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.

87.5% 203/232 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.

78.0 / 100
Cost $5.58
Tokens 563k / 440k input / output, all attempts
Duration 53m 26s
Filter:
Per-task results for run 86df02dd-0a62-4f13-b8ac-627eb2dd10fb
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK24.9s258 / 418
CG-AL-E006easy262.5 / 1000/1OK28.0s953 / 1.1k
CG-AL-E010easy1100.0 / 1005/5OK25.3s280 / 225
CG-AL-E050easy2100.0 / 10013/13OK17.5s1.8k / 862
CG-AL-E052easy1100.0 / 10016/16OK10.6s352 / 367
CG-AL-E054easy20.0 / 1000/0FAIL9.5s971 / 1.5k
CG-AL-E056easy2100.0 / 10015/15OK11.8s1.7k / 881
CG-AL-H007hard1100.0 / 10011/11OK14.1s545 / 1.0k
CG-AL-H011hard20.0 / 1000/0FAIL3.6s944 / 1.4k
CG-AL-H014hard20.0 / 1000/0FAIL4.1s1.5k / 1.4k
CG-AL-H017hard2100.0 / 1005/5OK12.6s984 / 1.3k
CG-AL-H020hard2100.0 / 10010/10OK11.0s1.7k / 1.7k
CG-AL-H021hard262.5 / 1006/20OK10.9s1.8k / 1.6k
CG-AL-H023hard20.0 / 1000/0FAIL4.2s6.3k / 11k
CG-AL-H027hard1100.0 / 1004/4OK11.4s738 / 667
CG-AL-H029hard20.0 / 1000/0FAIL4.1s2.7k / 2.8k
CG-AL-H030hard2100.0 / 10010/10OK10.4s2.5k / 4.0k
CG-AL-H031hard2100.0 / 10022/22OK10.3s2.8k / 2.3k
CG-AL-H034hard2100.0 / 1003/3OK10.6s1.6k / 837
CG-AL-H036hard20.0 / 1000/0FAIL4.1s930 / 1.8k
CG-AL-H037hard2100.0 / 1003/3OK10.1s1.1k / 771
CG-AL-H041hard1100.0 / 1003/3OK9.7s565 / 707
CG-AL-H050hard2100.0 / 1003/3OK10.0s1.4k / 2.1k
CG-AL-H054hard20.0 / 1000/0FAIL3.8s1.8k / 1.1k
CG-AL-H056hard20.0 / 1000/0FAIL3.9s1.4k / 1.2k
CG-AL-M001medium20.0 / 1000/0FAIL3.9s1.4k / 1.4k
CG-AL-M003medium2100.0 / 1009/9OK15.7s1.5k / 2.3k
CG-AL-M004medium1100.0 / 10012/12OK53.9s449 / 1.9k
CG-AL-M006medium2100.0 / 10018/18OK11.4s2.4k / 5.3k
CG-AL-M007medium20.0 / 1000/0FAIL4.1s3.2k / 8.0k
CG-AL-M008medium262.5 / 1001/12OK11.4s4.4k / 9.6k
CG-AL-M009medium1100.0 / 10011/11OK9.8s429 / 5.8k
CG-AL-M010medium1100.0 / 10021/21OK23.3s596 / 4.1k
CG-AL-M020medium2100.0 / 10017/17OK9.9s2.2k / 2.7k
CG-AL-M023medium2100.0 / 10011/11OK11.0s1.5k / 1.3k
CG-AL-M025medium2100.0 / 1008/8OK10.3s2.8k / 1.4k
CG-AL-M026medium1100.0 / 1008/8OK10.1s370 / 958
CG-AL-M027medium2100.0 / 10018/18OK10.6s3.6k / 3.1k
CG-AL-M028medium2100.0 / 1003/3OK23.9s1.0k / 765
CG-AL-M031medium2100.0 / 1002/2OK10.2s2.0k / 1.3k
CG-AL-M034medium1100.0 / 1002/2OK10.5s415 / 602
