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.

94.4% 219/232 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.

85.6 / 100
Cost $4.73
Tokens 504k / 372k input / output, all attempts
Duration 4h 37m
Filter:
Per-task results for run 922d1605-ba40-492b-be8f-e45a26ee868d
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK31.4s258 / 303
CG-AL-E006easy1100.0 / 1007/7OK1m 28s305 / 464
CG-AL-E010easy2100.0 / 1005/5OK20.1s1.6k / 369
CG-AL-E050easy1100.0 / 10013/13OK34.2s376 / 625
CG-AL-E052easy1100.0 / 10016/16OK30.5s352 / 250
CG-AL-E054easy2100.0 / 1009/9OK16.7s983 / 607
CG-AL-E056easy2100.0 / 10015/15OK21.5s1.7k / 787
CG-AL-H007hard1100.0 / 10011/11OK34.9s545 / 862
CG-AL-H011hard1100.0 / 1006/6OK33.5s352 / 273
CG-AL-H014hard2100.0 / 1007/7OK20.2s1.7k / 1.8k
CG-AL-H017hard1100.0 / 1005/5OK33.8s357 / 384
CG-AL-H020hard1100.0 / 10010/10OK49.0s467 / 1.2k
CG-AL-H021hard2100.0 / 10020/20OK27.8s13k / 1.4k
CG-AL-H023hard2100.0 / 10025/25OK1m 16s7.7k / 12k
CG-AL-H027hard1100.0 / 1004/4OK45.4s738 / 457
CG-AL-H029hard1100.0 / 10018/18OK1m 4s815 / 1.4k
CG-AL-H030hard1100.0 / 10010/10OK40.1s669 / 1.4k
CG-AL-H031hard1100.0 / 10022/22OK40.3s939 / 1.4k
CG-AL-H034hard2100.0 / 1003/3OK21.6s1.6k / 380
CG-AL-H036hard20.0 / 1000/0FAIL20.6s920 / 901
CG-AL-H037hard1100.0 / 1003/3OK20.9s497 / 277
CG-AL-H041hard1100.0 / 1003/3OK30.8s565 / 773
CG-AL-H050hard1100.0 / 1003/3OK23.8s501 / 502
CG-AL-H054hard2100.0 / 1005/5OK16.9s1.8k / 757
CG-AL-H056hard20.0 / 1000/0FAIL13.7s1.4k / 594
CG-AL-M001medium20.0 / 1000/0FAIL1m 20s1.5k / 1.3k
CG-AL-M003medium1100.0 / 1009/9OK1m 36s419 / 1.2k
CG-AL-M004medium1100.0 / 10012/12OK2m 25s449 / 1.9k
CG-AL-M006medium2100.0 / 10018/18OK1m 27s3.5k / 5.9k
CG-AL-M007medium2100.0 / 10015/15OK2m 45s1.1k / 7.3k
CG-AL-M008medium262.5 / 1001/12OK1m 21s6.6k / 14k
CG-AL-M009medium1100.0 / 10011/11OK3m 19s429 / 7.0k
CG-AL-M010medium1100.0 / 10021/21OK1m 56s596 / 2.9k
CG-AL-M020medium2100.0 / 10017/17OK1m 23s2.4k / 2.4k
CG-AL-M023medium1100.0 / 10011/11OK1m 14s482 / 520
CG-AL-M025medium2100.0 / 1008/8OK1m 8s1.6k / 2.7k
CG-AL-M026medium1100.0 / 1008/8OK1m 24s370 / 520
CG-AL-M027medium2100.0 / 10018/18OK1m 19s3.4k / 2.5k
CG-AL-M028medium2100.0 / 1003/3OK1m 27s1.0k / 689
CG-AL-M031medium1100.0 / 1002/2OK1m 39s685 / 973
CG-AL-M034medium1100.0 / 1002/2OK1m 20s415 / 401
CG-AL-M036medium211.1 / 1000/0FAIL51.3s1.5k / 756
CG-AL-M040medium1100.0 / 1002/2OK1m 4s311 / 425
CG-AL-M042medium1100.0 / 1008/8OK1m 3s498 / 426
CG-AL-X001hard1100.0 / 1002/2OK16.5s308 / 158
CG-AL-X002hard2100.0 / 1004/4OK16.9s1.3k / 1.4k
