100.0 / 1003/3OK11.0s1.8k / 1.2k
CG-AL-X022medium2100.0 / 1003/3OK10.5s1.3k / 656
CG-AL-X024medium1100.0 / 1003/3OK12.0s333 / 849
CG-AL-X025medium1100.0 / 1001/1OK11.8s371 / 516
CG-AL-X026medium1100.0 / 1003/3OK12.1s327 / 312
CG-AL-X027medium1100.0 / 1004/4OK11.7s258 / 424
CG-AL-X029medium1100.0 / 1002/2OK11.4s276 / 651
CG-AL-X030medium1100.0 / 1002/2OK11.4s239 / 379
CG-AL-X031medium1100.0 / 1003/3OK11.5s297 / 335
CG-AL-X033hard1100.0 / 1002/2OK11.8s348 / 259
CG-AL-X034hard1100.0 / 1003/3OK11.6s304 / 581
CG-AL-X035hard1100.0 / 1003/3OK11.3s331 / 1.0k
CG-AL-X037hard1100.0 / 1004/4OK11.2s408 / 3.3k
CG-AL-X040hard20.0 / 1000/0FAIL3.9s1.4k / 3.4k
CG-AL-X041hard1100.0 / 1005/5OK12.3s446 / 1.7k
CG-AL-X043hard2100.0 / 1001/1OK17.1s1.4k / 4.6k
CG-AL-X044hard2100.0 / 1003/3OK11.2s1.7k / 8.0k
CG-AL-X045hard1100.0 / 1003/3OK12.3s371 / 343
CG-AL-X046hard1100.0 / 1002/2OK11.4s369 / 569
CG-AL-X047hard1100.0 / 1002/2OK11.2s390 / 3.0k
CG-AL-X050hard1100.0 / 1002/2OK13.2s405 / 1.5k
CG-AL-X051hard1100.0 / 1002/2OK11.6s509 / 581
CG-AL-X052hard1100.0 / 1003/3OK11.5s358 / 331
CG-AL-X055hard1100.0 / 1005/5OK11.0s344 / 497
CG-AL-X056hard1100.0 / 1005/5OK10.5s280 / 605
CG-AL-X057hard1100.0 / 1005/5OK10.7s250 / 258
CG-AL-X058hard1100.0 / 1005/5OK11.1s314 / 1.1k
CG-AL-X059hard1100.0 / 1003/3OK10.8s327 / 195
CG-AL-X060hard1100.0 / 1003/3OK11.7s302 / 364
CG-AL-X061hard1100.0 / 1004/4OK11.1s364 / 92
CG-AL-X062hard1100.0 / 1004/4OK11.1s358 / 513
CG-AL-X063hard1100.0 / 1003/3OK11.3s360 / 659
CG-AL-X064hard1100.0 / 1007/7OK11.1s277 / 586
CG-AL-X065hard1100.0 / 1006/6OK10.9s709 / 603
CG-AL-X066hard1100.0 / 10014/14OK10.9s1.2k / 1.1k
CG-AL-X067hard1100.0 / 1007/7OK10.6s611 / 653
CG-AL-X068hard1100.0 / 10012/12OK10.9s1.2k / 1.2k
CG-AL-X069hard1100.0 / 1008/8OK11.4s1.1k / 4.0k
CG-AL-X070hard1100.0 / 10012/12OK10.7s1.2k / 897
CG-AL-X071hard1100.0 / 1008/8OK10.7s1.4k / 1.1k
CG-AL-X072hard1100.0 / 1007/7OK11.0s1.1k / 819
CG-AL-X073hard1100.0 / 1008/8OK10.8s1.4k / 1.3k
CG-AL-X074hard2100.0 / 1007/7OK11.0s3.4k / 5.2k
CG-AL-X075hard1100.0 / 1007/7OK10.6s810 / 3.6k
CG-AL-X076hard1100.0 / 10014/14OK10.7s954 / 1.6k
CG-AL-X077hard1100.0 / 10022/22OK11.1s1.5k / 1.3k
CG-AL-X078hard1100.0 / 10017/17OK11.1s1.2k / 903
CG-AL-X079hard1100.0 / 10011/11OK11.0s1.2k / 3.2k
CG-AL-X080hard2100.0 / 1007/7OK11.3s2.4k / 2.9k
CG-AL-X081hard1100.0 / 1008/8OK12.2s902 / 564
CG-AL-X082hard1100.0 / 10015/15OK12.7s1.2k / 920
CG-AL-X083hard1100.0 / 1009/9OK11.8s1.5k / 1.2k
CG-AL-X084hard1100.0 / 10010/10OK12.1s1.4k / 3.2k
CG-AL-X085hard1100.0 / 1007/7OK10.9s980 / 600
CG-AL-X086hard1100.0 / 1006/6OK12.2s1.4k / 1.3k
CG-AL-X087hard1100.0 / 1003/3OK11.4s1.0k / 962
CG-AL-X088hard1100.0 / 1006/6OK11.1s974 / 1.0k
CG-AL-X089hard1100.0 / 10011/11OK11.4s1.1k / 3.5k