CG-AL-M036medium1100.0 / 1002/2OK10.0s532 / 603
CG-AL-M040medium1100.0 / 1002/2OK10.1s311 / 587
CG-AL-M042medium1100.0 / 1008/8OK10.1s498 / 492
CG-AL-X001hard1100.0 / 1002/2OK10.1s308 / 255
CG-AL-X002hard1100.0 / 1004/4OK10.0s488 / 920
CG-AL-X003hard262.5 / 1002/3OK10.2s591 / 1.3k
CG-AL-X004medium1100.0 / 1003/3OK9.9s358 / 629
CG-AL-X005hard1100.0 / 1002/2OK10.5s327 / 414
CG-AL-X006hard1100.0 / 1003/3OK10.0s383 / 523
CG-AL-X007hard1100.0 / 1002/2OK1m 34s372 / 655
CG-AL-X008hard1100.0 / 1001/1OK10.6s417 / 1.0k
CG-AL-X009medium1100.0 / 1002/2OK10.7s313 / 345
CG-AL-X010medium1100.0 / 1003/3OK11.4s284 / 258
CG-AL-X011medium1100.0 / 1002/2OK10.6s360 / 265
CG-AL-X012hard1100.0 / 1001/1OK12.5s380 / 382
CG-AL-X013hard1100.0 / 1002/2OK9.9s263 / 176
CG-AL-X014medium1100.0 / 1004/4OK10.1s291 / 439
CG-AL-X017medium2100.0 / 1003/3OK10.1s1.4k / 397
CG-AL-X018medium1100.0 / 1003/3OK10.8s384 / 406
CG-AL-X019medium2100.0 / 1003/3OK12.2s1.7k / 756
CG-AL-X022medium2100.0 / 1003/3OK10.2s1.2k / 528
CG-AL-X024medium1100.0 / 1003/3OK9.9s333 / 641
CG-AL-X025medium1100.0 / 1001/1OK10.4s371 / 562
CG-AL-X026medium1100.0 / 1003/3OK9.8s327 / 174
CG-AL-X027medium1100.0 / 1004/4OK9.8s258 / 525
CG-AL-X029medium1100.0 / 1002/2OK9.8s276 / 961
CG-AL-X030medium1100.0 / 1002/2OK10.3s239 / 242
CG-AL-X031medium1100.0 / 1003/3OK10.2s297 / 241
CG-AL-X033hard1100.0 / 1002/2OK10.2s348 / 232
CG-AL-X034hard1100.0 / 1003/3OK10.1s304 / 366
CG-AL-X035hard262.5 / 1000/3OK10.4s1.5k / 1.1k
CG-AL-X037hard1100.0 / 1004/4OK9.9s408 / 792
CG-AL-X040hard1100.0 / 1004/4OK10.0s550 / 1.6k
CG-AL-X041hard1100.0 / 1005/5OK10.1s446 / 1.1k
CG-AL-X043hard2100.0 / 1001/1OK14.8s1.6k / 5.3k
CG-AL-X044hard20.0 / 1000/0FAIL4.2s1.6k / 2.6k
CG-AL-X045hard1100.0 / 1003/3OK10.2s371 / 291
CG-AL-X046hard1100.0 / 1002/2OK11.4s369 / 252
CG-AL-X047hard1100.0 / 1002/2OK12.0s390 / 932
CG-AL-X050hard1100.0 / 1002/2OK11.5s405 / 470
CG-AL-X051hard1100.0 / 1002/2OK10.3s509 / 490
CG-AL-X052hard1100.0 / 1003/3OK10.3s358 / 436
CG-AL-X055hard1100.0 / 1005/5OK10.1s344 / 434
CG-AL-X056hard1100.0 / 1005/5OK10.1s280 / 599
CG-AL-X057hard1100.0 / 1005/5OK9.9s250 / 197
CG-AL-X058hard1100.0 / 1005/5OK9.9s314 / 526
CG-AL-X059hard1100.0 / 1003/3OK10.3s327 / 177
CG-AL-X060hard1100.0 / 1003/3OK10.1s302 / 261