CG-AL-X003hard262.5 / 1002/3OK15.0s614 / 1.6k
CG-AL-X004medium1100.0 / 1003/3OK1m 14s358 / 543
CG-AL-X005hard1100.0 / 1002/2OK20.5s327 / 258
CG-AL-X006hard1100.0 / 1003/3OK19.4s383 / 337
CG-AL-X007hard1100.0 / 1002/2OK1m 50s372 / 554
CG-AL-X008hard1100.0 / 1001/1OK51.2s417 / 1.5k
CG-AL-X009medium1100.0 / 1002/2OK1m 13s313 / 243
CG-AL-X010medium1100.0 / 1003/3OK1m 10s284 / 222
CG-AL-X011medium1100.0 / 1002/2OK51.5s360 / 188
CG-AL-X012hard1100.0 / 1001/1OK22.5s380 / 240
CG-AL-X013hard1100.0 / 1002/2OK22.5s263 / 101
CG-AL-X014medium1100.0 / 1004/4OK44.4s291 / 119
CG-AL-X017medium2100.0 / 1003/3OK13.0s1.4k / 224
CG-AL-X018medium1100.0 / 1003/3OK43.4s384 / 296
CG-AL-X019medium2100.0 / 1003/3OK15.1s1.8k / 656
CG-AL-X022medium1100.0 / 1003/3OK20.9s276 / 480
CG-AL-X024medium1100.0 / 1003/3OK19.6s333 / 484
CG-AL-X025medium1100.0 / 1001/1OK19.7s371 / 500
CG-AL-X026medium1100.0 / 1003/3OK13.7s327 / 127
CG-AL-X027medium1100.0 / 1004/4OK24.4s258 / 461
CG-AL-X029medium1100.0 / 1002/2OK21.7s276 / 540
CG-AL-X030medium1100.0 / 1002/2OK15.8s239 / 105
CG-AL-X031medium1100.0 / 1003/3OK13.9s297 / 107
CG-AL-X033hard1100.0 / 1002/2OK21.4s348 / 186
CG-AL-X034hard1100.0 / 1003/3OK21.5s304 / 430
CG-AL-X035hard1100.0 / 1003/3OK19.9s331 / 235
CG-AL-X037hard1100.0 / 1004/4OK28.8s408 / 497
CG-AL-X040hard262.5 / 1000/4OK21.3s1.4k / 1.4k
CG-AL-X041hard1100.0 / 1005/5OK20.8s446 / 414
CG-AL-X043hard20.0 / 1000/0FAIL24.6s1.5k / 3.8k
CG-AL-X044hard2100.0 / 1003/3OK27.4s1.8k / 2.3k
CG-AL-X045hard1100.0 / 1003/3OK17.4s371 / 151
CG-AL-X046hard1100.0 / 1002/2OK15.7s369 / 226
CG-AL-X047hard1100.0 / 1002/2OK38.4s390 / 1.3k
CG-AL-X050hard1100.0 / 1002/2OK29.0s405 / 651
CG-AL-X051hard1100.0 / 1002/2OK28.8s509 / 428
CG-AL-X052hard1100.0 / 1003/3OK28.3s358 / 457
CG-AL-X055hard1100.0 / 1005/5OK28.4s344 / 348
CG-AL-X056hard1100.0 / 1005/5OK16.4s280 / 261
CG-AL-X057hard1100.0 / 1005/5OK13.2s250 / 103
CG-AL-X058hard1100.0 / 1005/5OK33.1s314 / 952
CG-AL-X059hard1100.0 / 1003/3OK12.6s327 / 65
CG-AL-X060hard1100.0 / 1003/3OK16.1s302 / 193
CG-AL-X061hard1100.0 / 1004/4OK13.1s364 / 92
CG-AL-X062hard1100.0 / 1004/4OK17.0s358 / 326
CG-AL-X063hard1100.0 / 1003/3OK19.4s360 / 387
CG-AL-X064hard1100.0 / 1007/7OK18.6s277 / 395
CG-AL-X065hard1100.0 / 1006/6OK20.0s709 / 584
CG-AL-X066hard1100.0 / 10014/14OK24.1s1.2k / 981
CG-AL-X067hard1100.0 / 1007/7OK16.3s611 / 357
CG-AL-X068hard1100.0 / 10012/12OK21.5s1.2k / 914
CG-AL-X069hard1100.0 / 1008/8OK1m 3s1.1k / 2.9k
CG-AL-X070hard1100.0 / 10012/12OK21.1s1.2k / 738