CG-AL-X090hard1100.0 / 10010/10OK11.0s889 / 1.7k
CG-AL-X091hard1100.0 / 1006/6OK10.7s569 / 317
CG-AL-X092hard1100.0 / 10015/15OK10.6s444 / 274
CG-AL-X093hard1100.0 / 10010/10OK11.0s989 / 929
CG-AL-X094hard1100.0 / 1007/7OK10.9s754 / 574
CG-AL-X095hard262.5 / 1002/5OK11.0s2.8k / 3.2k
CG-AL-X096hard1100.0 / 10049/49OK11.2s3.3k / 3.0k
CG-AL-X097hard1100.0 / 10046/46OK11.2s3.4k / 3.1k
CG-AL-X098hard1100.0 / 10029/29OK10.9s2.6k / 2.2k
CG-AL-X099hard1100.0 / 10039/39OK12.8s3.6k / 4.4k
CG-AL-X100hard1100.0 / 10035/35OK12.0s3.5k / 3.7k
CG-AL-X101hard1100.0 / 10010/10OK10.7s1.1k / 1.0k
CG-AL-X102hard1100.0 / 1008/8OK11.0s531 / 1.3k
CG-AL-X103hard1100.0 / 1007/7OK11.2s725 / 458
CG-AL-X104hard1100.0 / 1006/6OK11.2s1.1k / 923
CG-AL-X105hard1100.0 / 1006/6OK11.0s777 / 443
CG-AL-X106hard1100.0 / 1005/5OK11.9s878 / 1.1k
CG-AL-X107hard1100.0 / 1004/4OK11.3s805 / 716
CG-AL-X108hard1100.0 / 1006/6OK12.5s729 / 427
CG-AL-X109hard1100.0 / 1005/5OK11.9s548 / 369
CG-AL-X110hard1100.0 / 10017/17OK12.3s1.2k / 1.0k
CG-AL-X111hard1100.0 / 1008/8OK13.8s1.2k / 2.5k
CG-AL-X112hard1100.0 / 10012/12OK12.6s906 / 2.6k
CG-AL-X113hard1100.0 / 10013/13OK13.6s705 / 1.2k
CG-AL-X114hard1100.0 / 1007/7OK11.5s718 / 479
CG-AL-X115hard1100.0 / 10013/13OK11.1s478 / 616
CG-AL-X116hard1100.0 / 10017/17OK12.3s926 / 2.4k
CG-AL-X117hard1100.0 / 1008/8OK11.2s1.0k / 876
CG-AL-X118hard1100.0 / 10017/17OK11.7s1.4k / 1.1k
CG-AL-X119hard1100.0 / 10015/15OK11.8s1.7k / 1.7k
CG-AL-X120hard1100.0 / 10012/12OK11.2s1.2k / 1.1k
CG-AL-X121hard1100.0 / 1006/6OK11.4s1.0k / 842
CG-AL-X122hard1100.0 / 10010/10OK11.7s1.5k / 1.5k
CG-AL-X123hard1100.0 / 1005/5OK11.4s603 / 371
CG-AL-X124hard1100.0 / 10010/10OK12.0s994 / 766
CG-AL-X125hard1100.0 / 1008/8OK11.0s1.4k / 2.2k
CG-AL-X126hard1100.0 / 10014/14OK10.8s711 / 399
CG-AL-X127hard1100.0 / 1005/5OK12.0s666 / 782
CG-AL-X128hard1100.0 / 1008/8OK11.2s1.1k / 811
CG-AL-X129hard1100.0 / 10014/14OK12.3s1.2k / 1.1k
CG-AL-X130hard2100.0 / 1005/5OK11.1s1.1k / 1.1k
CG-AL-X131hard1100.0 / 10013/13OK11.6s941 / 685
CG-AL-X132hard1100.0 / 10010/10OK11.8s709 / 410
CG-AL-X133hard262.5 / 1007/8OK11.3s3.4k / 5.7k
CG-AL-X134hard1100.0 / 1006/6OK11.9s1.2k / 2.0k
CG-AL-X135hard1100.0 / 1004/4OK12.1s866 / 554
CG-AL-X136hard1100.0 / 1007/7OK11.5s754 / 426
CG-AL-X137hard1100.0 / 1004/4OK11.4s915 / 1.4k
CG-AL-X138hard1100.0 / 1009/9OK11.7s1.4k / 1.8k
CG-AL-X139hard1100.0 / 10011/11OK12.6s1.6k / 1.5k
CG-AL-X140hard2100.0 / 1007/7OK11.4s4.2k / 7.2k
CG-AL-X141hard1100.0 / 10039/39OK12.6s3.5k / 3.9k
CG-AL-X142hard2100.0 / 10048/48OK12.2s9.0k / 11k
CG-AL-X143hard1100.0 / 10035/35OK19.8s4.0k / 3.8k
CG-AL-X144hard1100.0 / 10043/43OK13.3s3.6k / 3.2k
CG-AL-X145hard1100.0 / 10032/32OK13.3s4.2k / 4.0k
CG-AL-X146hard1100.0 / 1009/9OK12.2s1.7k / 4.7k