CG-AL-X061hard1100.0 / 1004/4OK10.4s364 / 92
CG-AL-X062hard1100.0 / 1004/4OK10.3s358 / 416
CG-AL-X063hard1100.0 / 1003/3OK10.2s360 / 540
CG-AL-X064hard1100.0 / 1007/7OK10.0s277 / 374
CG-AL-X065hard1100.0 / 1006/6OK10.1s709 / 583
CG-AL-X066hard1100.0 / 10014/14OK10.4s1.2k / 1.0k
CG-AL-X067hard2100.0 / 1007/7OK10.0s1.6k / 1.1k
CG-AL-X068hard1100.0 / 10012/12OK10.1s1.2k / 1.0k
CG-AL-X069hard1100.0 / 1008/8OK10.3s1.1k / 3.4k
CG-AL-X070hard1100.0 / 10012/12OK10.1s1.2k / 787
CG-AL-X071hard1100.0 / 1008/8OK9.9s1.4k / 1.1k
CG-AL-X072hard1100.0 / 1007/7OK9.7s1.1k / 793
CG-AL-X073hard1100.0 / 1008/8OK10.3s1.4k / 1.3k
CG-AL-X074hard2100.0 / 1007/7OK10.8s3.4k / 3.5k
CG-AL-X075hard1100.0 / 1007/7OK9.9s810 / 1.2k
CG-AL-X076hard1100.0 / 10014/14OK10.1s954 / 1.2k
CG-AL-X077hard1100.0 / 10022/22OK10.3s1.5k / 1.3k
CG-AL-X078hard1100.0 / 10017/17OK10.2s1.2k / 935
CG-AL-X079hard1100.0 / 10011/11OK10.4s1.2k / 1.3k
CG-AL-X080hard262.5 / 1006/7OK11.3s2.4k / 2.4k
CG-AL-X081hard1100.0 / 1008/8OK10.5s902 / 588
CG-AL-X082hard1100.0 / 10015/15OK10.4s1.2k / 944
CG-AL-X083hard1100.0 / 1009/9OK10.1s1.5k / 1.2k
CG-AL-X084hard1100.0 / 10010/10OK10.5s1.4k / 1.6k
CG-AL-X085hard1100.0 / 1007/7OK10.0s980 / 603
CG-AL-X086hard1100.0 / 1006/6OK9.8s1.4k / 1.1k
CG-AL-X087hard1100.0 / 1003/3OK9.6s1.0k / 1.2k
CG-AL-X088hard1100.0 / 1006/6OK10.6s974 / 856
CG-AL-X089hard1100.0 / 10011/11OK10.1s1.1k / 1.7k
CG-AL-X090hard1100.0 / 10010/10OK9.9s889 / 1.2k
CG-AL-X091hard1100.0 / 1006/6OK9.5s569 / 312
CG-AL-X092hard1100.0 / 10015/15OK9.6s444 / 234
CG-AL-X093hard1100.0 / 10010/10OK9.8s989 / 824
CG-AL-X094hard1100.0 / 1007/7OK9.4s754 / 524
CG-AL-X095hard262.5 / 1003/5OK10.8s2.4k / 2.1k
CG-AL-X096hard1100.0 / 10049/49OK10.6s3.3k / 3.0k
CG-AL-X097hard1100.0 / 10046/46OK10.2s3.4k / 3.1k
CG-AL-X098hard1100.0 / 10029/29OK10.6s2.6k / 2.1k
CG-AL-X099hard1100.0 / 10039/39OK11.7s3.6k / 3.7k
CG-AL-X100hard1100.0 / 10035/35OK10.4s3.5k / 3.5k
CG-AL-X101hard1100.0 / 10010/10OK9.5s1.1k / 915
CG-AL-X102hard1100.0 / 1008/8OK9.7s531 / 1.2k
CG-AL-X103hard1100.0 / 1007/7OK9.6s725 / 481
CG-AL-X104hard1100.0 / 1006/6OK10.2s1.1k / 874
CG-AL-X105hard1100.0 / 1006/6OK9.9s777 / 495
CG-AL-X106hard1100.0 / 1005/5OK10.0s878 / 997
CG-AL-X107hard1100.0 / 1004/4OK9.7s805 / 763
CG-AL-X108hard1100.0 / 1006/6OK10.3s729 / 382
