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.

92.7% 215/232 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.

84.6 / 100
Cost $4.97
Tokens 519k / 390k input / output, all attempts
Duration 4h 54m
Filter:
Per-task results for run 865c858f-c006-40bf-8592-fa8129b7351a
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.3s258 / 320
CG-AL-E006easy1100.0 / 1007/7OK31.0s305 / 442
CG-AL-E010easy1100.0 / 1005/5OK17.6s280 / 238
CG-AL-E050easy2100.0 / 10013/13OK44.5s1.8k / 1.2k
CG-AL-E052easy1100.0 / 10016/16OK14.9s352 / 250
CG-AL-E054easy2100.0 / 1009/9OK28.1s986 / 589
CG-AL-E056easy2100.0 / 10015/15OK40.7s1.7k / 740
CG-AL-H007hard1100.0 / 10011/11OK34.2s545 / 950
CG-AL-H011hard1100.0 / 1006/6OK22.4s352 / 267
CG-AL-H014hard2100.0 / 1007/7OK41.0s1.6k / 1.7k
CG-AL-H017hard1100.0 / 1005/5OK32.2s357 / 482
CG-AL-H020hard1100.0 / 10010/10OK41.6s467 / 1.0k
CG-AL-H021hard2100.0 / 10020/20OK41.3s13k / 1.4k
CG-AL-H023hard2100.0 / 10025/25OK1m 19s8.7k / 15k
CG-AL-H027hard1100.0 / 1004/4OK55.9s738 / 958
CG-AL-H029hard1100.0 / 10018/18OK1m 4s815 / 1.4k
CG-AL-H030hard1100.0 / 10010/10OK54.4s669 / 1.5k
CG-AL-H031hard1100.0 / 10022/22OK48.5s939 / 1.3k
CG-AL-H034hard2100.0 / 1003/3OK14.7s1.6k / 366
CG-AL-H036hard20.0 / 1000/0FAIL14.4s912 / 718
CG-AL-H037hard1100.0 / 1003/3OK39.9s497 / 255
CG-AL-H041hard1100.0 / 1003/3OK52.5s565 / 784
CG-AL-H050hard1100.0 / 1003/3OK47.2s501 / 542
CG-AL-H054hard2100.0 / 1005/5OK15.4s1.8k / 782
CG-AL-H056hard2100.0 / 1004/4OK30.4s1.4k / 1.1k
CG-AL-M001medium20.0 / 1000/0FAIL1m 28s1.5k / 1.4k
CG-AL-M003medium1100.0 / 1009/9OK2m 3s419 / 1.2k
CG-AL-M004medium1100.0 / 10012/12OK2m 10s449 / 1.9k
CG-AL-M006medium2100.0 / 10018/18OK1m 42s3.4k / 5.5k
CG-AL-M007medium20.0 / 1000/0FAIL1m 31s6.8k / 13k
CG-AL-M008medium262.5 / 1002/12OK1m 31s11k / 16k
CG-AL-M009medium2100.0 / 10011/11OK1m 37s7.0k / 13k
CG-AL-M010medium1100.0 / 10021/21OK2m 35s596 / 3.1k
CG-AL-M020medium2100.0 / 10017/17OK52.9s1.9k / 1.8k
CG-AL-M023medium1100.0 / 10011/11OK2m 6s482 / 532
CG-AL-M025medium1100.0 / 1008/8OK2m 15s400 / 791
CG-AL-M026medium1100.0 / 1008/8OK2m 10s370 / 472
CG-AL-M027medium2100.0 / 10018/18OK43.5s3.4k / 2.3k
CG-AL-M028medium1100.0 / 1003/3OK2m 21s357 / 592
CG-AL-M031medium1100.0 / 1002/2OK2m 11s685 / 795
CG-AL-M034medium1100.0 / 1002/2OK1m 44s415 / 405
