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.

88.4% 205/232 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.

79.8 / 100
Cost $5.54
Tokens 560k / 441k input / output, all attempts
Duration 55m 22s
Filter:
Per-task results for run c64bba36-7919-4365-9a90-f9628238be11
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK14.5s258 / 311
CG-AL-E006easy1100.0 / 1007/7OK29.6s305 / 535
CG-AL-E010easy2100.0 / 1005/5OK16.8s694 / 388
CG-AL-E050easy20.0 / 1000/0FAIL9.3s1.8k / 1.5k
CG-AL-E052easy1100.0 / 10016/16OK9.9s352 / 368
CG-AL-E054easy20.0 / 1000/0FAIL9.5s1.0k / 1.3k
CG-AL-E056easy2100.0 / 10015/15OK11.1s1.7k / 760
CG-AL-H007hard1100.0 / 10011/11OK9.9s545 / 1.2k
CG-AL-H011hard20.0 / 1000/0FAIL3.9s942 / 1.4k
CG-AL-H014hard20.0 / 1000/0FAIL4.3s1.5k / 1.2k
CG-AL-H017hard2100.0 / 1005/5OK11.2s976 / 1.0k
CG-AL-H020hard2100.0 / 10010/10OK17.0s1.7k / 2.2k
CG-AL-H021hard262.5 / 1006/20OK10.9s1.8k / 1.6k
CG-AL-H023hard2100.0 / 10025/25OK13.2s5.8k / 9.4k
CG-AL-H027hard1100.0 / 1004/4OK10.6s738 / 667
CG-AL-H029hard20.0 / 1000/0FAIL4.3s2.8k / 3.0k
CG-AL-H030hard20.0 / 1000/0FAIL4.3s2.5k / 5.3k
CG-AL-H031hard1100.0 / 10022/22OK10.5s939 / 1.9k
CG-AL-H034hard1100.0 / 1003/3OK9.9s431 / 969
CG-AL-H036hard20.0 / 1000/0FAIL4.1s943 / 1.6k
CG-AL-H037hard2100.0 / 1003/3OK10.5s1.2k / 1.1k
CG-AL-H041hard1100.0 / 1003/3OK9.9s565 / 847
CG-AL-H050hard1100.0 / 1003/3OK10.1s501 / 791
CG-AL-H054hard20.0 / 1000/0FAIL4.0s1.8k / 954
CG-AL-H056hard20.0 / 1000/0FAIL5.0s1.4k / 1.2k
CG-AL-M001medium20.0 / 1000/0FAIL4.1s1.3k / 1.5k
CG-AL-M003medium2100.0 / 1009/9OK16.2s1.5k / 2.3k
CG-AL-M004medium1100.0 / 10012/12OK25.9s449 / 1.8k
CG-AL-M006medium262.5 / 10017/18OK12.0s3.0k / 4.6k
CG-AL-M007medium20.0 / 1000/0FAIL5.3s4.3k / 9.4k
CG-AL-M008medium262.5 / 1001/12OK12.7s4.3k / 8.9k
CG-AL-M009medium2100.0 / 10011/11OK10.8s3.7k / 7.7k
CG-AL-M010medium1100.0 / 10021/21OK27.0s596 / 3.3k
CG-AL-M020medium2100.0 / 10017/17OK10.6s2.0k / 2.2k
CG-AL-M023medium1100.0 / 10011/11OK10.8s482 / 692
CG-AL-M025medium1100.0 / 1008/8OK10.9s400 / 1.1k
CG-AL-M026medium1100.0 / 1008/8OK10.3s370 / 691
CG-AL-M027medium2100.0 / 10018/18OK10.4s3.4k / 2.9k
CG-AL-M028medium2100.0 / 1003/3OK22.7s1.0k / 746
CG-AL-M031medium2100.0 / 1002/2OK10.4s2.0k / 1.4k
CG-AL-M034medium1100.0 / 1002/2OK11.6s415 / 703