CG-AL-X109hard1100.0 / 1005/5OK9.8s548 / 346
CG-AL-X110hard1100.0 / 10017/17OK9.9s1.2k / 986
CG-AL-X111hard1100.0 / 1008/8OK9.7s1.2k / 1.8k
CG-AL-X112hard1100.0 / 10012/12OK9.6s906 / 1.2k
CG-AL-X113hard1100.0 / 10013/13OK10.0s705 / 1.5k
CG-AL-X114hard1100.0 / 1007/7OK9.5s718 / 437
CG-AL-X115hard1100.0 / 10013/13OK9.9s478 / 482
CG-AL-X116hard1100.0 / 10017/17OK9.7s926 / 1.2k
CG-AL-X117hard1100.0 / 1008/8OK10.0s1.0k / 911
CG-AL-X118hard1100.0 / 10017/17OK9.9s1.4k / 1.3k
CG-AL-X119hard1100.0 / 10015/15OK9.8s1.7k / 1.6k
CG-AL-X120hard1100.0 / 10012/12OK10.6s1.2k / 1.0k
CG-AL-X121hard1100.0 / 1006/6OK10.3s1.0k / 813
CG-AL-X122hard1100.0 / 10010/10OK9.8s1.5k / 1.5k
CG-AL-X123hard1100.0 / 1005/5OK10.2s603 / 307
CG-AL-X124hard1100.0 / 10010/10OK9.7s994 / 730
CG-AL-X125hard1100.0 / 1008/8OK9.8s1.4k / 1.6k
CG-AL-X126hard1100.0 / 10014/14OK9.6s711 / 370
CG-AL-X127hard1100.0 / 1005/5OK9.7s666 / 559
CG-AL-X128hard1100.0 / 1008/8OK10.1s1.1k / 833
CG-AL-X129hard1100.0 / 10014/14OK9.8s1.2k / 1.1k
CG-AL-X130hard2100.0 / 1005/5OK10.5s1.1k / 685
CG-AL-X131hard1100.0 / 10013/13OK9.8s941 / 824
CG-AL-X132hard1100.0 / 10010/10OK9.6s709 / 431
CG-AL-X133hard1100.0 / 1008/8OK9.8s1.6k / 2.2k
CG-AL-X134hard1100.0 / 1006/6OK10.1s1.2k / 1.1k
CG-AL-X135hard2100.0 / 1004/4OK10.6s1.8k / 1.2k
CG-AL-X136hard1100.0 / 1007/7OK10.5s754 / 358
CG-AL-X137hard2100.0 / 1004/4OK10.7s1.9k / 2.0k
CG-AL-X138hard1100.0 / 1009/9OK9.8s1.4k / 1.3k
CG-AL-X139hard1100.0 / 10011/11OK9.9s1.6k / 1.5k
CG-AL-X140hard1100.0 / 1007/7OK10.0s1.5k / 3.3k
CG-AL-X141hard1100.0 / 10039/39OK10.7s3.5k / 4.0k
CG-AL-X142hard262.5 / 10045/48OK11.9s9.1k / 8.5k
CG-AL-X143hard1100.0 / 10035/35OK14.6s4.0k / 3.7k
CG-AL-X144hard1100.0 / 10043/43OK10.5s3.6k / 3.2k
CG-AL-X145hard1100.0 / 10032/32OK10.5s4.2k / 3.9k
CG-AL-X146hard1100.0 / 1009/9OK10.1s1.7k / 2.4k
CG-AL-X147hard1100.0 / 1008/8OK10.0s1.3k / 977
CG-AL-X148hard1100.0 / 1006/6OK9.7s1.1k / 808
CG-AL-X149hard1100.0 / 1007/7OK9.7s1.1k / 932
CG-AL-X150hard1100.0 / 1009/9OK10.2s1.9k / 2.8k
CG-AL-X151hard1100.0 / 1006/6OK10.1s818 / 535
CG-AL-X152hard1100.0 / 1008/8OK9.6s1.1k / 816
CG-AL-X153hard1100.0 / 1009/9OK13.3s888 / 878
CG-AL-X154hard2100.0 / 1009/9OK11.4s2.5k / 2.4k
CG-AL-X155hard1100.0 / 10011/11OK9.5s923 / 794
CG-AL-X156hard1100.0 / 1007/7OK9.9s884 / 561