CG-AL-M036medium211.1 / 1000/0FAIL26.5s1.5k / 761
CG-AL-M040medium2100.0 / 1002/2OK34.2s793 / 1.0k
CG-AL-M042medium1100.0 / 1008/8OK54.3s498 / 437
CG-AL-X001hard1100.0 / 1002/2OK19.1s308 / 179
CG-AL-X002hard1100.0 / 1004/4OK32.0s488 / 757
CG-AL-X003hard2100.0 / 1003/3OK14.7s824 / 1.5k
CG-AL-X004medium1100.0 / 1003/3OK49.4s358 / 515
CG-AL-X005hard1100.0 / 1002/2OK20.0s327 / 231
CG-AL-X006hard1100.0 / 1003/3OK25.6s383 / 346
CG-AL-X007hard1100.0 / 1002/2OK1m 45s372 / 486
CG-AL-X008hard1100.0 / 1001/1OK48.2s417 / 1.3k
CG-AL-X009medium1100.0 / 1002/2OK43.6s313 / 249
CG-AL-X010medium1100.0 / 1003/3OK33.5s284 / 246
CG-AL-X011medium1100.0 / 1002/2OK31.6s360 / 255
CG-AL-X012hard1100.0 / 1001/1OK27.0s380 / 243
CG-AL-X013hard1100.0 / 1002/2OK19.9s263 / 112
CG-AL-X014medium1100.0 / 1004/4OK30.7s291 / 135
CG-AL-X017medium2100.0 / 1003/3OK26.5s1.4k / 204
CG-AL-X018medium1100.0 / 1003/3OK32.6s384 / 262
CG-AL-X019medium2100.0 / 1003/3OK14.4s1.8k / 590
CG-AL-X022medium2100.0 / 1003/3OK21.3s1.3k / 927
CG-AL-X024medium1100.0 / 1003/3OK25.5s333 / 525
CG-AL-X025medium1100.0 / 1001/1OK27.3s371 / 499
CG-AL-X026medium1100.0 / 1003/3OK22.9s327 / 127
CG-AL-X027medium1100.0 / 1004/4OK28.9s258 / 446
CG-AL-X029medium1100.0 / 1002/2OK28.7s276 / 497
CG-AL-X030medium1100.0 / 1002/2OK21.5s239 / 111
CG-AL-X031medium1100.0 / 1003/3OK20.4s297 / 108
CG-AL-X033hard1100.0 / 1002/2OK19.6s348 / 148
CG-AL-X034hard1100.0 / 1003/3OK23.5s304 / 260
CG-AL-X035hard1100.0 / 1003/3OK17.9s331 / 284
CG-AL-X037hard1100.0 / 1004/4OK21.7s408 / 480
CG-AL-X040hard262.5 / 1000/4OK30.0s1.4k / 1.7k
CG-AL-X041hard262.5 / 1000/5OK18.3s1.1k / 1.1k
CG-AL-X043hard2100.0 / 1001/1OK47.2s1.9k / 5.6k
CG-AL-X044hard20.0 / 1000/0FAIL19.3s1.7k / 2.7k
CG-AL-X045hard1100.0 / 1003/3OK17.1s371 / 101
CG-AL-X046hard1100.0 / 1002/2OK20.7s369 / 264
CG-AL-X047hard1100.0 / 1002/2OK36.0s390 / 1.1k
CG-AL-X050hard1100.0 / 1002/2OK26.7s405 / 507
CG-AL-X051hard1100.0 / 1002/2OK24.7s509 / 349
CG-AL-X052hard1100.0 / 1003/3OK18.8s358 / 379
CG-AL-X055hard1100.0 / 1005/5OK18.3s344 / 352
CG-AL-X056hard1100.0 / 1005/5OK18.2s280 / 215
CG-AL-X057hard1100.0 / 1005/5OK13.1s250 / 110
CG-AL-X058hard1100.0 / 1005/5OK28.6s314 / 775
CG-AL-X059hard1100.0 / 1003/3OK12.6s327 / 63
CG-AL-X060hard1100.0 / 1003/3OK15.5s302 / 191
CG-AL-X061hard1100.0 / 1004/4OK13.0s364 / 92