CG-AL-M036medium211.1 / 1000/0FAIL4.1s1.5k / 1.1k
CG-AL-M040medium1100.0 / 1002/2OK9.7s311 / 634
CG-AL-M042medium1100.0 / 1008/8OK9.8s498 / 386
CG-AL-X001hard1100.0 / 1002/2OK10.0s308 / 218
CG-AL-X002hard1100.0 / 1004/4OK10.1s488 / 778
CG-AL-X003hard2100.0 / 1003/3OK10.7s957 / 1.3k
CG-AL-X004medium1100.0 / 1003/3OK9.9s358 / 760
CG-AL-X005hard1100.0 / 1002/2OK10.4s327 / 395
CG-AL-X006hard1100.0 / 1003/3OK10.1s383 / 703
CG-AL-X007hard1100.0 / 1002/2OK1m 19s372 / 602
CG-AL-X008hard2100.0 / 1001/1OK10.5s1.2k / 1.4k
CG-AL-X009medium1100.0 / 1002/2OK10.6s313 / 273
CG-AL-X010medium1100.0 / 1003/3OK10.8s284 / 257
CG-AL-X011medium1100.0 / 1002/2OK10.6s360 / 290
CG-AL-X012hard1100.0 / 1001/1OK10.7s380 / 617
CG-AL-X013hard1100.0 / 1002/2OK11.4s263 / 228
CG-AL-X014medium1100.0 / 1004/4OK10.7s291 / 268
CG-AL-X017medium2100.0 / 1003/3OK10.0s1.4k / 303
CG-AL-X018medium1100.0 / 1003/3OK10.9s384 / 372
CG-AL-X019medium2100.0 / 1003/3OK10.6s1.7k / 729
CG-AL-X022medium2100.0 / 1003/3OK10.4s1.2k / 632
CG-AL-X024medium1100.0 / 1003/3OK10.7s333 / 681
CG-AL-X025medium1100.0 / 1001/1OK10.6s371 / 441
CG-AL-X026medium1100.0 / 1003/3OK11.5s327 / 206
CG-AL-X027medium1100.0 / 1004/4OK10.8s258 / 397
CG-AL-X029medium1100.0 / 1002/2OK11.2s276 / 1.3k
CG-AL-X030medium1100.0 / 1002/2OK10.8s239 / 164
CG-AL-X031medium1100.0 / 1003/3OK11.8s297 / 232
CG-AL-X033hard1100.0 / 1002/2OK12.3s348 / 210
CG-AL-X034hard1100.0 / 1003/3OK11.1s304 / 376
CG-AL-X035hard1100.0 / 1003/3OK9.5s331 / 528
CG-AL-X037hard1100.0 / 1004/4OK10.9s408 / 1.2k
CG-AL-X040hard1100.0 / 1004/4OK11.0s550 / 1.2k
CG-AL-X041hard1100.0 / 1005/5OK10.9s446 / 626
CG-AL-X043hard2100.0 / 1001/1OK11.1s1.6k / 4.2k
CG-AL-X044hard262.5 / 1001/3OK10.4s1.3k / 4.0k
CG-AL-X045hard1100.0 / 1003/3OK10.7s371 / 213
CG-AL-X046hard1100.0 / 1002/2OK10.6s369 / 364
CG-AL-X047hard1100.0 / 1002/2OK11.0s390 / 1.3k
CG-AL-X050hard1100.0 / 1002/2OK10.7s405 / 611
CG-AL-X051hard1100.0 / 1002/2OK10.7s509 / 416
CG-AL-X052hard1100.0 / 1003/3OK10.6s358 / 553
CG-AL-X055hard1100.0 / 1005/5OK10.5s344 / 450
CG-AL-X056hard1100.0 / 1005/5OK11.1s280 / 379
CG-AL-X057hard1100.0 / 1005/5OK10.4s250 / 243
CG-AL-X058hard1100.0 / 1005/5OK10.7s314 / 685
CG-AL-X059hard1100.0 / 1003/3OK11.0s327 / 145
CG-AL-X060hard1100.0 / 1003/3OK10.7s302 / 283
CG-AL-X061hard1100.0 / 1004/4OK10.7s364 / 92