CG-AL-X071hard1100.0 / 1008/8OK24.0s1.4k / 1.1k
CG-AL-X072hard1100.0 / 1007/7OK19.9s1.1k / 768
CG-AL-X073hard1100.0 / 1008/8OK25.8s1.4k / 1.2k
CG-AL-X074hard2100.0 / 1007/7OK36.4s3.4k / 2.9k
CG-AL-X075hard1100.0 / 1007/7OK30.5s810 / 1.0k
CG-AL-X076hard2100.0 / 10014/14OK35.5s3.2k / 1.7k
CG-AL-X077hard1100.0 / 10022/22OK28.0s1.5k / 1.2k
CG-AL-X078hard1100.0 / 10017/17OK30.1s1.2k / 905
CG-AL-X079hard1100.0 / 10011/11OK52.8s1.2k / 1.8k
CG-AL-X080hard2100.0 / 1007/7OK39.4s2.4k / 1.7k
CG-AL-X081hard1100.0 / 1008/8OK22.8s902 / 564
CG-AL-X082hard1100.0 / 10015/15OK27.1s1.2k / 920
CG-AL-X083hard1100.0 / 1009/9OK29.1s1.5k / 1.2k
CG-AL-X084hard1100.0 / 10010/10OK49.9s1.4k / 1.9k
CG-AL-X085hard1100.0 / 1007/7OK23.1s980 / 643
CG-AL-X086hard1100.0 / 1006/6OK33.9s1.4k / 1.2k
CG-AL-X087hard1100.0 / 1003/3OK29.4s1.0k / 876
CG-AL-X088hard1100.0 / 1006/6OK27.7s974 / 789
CG-AL-X089hard1100.0 / 10011/11OK43.0s1.1k / 1.4k
CG-AL-X090hard1100.0 / 10010/10OK34.8s889 / 852
CG-AL-X091hard1100.0 / 1006/6OK28.4s569 / 286
CG-AL-X092hard1100.0 / 10015/15OK27.9s444 / 166
CG-AL-X093hard1100.0 / 10010/10OK35.4s989 / 814
CG-AL-X094hard1100.0 / 1007/7OK32.4s754 / 497
CG-AL-X095hard262.5 / 1003/5OK49.0s2.4k / 1.3k
CG-AL-X096hard1100.0 / 10049/49OK56.7s3.3k / 2.9k
CG-AL-X097hard1100.0 / 10046/46OK58.1s3.4k / 3.0k
CG-AL-X098hard1100.0 / 10029/29OK43.4s2.6k / 2.1k
CG-AL-X099hard1100.0 / 10039/39OK1m 14s3.6k / 3.9k
CG-AL-X100hard1100.0 / 10035/35OK52.9s3.5k / 3.0k
CG-AL-X101hard1100.0 / 10010/10OK48.5s1.1k / 816
CG-AL-X102hard1100.0 / 1008/8OK51.2s531 / 707
CG-AL-X103hard1100.0 / 1007/7OK45.8s725 / 458
CG-AL-X104hard1100.0 / 1006/6OK51.6s1.1k / 851
CG-AL-X105hard1100.0 / 1006/6OK47.2s777 / 443
CG-AL-X106hard1100.0 / 1005/5OK53.7s878 / 789
CG-AL-X107hard1100.0 / 1004/4OK49.5s805 / 604
CG-AL-X108hard1100.0 / 1006/6OK48.3s729 / 378
CG-AL-X109hard1100.0 / 1005/5OK48.4s548 / 315
CG-AL-X110hard1100.0 / 10017/17OK51.5s1.2k / 960
CG-AL-X111hard1100.0 / 1008/8OK45.4s1.2k / 1.1k
CG-AL-X112hard1100.0 / 10012/12OK42.0s906 / 1.1k
CG-AL-X113hard1100.0 / 10013/13OK28.8s705 / 655
CG-AL-X114hard1100.0 / 1007/7OK28.5s718 / 413
CG-AL-X115hard1100.0 / 10013/13OK31.8s478 / 529
CG-AL-X116hard1100.0 / 10017/17OK35.8s926 / 792
CG-AL-X117hard1100.0 / 1008/8OK30.4s1.0k / 764
CG-AL-X118hard1100.0 / 10017/17OK38.5s1.4k / 1.1k
CG-AL-X119hard1100.0 / 10015/15OK40.7s1.7k / 1.6k
CG-AL-X120hard1100.0 / 10012/12OK32.9s1.2k / 1.0k
CG-AL-X121hard1100.0 / 1006/6OK30.6s1.0k / 792
CG-AL-X122hard1100.0 / 10010/10OK40.9s1.5k / 1.3k
CG-AL-X123hard1100.0 / 1005/5OK30.5s603 / 329