CG-AL-X062hard1100.0 / 1004/4OK16.7s358 / 337
CG-AL-X063hard1100.0 / 1003/3OK19.8s360 / 336
CG-AL-X064hard1100.0 / 1007/7OK17.6s277 / 314
CG-AL-X065hard1100.0 / 1006/6OK19.2s709 / 583
CG-AL-X066hard1100.0 / 10014/14OK26.7s1.2k / 959
CG-AL-X067hard1100.0 / 1007/7OK17.2s611 / 375
CG-AL-X068hard1100.0 / 10012/12OK24.8s1.2k / 923
CG-AL-X069hard1100.0 / 1008/8OK47.3s1.1k / 1.9k
CG-AL-X070hard1100.0 / 10012/12OK20.3s1.2k / 735
CG-AL-X071hard1100.0 / 1008/8OK24.4s1.4k / 1.1k
CG-AL-X072hard1100.0 / 1007/7OK20.5s1.1k / 768
CG-AL-X073hard1100.0 / 1008/8OK26.9s1.4k / 1.3k
CG-AL-X074hard2100.0 / 1007/7OK33.5s3.4k / 2.8k
CG-AL-X075hard1100.0 / 1007/7OK27.1s810 / 771
CG-AL-X076hard1100.0 / 10014/14OK32.1s954 / 1.0k
CG-AL-X077hard1100.0 / 10022/22OK28.5s1.5k / 1.2k
CG-AL-X078hard1100.0 / 10017/17OK29.3s1.2k / 905
CG-AL-X079hard1100.0 / 10011/11OK34.4s1.2k / 1.3k
CG-AL-X080hard2100.0 / 1007/7OK33.7s2.4k / 1.8k
CG-AL-X081hard1100.0 / 1008/8OK21.7s902 / 564
CG-AL-X082hard1100.0 / 10015/15OK23.8s1.2k / 920
CG-AL-X083hard1100.0 / 1009/9OK25.9s1.5k / 1.2k
CG-AL-X084hard1100.0 / 10010/10OK39.8s1.4k / 1.5k
CG-AL-X085hard1100.0 / 1007/7OK21.1s980 / 621
CG-AL-X086hard1100.0 / 1006/6OK30.3s1.4k / 1.1k
CG-AL-X087hard1100.0 / 1003/3OK28.1s1.0k / 844
CG-AL-X088hard1100.0 / 1006/6OK25.9s974 / 817
CG-AL-X089hard1100.0 / 10011/11OK35.7s1.1k / 1.4k
CG-AL-X090hard1100.0 / 10010/10OK36.7s889 / 875
CG-AL-X091hard1100.0 / 1006/6OK22.2s569 / 286
CG-AL-X092hard1100.0 / 10015/15OK21.4s444 / 190
CG-AL-X093hard1100.0 / 10010/10OK29.5s989 / 810
CG-AL-X094hard1100.0 / 1007/7OK25.7s754 / 497
CG-AL-X095hard262.5 / 1003/5OK46.6s2.4k / 1.3k
CG-AL-X096hard1100.0 / 10049/49OK51.7s3.3k / 2.9k
CG-AL-X097hard1100.0 / 10046/46OK52.3s3.4k / 3.0k
CG-AL-X098hard1100.0 / 10029/29OK41.9s2.6k / 2.1k
CG-AL-X099hard1100.0 / 10039/39OK1m 4s3.6k / 3.6k
CG-AL-X100hard1100.0 / 10035/35OK54.4s3.5k / 3.0k
CG-AL-X101hard1100.0 / 10010/10OK48.5s1.1k / 811
CG-AL-X102hard1100.0 / 1008/8OK50.0s531 / 716
CG-AL-X103hard1100.0 / 1007/7OK43.8s725 / 458
CG-AL-X104hard1100.0 / 1006/6OK51.2s1.1k / 851
CG-AL-X105hard1100.0 / 1006/6OK46.3s777 / 443
CG-AL-X106hard1100.0 / 1005/5OK49.9s878 / 765
CG-AL-X107hard1100.0 / 1004/4OK47.2s805 / 607
CG-AL-X108hard1100.0 / 1006/6OK46.3s729 / 376
CG-AL-X109hard1100.0 / 1005/5OK48.9s548 / 328