CG-AL-X157hard1100.0 / 10010/10OK9.8s1.3k / 951
CG-AL-X158hard1100.0 / 1007/7OK9.7s801 / 470
CG-AL-X159hard1100.0 / 1007/7OK11.1s849 / 601
CG-AL-X160hard1100.0 / 10013/13OK10.4s1.2k / 1.3k
CG-AL-X161hard1100.0 / 10010/10OK10.1s1.4k / 1.3k
CG-AL-X162hard1100.0 / 1007/7OK11.1s956 / 770
CG-AL-X163hard1100.0 / 1007/7OK12.1s1.0k / 744
CG-AL-X164hard1100.0 / 1007/7OK10.5s945 / 865
CG-AL-X165hard20.0 / 1000/0FAIL4.1s5.3k / 7.0k
CG-AL-X166hard1100.0 / 10014/14OK11.5s1.6k / 1.4k
CG-AL-X167hard262.5 / 10010/13OK11.1s2.8k / 3.4k
CG-AL-X168hard2100.0 / 1009/9OK10.7s3.7k / 4.1k
CG-AL-X169hard1100.0 / 10011/11OK11.0s1.6k / 2.4k
CG-AL-X170hard1100.0 / 10011/11OK10.6s3.1k / 4.6k
CG-AL-X171hard1100.0 / 1009/9OK11.1s1.4k / 3.3k
CG-AL-X172hard1100.0 / 10011/11OK10.6s2.2k / 3.2k
CG-AL-X173hard262.5 / 10017/19OK11.8s7.1k / 8.1k
CG-AL-X174hard1100.0 / 10016/16OK10.5s3.9k / 4.0k
CG-AL-X185hard262.5 / 10041/43OK11.7s6.9k / 1.8k
CG-AL-X187hard262.5 / 10030/33OK11.2s7.5k / 3.6k
CG-AL-X194hard2100.0 / 10050/50OK11.5s9.9k / 3.9k
CG-AL-X211hard262.5 / 10042/43OK11.4s7.5k / 3.9k
CG-AL-X214hard2100.0 / 10034/34OK11.7s8.0k / 5.3k
CG-AL-X218hard2100.0 / 10027/27OK12.6s7.8k / 3.5k
CG-AL-X234hard1100.0 / 10035/35OK10.6s3.7k / 2.7k
CG-AL-X239hard2100.0 / 10037/37OK12.7s11k / 5.4k
CG-AL-X244hard2100.0 / 10038/38OK12.5s11k / 5.5k
CG-AL-X245hard1100.0 / 10063/63OK10.7s4.3k / 2.4k
CG-AL-X248hard2100.0 / 10066/66OK13.1s9.8k / 2.7k
CG-AL-X249hard2100.0 / 10037/37OK11.7s9.7k / 4.5k
CG-AL-X254hard262.5 / 10064/70OK11.8s15k / 5.5k
CG-AL-X257hard262.5 / 10050/53OK11.8s8.0k / 2.9k
CG-AL-X263hard2100.0 / 10061/61OK11.7s11k / 6.4k
CG-AL-X264hard1100.0 / 10065/65OK11.5s4.9k / 3.1k
CG-AL-X270hard2100.0 / 10063/63OK12.0s16k / 6.3k
CG-AL-X271hard2100.0 / 10070/70OK12.8s17k / 8.1k
CG-AL-X272hard1100.0 / 10079/79OK12.7s6.0k / 4.5k
CG-AL-X274hard262.5 / 10061/64OK11.4s14k / 5.3k
CG-AL-X276hard2100.0 / 10078/78OK12.0s15k / 5.7k
CG-AL-X278hard2100.0 / 10071/71OK12.4s15k / 6.2k
CG-AL-X283hard2100.0 / 10076/76OK11.9s14k / 4.3k
CG-AL-X289hard20.0 / 1000/0FAIL4.2s10k / 6.2k
CG-AL-X290hard2100.0 / 10047/47OK11.7s12k / 3.7k
CG-AL-X292hard1100.0 / 10057/57OK10.7s4.8k / 2.7k
CG-AL-X293hard2100.0 / 10049/49OK11.8s10k / 3.7k
CG-AL-X296hard2100.0 / 10047/47OK17.0s15k / 8.2k
CG-AL-X298hard2100.0 / 10055/55OK11.5s9.1k / 3.8k