CG-AL-X062hard1100.0 / 1004/4OK10.9s358 / 443
CG-AL-X063hard1100.0 / 1003/3OK11.0s360 / 428
CG-AL-X064hard1100.0 / 1007/7OK10.8s277 / 526
CG-AL-X065hard1100.0 / 1006/6OK10.6s709 / 785
CG-AL-X066hard1100.0 / 10014/14OK10.7s1.2k / 1.0k
CG-AL-X067hard2100.0 / 1007/7OK10.6s1.6k / 1.4k
CG-AL-X068hard1100.0 / 10012/12OK10.6s1.2k / 991
CG-AL-X069hard1100.0 / 1008/8OK10.7s1.1k / 3.4k
CG-AL-X070hard1100.0 / 10012/12OK10.8s1.2k / 808
CG-AL-X071hard1100.0 / 1008/8OK10.6s1.4k / 1.1k
CG-AL-X072hard1100.0 / 1007/7OK10.7s1.1k / 813
CG-AL-X073hard1100.0 / 1008/8OK10.9s1.4k / 1.3k
CG-AL-X074hard2100.0 / 1007/7OK10.4s3.4k / 3.2k
CG-AL-X075hard1100.0 / 1007/7OK10.8s810 / 987
CG-AL-X076hard1100.0 / 10014/14OK10.8s954 / 1.1k
CG-AL-X077hard1100.0 / 10022/22OK10.6s1.5k / 1.2k
CG-AL-X078hard1100.0 / 10017/17OK10.8s1.2k / 936
CG-AL-X079hard1100.0 / 10011/11OK17.4s1.2k / 1.4k
CG-AL-X080hard20.0 / 1000/0FAIL4.1s2.4k / 2.4k
CG-AL-X081hard1100.0 / 1008/8OK11.2s902 / 607
CG-AL-X082hard1100.0 / 10015/15OK10.8s1.2k / 944
CG-AL-X083hard1100.0 / 1009/9OK10.5s1.5k / 1.2k
CG-AL-X084hard1100.0 / 10010/10OK11.2s1.4k / 1.8k
CG-AL-X085hard1100.0 / 1007/7OK10.5s980 / 670
CG-AL-X086hard1100.0 / 1006/6OK11.1s1.4k / 1.1k
CG-AL-X087hard1100.0 / 1003/3OK10.3s1.0k / 1.0k
CG-AL-X088hard1100.0 / 1006/6OK10.6s974 / 906
CG-AL-X089hard1100.0 / 10011/11OK10.9s1.1k / 2.4k
CG-AL-X090hard1100.0 / 10010/10OK11.0s889 / 1.1k
CG-AL-X091hard1100.0 / 1006/6OK10.9s569 / 328
CG-AL-X092hard1100.0 / 10015/15OK10.6s444 / 242
CG-AL-X093hard1100.0 / 10010/10OK10.6s989 / 779
CG-AL-X094hard1100.0 / 1007/7OK10.3s754 / 543
CG-AL-X095hard262.5 / 1003/5OK10.0s2.4k / 2.1k
CG-AL-X096hard1100.0 / 10049/49OK10.9s3.3k / 2.9k
CG-AL-X097hard1100.0 / 10046/46OK11.2s3.4k / 3.1k
CG-AL-X098hard1100.0 / 10029/29OK10.8s2.6k / 2.1k
CG-AL-X099hard1100.0 / 10039/39OK13.0s3.6k / 3.8k
CG-AL-X100hard1100.0 / 10035/35OK10.2s3.5k / 3.4k
CG-AL-X101hard1100.0 / 10010/10OK9.9s1.1k / 856
CG-AL-X102hard1100.0 / 1008/8OK9.8s531 / 827
CG-AL-X103hard1100.0 / 1007/7OK9.9s725 / 483
CG-AL-X104hard1100.0 / 1006/6OK9.9s1.1k / 874
CG-AL-X105hard1100.0 / 1006/6OK9.8s777 / 475
CG-AL-X106hard1100.0 / 1005/5OK10.0s878 / 1.0k
CG-AL-X107hard1100.0 / 1004/4OK9.9s805 / 741
CG-AL-X108hard1100.0 / 1006/6OK10.4s729 / 377
CG-AL-X109hard1100.0 / 1005/5OK10.5s548 / 368