CG-AL-X110hard1100.0 / 10017/17OK49.0s1.2k / 960
CG-AL-X111hard1100.0 / 1008/8OK35.9s1.2k / 1.1k
CG-AL-X112hard1100.0 / 10012/12OK35.7s906 / 930
CG-AL-X113hard1100.0 / 10013/13OK28.8s705 / 657
CG-AL-X114hard1100.0 / 1007/7OK24.1s718 / 413
CG-AL-X115hard1100.0 / 10013/13OK26.9s478 / 355
CG-AL-X116hard1100.0 / 10017/17OK34.7s926 / 821
CG-AL-X117hard1100.0 / 1008/8OK30.3s1.0k / 789
CG-AL-X118hard1100.0 / 10017/17OK34.7s1.4k / 1.1k
CG-AL-X119hard1100.0 / 10015/15OK36.1s1.7k / 1.6k
CG-AL-X120hard1100.0 / 10012/12OK28.3s1.2k / 1.0k
CG-AL-X121hard1100.0 / 1006/6OK31.7s1.0k / 792
CG-AL-X122hard1100.0 / 10010/10OK38.3s1.5k / 1.3k
CG-AL-X123hard1100.0 / 1005/5OK28.8s603 / 338
CG-AL-X124hard1100.0 / 10010/10OK33.4s994 / 794
CG-AL-X125hard1100.0 / 1008/8OK43.3s1.4k / 1.3k
CG-AL-X126hard1100.0 / 10014/14OK30.3s711 / 377
CG-AL-X127hard1100.0 / 1005/5OK28.2s666 / 491
CG-AL-X128hard1100.0 / 1008/8OK32.4s1.1k / 811
CG-AL-X129hard1100.0 / 10014/14OK35.2s1.2k / 1.0k
CG-AL-X130hard1100.0 / 1005/5OK25.0s529 / 305
CG-AL-X131hard1100.0 / 10013/13OK27.1s941 / 610
CG-AL-X132hard1100.0 / 10010/10OK25.7s709 / 410
CG-AL-X133hard20.0 / 1000/0FAIL1m 19s1.9k / 2.3k
CG-AL-X134hard1100.0 / 1006/6OK39.2s1.2k / 1.3k
CG-AL-X135hard1100.0 / 1004/4OK26.9s866 / 554
CG-AL-X136hard1100.0 / 1007/7OK22.4s754 / 341
CG-AL-X137hard1100.0 / 1004/4OK27.1s915 / 688
CG-AL-X138hard1100.0 / 1009/9OK36.1s1.4k / 1.3k
CG-AL-X139hard1100.0 / 10011/11OK31.5s1.6k / 1.4k
CG-AL-X140hard20.0 / 1000/0FAIL1m 30s2.9k / 2.6k
CG-AL-X141hard1100.0 / 10039/39OK1m 7s3.5k / 3.4k
CG-AL-X142hard20.0 / 1000/0FAIL2m 7s5.7k / 7.9k
CG-AL-X143hard1100.0 / 10035/35OK1m 16s4.0k / 3.7k
CG-AL-X144hard2100.0 / 10043/43OK1m 21s7.9k / 6.5k
CG-AL-X145hard1100.0 / 10032/32OK1m 14s4.2k / 3.9k
CG-AL-X146hard1100.0 / 1009/9OK1m 36s1.7k / 2.3k
CG-AL-X147hard1100.0 / 1008/8OK1m 13s1.3k / 948
CG-AL-X148hard1100.0 / 1006/6OK1m 11s1.1k / 788
CG-AL-X149hard1100.0 / 1007/7OK1m 8s1.1k / 862
CG-AL-X150hard2100.0 / 1009/9OK1m 1s5.1k / 5.2k
CG-AL-X151hard1100.0 / 1006/6OK1m 12s818 / 511
CG-AL-X152hard1100.0 / 1008/8OK1m 9s1.1k / 731
CG-AL-X153hard2100.0 / 1009/9OK49.8s2.1k / 1.7k
CG-AL-X154hard1100.0 / 1009/9OK1m 29s1.2k / 1.1k
CG-AL-X155hard1100.0 / 10011/11OK50.5s923 / 742
CG-AL-X156hard1100.0 / 1007/7OK48.7s884 / 541
CG-AL-X157hard1100.0 / 10010/10OK54.4s1.3k / 917