CG-AL-X147hard1100.0 / 1008/8OK12.2s1.3k / 1.0k
CG-AL-X148hard1100.0 / 1006/6OK12.3s1.1k / 788
CG-AL-X149hard1100.0 / 1007/7OK12.2s1.1k / 940
CG-AL-X150hard1100.0 / 1009/9OK13.0s1.9k / 4.4k
CG-AL-X151hard1100.0 / 1006/6OK12.8s818 / 511
CG-AL-X152hard1100.0 / 1008/8OK12.7s1.1k / 797
CG-AL-X153hard20.0 / 1000/0FAIL4.0s1.9k / 3.1k
CG-AL-X154hard1100.0 / 1009/9OK12.4s1.2k / 1.2k
CG-AL-X155hard1100.0 / 10011/11OK12.0s923 / 818
CG-AL-X156hard1100.0 / 1007/7OK12.3s884 / 541
CG-AL-X157hard1100.0 / 10010/10OK12.8s1.3k / 971
CG-AL-X158hard1100.0 / 1007/7OK11.3s801 / 415
CG-AL-X159hard1100.0 / 1007/7OK11.6s849 / 593
CG-AL-X160hard1100.0 / 10013/13OK11.2s1.2k / 1.4k
CG-AL-X161hard1100.0 / 10010/10OK11.5s1.4k / 1.3k
CG-AL-X162hard1100.0 / 1007/7OK11.6s956 / 728
CG-AL-X163hard1100.0 / 1007/7OK12.3s1.0k / 781
CG-AL-X164hard1100.0 / 1007/7OK12.3s945 / 791
CG-AL-X165hard1100.0 / 10013/13OK15.4s2.6k / 4.1k
CG-AL-X166hard1100.0 / 10014/14OK13.4s1.6k / 1.1k
CG-AL-X167hard20.0 / 1000/0FAIL4.1s3.6k / 6.1k
CG-AL-X168hard1100.0 / 1009/9OK11.6s1.3k / 2.6k
CG-AL-X169hard1100.0 / 10011/11OK12.2s1.6k / 3.2k
CG-AL-X170hard1100.0 / 10011/11OK12.2s3.1k / 5.3k
CG-AL-X171hard1100.0 / 1009/9OK11.3s1.4k / 4.6k
CG-AL-X172hard1100.0 / 10011/11OK12.2s2.2k / 4.3k
CG-AL-X173hard1100.0 / 10019/19OK13.0s3.1k / 4.9k
CG-AL-X174hard1100.0 / 10016/16OK12.3s3.9k / 4.9k
CG-AL-X185hard262.5 / 10041/43OK11.8s5.3k / 2.7k
CG-AL-X187hard262.5 / 10030/33OK12.8s7.5k / 4.4k
CG-AL-X194hard2100.0 / 10050/50OK12.3s10k / 7.5k
CG-AL-X211hard2100.0 / 10043/43OK13.0s8.2k / 6.8k
CG-AL-X214hard2100.0 / 10034/34OK12.9s8.0k / 4.9k
CG-AL-X218hard2100.0 / 10027/27OK12.8s7.8k / 4.8k
CG-AL-X234hard2100.0 / 10035/35OK12.3s9.1k / 4.3k
CG-AL-X239hard2100.0 / 10037/37OK12.4s11k / 6.5k
CG-AL-X244hard2100.0 / 10038/38OK12.3s11k / 7.9k
CG-AL-X245hard2100.0 / 10063/63OK13.1s9.9k / 3.7k
CG-AL-X248hard2100.0 / 10066/66OK12.4s9.8k / 4.7k
CG-AL-X249hard2100.0 / 10037/37OK12.3s9.6k / 5.9k
CG-AL-X254hard262.5 / 10064/70OK12.6s15k / 8.0k
CG-AL-X257hard2100.0 / 10053/53OK12.6s9.8k / 7.2k
CG-AL-X263hard2100.0 / 10061/61OK13.0s11k / 7.3k
CG-AL-X264hard2100.0 / 10065/65OK12.3s12k / 6.8k
CG-AL-X270hard2100.0 / 10063/63OK12.9s17k / 9.8k
CG-AL-X271hard2100.0 / 10070/70OK13.6s17k / 10k
CG-AL-X272hard2100.0 / 10079/79OK13.1s14k / 6.3k
CG-AL-X274hard2100.0 / 10064/64OK13.8s13k / 5.8k
CG-AL-X276hard2100.0 / 10078/78OK14.7s15k / 5.8k
CG-AL-X278hard2100.0 / 10071/71OK13.4s15k / 8.6k
CG-AL-X283hard2100.0 / 10076/76OK13.0s15k / 7.1k
CG-AL-X289hard2100.0 / 10057/57OK13.9s12k / 9.1k
CG-AL-X290hard262.5 / 10037/47OK13.5s11k / 6.0k
CG-AL-X292hard2100.0 / 10057/57OK13.0s11k / 4.9k
CG-AL-X293hard2100.0 / 10049/49OK12.8s10k / 6.0k
CG-AL-X296hard2100.0 / 10047/47OK13.3s20k / 12k
CG-AL-X298hard1100.0 / 10055/55OK11.8s4.4k / 3.8k