CG-AL-X110hard1100.0 / 10017/17OK10.3s1.2k / 979
CG-AL-X111hard1100.0 / 1008/8OK10.7s1.2k / 1.4k
CG-AL-X112hard1100.0 / 10012/12OK11.5s906 / 1.4k
CG-AL-X113hard1100.0 / 10013/13OK11.0s705 / 2.0k
CG-AL-X114hard1100.0 / 1007/7OK10.4s718 / 439
CG-AL-X115hard1100.0 / 10013/13OK10.5s478 / 472
CG-AL-X116hard1100.0 / 10017/17OK10.9s926 / 1.5k
CG-AL-X117hard1100.0 / 1008/8OK10.8s1.0k / 903
CG-AL-X118hard1100.0 / 10017/17OK11.2s1.4k / 1.2k
CG-AL-X119hard1100.0 / 10015/15OK11.7s1.7k / 1.6k
CG-AL-X120hard1100.0 / 10012/12OK11.3s1.2k / 1.1k
CG-AL-X121hard1100.0 / 1006/6OK11.6s1.0k / 812
CG-AL-X122hard1100.0 / 10010/10OK13.0s1.5k / 1.5k
CG-AL-X123hard1100.0 / 1005/5OK12.8s603 / 316
CG-AL-X124hard1100.0 / 10010/10OK12.5s994 / 702
CG-AL-X125hard1100.0 / 1008/8OK12.6s1.4k / 1.4k
CG-AL-X126hard1100.0 / 10014/14OK12.3s711 / 398
CG-AL-X127hard1100.0 / 1005/5OK10.5s666 / 612
CG-AL-X128hard1100.0 / 1008/8OK10.7s1.1k / 832
CG-AL-X129hard1100.0 / 10014/14OK10.6s1.2k / 1.1k
CG-AL-X130hard2100.0 / 1005/5OK9.8s1.1k / 793
CG-AL-X131hard1100.0 / 10013/13OK10.7s941 / 839
CG-AL-X132hard1100.0 / 10010/10OK10.4s709 / 427
CG-AL-X133hard2100.0 / 1008/8OK10.5s3.4k / 3.7k
CG-AL-X134hard1100.0 / 1006/6OK11.1s1.2k / 1.3k
CG-AL-X135hard1100.0 / 1004/4OK10.7s866 / 572
CG-AL-X136hard1100.0 / 1007/7OK11.3s754 / 398
CG-AL-X137hard1100.0 / 1004/4OK12.1s915 / 665
CG-AL-X138hard1100.0 / 1009/9OK11.0s1.4k / 1.4k
CG-AL-X139hard1100.0 / 10011/11OK11.2s1.6k / 1.5k
CG-AL-X140hard1100.0 / 1007/7OK11.2s1.5k / 3.3k
CG-AL-X141hard1100.0 / 10039/39OK11.9s3.5k / 3.1k
CG-AL-X142hard262.5 / 10045/48OK11.2s9.0k / 9.1k
CG-AL-X143hard1100.0 / 10035/35OK17.9s4.0k / 3.7k
CG-AL-X144hard2100.0 / 10043/43OK11.0s7.9k / 6.6k
CG-AL-X145hard1100.0 / 10032/32OK11.6s4.2k / 3.9k
CG-AL-X146hard1100.0 / 1009/9OK10.8s1.7k / 2.7k
CG-AL-X147hard1100.0 / 1008/8OK10.6s1.3k / 1.0k
CG-AL-X148hard1100.0 / 1006/6OK10.5s1.1k / 817
CG-AL-X149hard1100.0 / 1007/7OK11.0s1.1k / 918
CG-AL-X150hard1100.0 / 1009/9OK11.0s1.9k / 4.1k
CG-AL-X151hard1100.0 / 1006/6OK10.8s818 / 532
CG-AL-X152hard1100.0 / 1008/8OK12.0s1.1k / 856
CG-AL-X153hard1100.0 / 1009/9OK15.5s888 / 1.4k
CG-AL-X154hard1100.0 / 1009/9OK12.5s1.2k / 1.1k
CG-AL-X155hard1100.0 / 10011/11OK11.7s923 / 793
CG-AL-X156hard1100.0 / 1007/7OK10.5s884 / 541