CG-AL-X158hard1100.0 / 1007/7OK57.2s801 / 446
CG-AL-X159hard1100.0 / 1007/7OK48.6s849 / 610
CG-AL-X160hard1100.0 / 10013/13OK54.1s1.2k / 1.1k
CG-AL-X161hard1100.0 / 10010/10OK57.4s1.4k / 1.3k
CG-AL-X162hard1100.0 / 1007/7OK52.2s956 / 694
CG-AL-X163hard1100.0 / 1007/7OK52.4s1.0k / 713
CG-AL-X164hard1100.0 / 1007/7OK48.5s945 / 644
CG-AL-X165hard1100.0 / 10013/13OK1m 28s2.6k / 3.3k
CG-AL-X166hard1100.0 / 10014/14OK49.2s1.6k / 1.1k
CG-AL-X167hard2100.0 / 10013/13OK1m 40s5.4k / 3.8k
CG-AL-X168hard1100.0 / 1009/9OK1m 19s1.3k / 2.3k
CG-AL-X169hard1100.0 / 10011/11OK1m 22s1.6k / 1.8k
CG-AL-X170hard1100.0 / 10011/11OK1m 43s3.1k / 3.0k
CG-AL-X171hard1100.0 / 1009/9OK1m 30s1.4k / 1.8k
CG-AL-X172hard1100.0 / 10011/11OK1m 40s2.2k / 2.7k
CG-AL-X173hard1100.0 / 10019/19OK1m 48s3.1k / 3.3k
CG-AL-X174hard1100.0 / 10016/16OK2m 0s3.9k / 3.8k
CG-AL-X185hard262.5 / 10041/43OK1m 30s5.3k / 1.5k
CG-AL-X187hard2100.0 / 10033/33OK1m 48s7.3k / 3.0k
CG-AL-X194hard2100.0 / 10050/50OK1m 22s10.0k / 3.6k
CG-AL-X211hard2100.0 / 10043/43OK1m 23s8.1k / 3.9k
CG-AL-X214hard262.5 / 10031/34OK1m 24s7.7k / 2.5k
CG-AL-X218hard262.5 / 10024/27OK1m 26s7.7k / 2.9k
CG-AL-X234hard1100.0 / 10035/35OK1m 51s3.7k / 2.0k
CG-AL-X239hard2100.0 / 10037/37OK1m 57s11k / 4.1k
CG-AL-X244hard262.5 / 10037/38OK2m 1s11k / 6.0k
CG-AL-X245hard1100.0 / 10063/63OK1m 56s4.3k / 2.1k
CG-AL-X248hard1100.0 / 10066/66OK1m 36s4.3k / 1.8k
CG-AL-X249hard2100.0 / 10037/37OK1m 46s9.4k / 3.6k
CG-AL-X254hard1100.0 / 10070/70OK1m 55s5.6k / 2.5k
CG-AL-X257hard2100.0 / 10053/53OK2m 17s8.8k / 4.0k
CG-AL-X263hard2100.0 / 10061/61OK2m 19s9.5k / 4.3k
CG-AL-X264hard1100.0 / 10065/65OK2m 22s4.9k / 3.7k
CG-AL-X270hard2100.0 / 10063/63OK2m 4s15k / 5.3k
CG-AL-X271hard2100.0 / 10070/70OK2m 13s16k / 6.0k
CG-AL-X272hard1100.0 / 10079/79OK1m 35s6.0k / 3.4k
CG-AL-X274hard2100.0 / 10064/64OK1m 41s12k / 6.0k
CG-AL-X276hard2100.0 / 10078/78OK1m 51s14k / 3.5k
CG-AL-X278hard262.5 / 10070/71OK1m 52s13k / 6.6k
CG-AL-X283hard1100.0 / 10076/76OK2m 32s6.5k / 3.8k
CG-AL-X289hard1100.0 / 10057/57OK3m 13s5.0k / 5.2k
CG-AL-X290hard2100.0 / 10047/47OK1m 49s11k / 6.0k
CG-AL-X292hard1100.0 / 10057/57OK2m 41s4.8k / 1.7k
CG-AL-X293hard1100.0 / 10049/49OK2m 39s4.3k / 2.9k
CG-AL-X296hard1100.0 / 10047/47OK2m 50s6.6k / 4.2k
CG-AL-X298hard1100.0 / 10055/55OK2m 25s4.4k / 1.7k