CG-AL-X157hard1100.0 / 10010/10OK10.7s1.3k / 964
CG-AL-X158hard1100.0 / 1007/7OK10.5s801 / 463
CG-AL-X159hard1100.0 / 1007/7OK11.2s849 / 573
CG-AL-X160hard1100.0 / 10013/13OK12.8s1.2k / 1.2k
CG-AL-X161hard1100.0 / 10010/10OK12.1s1.4k / 1.3k
CG-AL-X162hard1100.0 / 1007/7OK12.3s956 / 777
CG-AL-X163hard1100.0 / 1007/7OK10.6s1.0k / 747
CG-AL-X164hard1100.0 / 1007/7OK12.2s945 / 876
CG-AL-X165hard262.5 / 10012/13OK13.1s6.1k / 6.1k
CG-AL-X166hard1100.0 / 10014/14OK14.1s1.6k / 1.3k
CG-AL-X167hard2100.0 / 10013/13OK10.8s3.7k / 3.3k
CG-AL-X168hard2100.0 / 1009/9OK10.4s3.8k / 4.6k
CG-AL-X169hard1100.0 / 10011/11OK11.6s1.6k / 2.7k
CG-AL-X170hard1100.0 / 10011/11OK11.6s3.1k / 3.3k
CG-AL-X171hard1100.0 / 1009/9OK11.0s1.4k / 2.5k
CG-AL-X172hard1100.0 / 10011/11OK12.6s2.2k / 3.1k
CG-AL-X173hard2100.0 / 10019/19OK11.6s7.1k / 8.0k
CG-AL-X174hard1100.0 / 10016/16OK12.6s3.9k / 3.8k
CG-AL-X185hard262.5 / 10041/43OK10.9s5.3k / 2.0k
CG-AL-X187hard262.5 / 10030/33OK11.2s7.4k / 3.2k
CG-AL-X194hard2100.0 / 10050/50OK11.0s9.9k / 3.6k
CG-AL-X211hard1100.0 / 10043/43OK13.9s3.5k / 3.6k
CG-AL-X214hard2100.0 / 10034/34OK11.3s8.0k / 4.3k
CG-AL-X218hard2100.0 / 10027/27OK11.4s7.8k / 3.3k
CG-AL-X234hard1100.0 / 10035/35OK12.8s3.7k / 3.0k
CG-AL-X239hard262.5 / 10034/37OK11.4s11k / 3.7k
CG-AL-X244hard262.5 / 10035/38OK11.4s11k / 7.2k
CG-AL-X245hard2100.0 / 10063/63OK11.5s9.8k / 3.0k
CG-AL-X248hard1100.0 / 10066/66OK13.7s4.3k / 2.9k
CG-AL-X249hard2100.0 / 10037/37OK11.0s9.7k / 4.9k
CG-AL-X254hard262.5 / 10064/70OK11.7s13k / 5.5k
CG-AL-X257hard2100.0 / 10053/53OK11.3s8.8k / 4.7k
CG-AL-X263hard2100.0 / 10061/61OK11.7s11k / 5.0k
CG-AL-X264hard2100.0 / 10065/65OK11.5s9.9k / 3.9k
CG-AL-X270hard2100.0 / 10063/63OK11.6s16k / 6.1k
CG-AL-X271hard2100.0 / 10070/70OK11.9s16k / 7.4k
CG-AL-X272hard1100.0 / 10079/79OK12.0s6.0k / 4.2k
CG-AL-X274hard2100.0 / 10064/64OK11.8s12k / 5.8k
CG-AL-X276hard2100.0 / 10078/78OK12.2s15k / 4.8k
CG-AL-X278hard2100.0 / 10071/71OK12.1s14k / 5.7k
CG-AL-X283hard2100.0 / 10076/76OK12.7s15k / 5.2k
CG-AL-X289hard262.5 / 10052/57OK11.7s10k / 6.4k
CG-AL-X290hard262.5 / 10041/47OK12.5s14k / 7.5k
CG-AL-X292hard2100.0 / 10057/57OK11.7s10k / 2.5k
CG-AL-X293hard2100.0 / 10049/49OK11.3s10k / 3.6k
CG-AL-X296hard2100.0 / 10047/47OK11.4s14k / 6.0k
CG-AL-X298hard1100.0 / 10055/55OK13.3s4.4k / 3.7k