CG-AL-X124hard1100.0 / 10010/10OK31.0s994 / 675
CG-AL-X125hard1100.0 / 1008/8OK41.0s1.4k / 1.3k
CG-AL-X126hard1100.0 / 10014/14OK32.2s711 / 471
CG-AL-X127hard1100.0 / 1005/5OK30.4s666 / 505
CG-AL-X128hard1100.0 / 1008/8OK30.4s1.1k / 811
CG-AL-X129hard1100.0 / 10014/14OK34.4s1.2k / 1.0k
CG-AL-X130hard1100.0 / 1005/5OK24.8s529 / 310
CG-AL-X131hard1100.0 / 10013/13OK28.7s941 / 622
CG-AL-X132hard1100.0 / 10010/10OK26.0s709 / 410
CG-AL-X133hard20.0 / 1000/0FAIL1m 15s2.9k / 2.1k
CG-AL-X134hard1100.0 / 1006/6OK36.7s1.2k / 1.3k
CG-AL-X135hard1100.0 / 1004/4OK26.9s866 / 554
CG-AL-X136hard1100.0 / 1007/7OK22.0s754 / 353
CG-AL-X137hard1100.0 / 1004/4OK25.7s915 / 626
CG-AL-X138hard1100.0 / 1009/9OK34.1s1.4k / 1.4k
CG-AL-X139hard1100.0 / 10011/11OK32.9s1.6k / 1.4k
CG-AL-X140hard20.0 / 1000/0FAIL1m 32s2.9k / 3.9k
CG-AL-X141hard1100.0 / 10039/39OK57.8s3.5k / 3.5k
CG-AL-X142hard262.5 / 10045/48OK1m 27s8.8k / 8.1k
CG-AL-X143hard1100.0 / 10035/35OK1m 10s4.0k / 3.6k
CG-AL-X144hard2100.0 / 10043/43OK1m 28s7.9k / 6.6k
CG-AL-X145hard1100.0 / 10032/32OK1m 32s4.2k / 3.9k
CG-AL-X146hard1100.0 / 1009/9OK1m 31s1.7k / 2.3k
CG-AL-X147hard1100.0 / 1008/8OK1m 10s1.3k / 992
CG-AL-X148hard1100.0 / 1006/6OK1m 17s1.1k / 788
CG-AL-X149hard1100.0 / 1007/7OK1m 19s1.1k / 853
CG-AL-X150hard1100.0 / 1009/9OK2m 1s1.9k / 2.8k
CG-AL-X151hard1100.0 / 1006/6OK1m 19s818 / 511
CG-AL-X152hard1100.0 / 1008/8OK1m 21s1.1k / 731
CG-AL-X153hard2100.0 / 1009/9OK51.8s2.1k / 1.5k
CG-AL-X154hard1100.0 / 1009/9OK1m 26s1.2k / 1.0k
CG-AL-X155hard1100.0 / 10011/11OK55.2s923 / 745
CG-AL-X156hard1100.0 / 1007/7OK43.9s884 / 541
CG-AL-X157hard1100.0 / 10010/10OK52.3s1.3k / 917
CG-AL-X158hard1100.0 / 1007/7OK49.5s801 / 446
CG-AL-X159hard1100.0 / 1007/7OK55.5s849 / 591
CG-AL-X160hard1100.0 / 10013/13OK57.5s1.2k / 1.1k
CG-AL-X161hard1100.0 / 10010/10OK59.9s1.4k / 1.3k
CG-AL-X162hard1100.0 / 1007/7OK54.2s956 / 694
CG-AL-X163hard1100.0 / 1007/7OK58.9s1.0k / 735
CG-AL-X164hard1100.0 / 1007/7OK58.6s945 / 656
CG-AL-X165hard1100.0 / 10013/13OK1m 41s2.6k / 3.5k
CG-AL-X166hard1100.0 / 10014/14OK59.0s1.6k / 1.1k
CG-AL-X167hard1100.0 / 10013/13OK1m 24s1.4k / 2.2k
CG-AL-X168hard1100.0 / 1009/9OK1m 11s1.3k / 2.1k
CG-AL-X169hard1100.0 / 10011/11OK1m 11s1.6k / 2.2k
CG-AL-X170hard1100.0 / 10011/11OK1m 14s3.1k / 3.0k
CG-AL-X171hard1100.0 / 1009/9OK1m 34s1.4k / 1.9k
CG-AL-X172hard1100.0 / 10011/11OK1m 36s2.2k / 2.6k
CG-AL-X173hard1100.0 / 10019/19OK1m 48s3.1k / 3.6k
CG-AL-X174hard1100.0 / 10016/16OK1m 44s3.9k / 4.0k
CG-AL-X185hard2100.0 / 10043/43OK1m 34s5.4k / 1.7k
CG-AL-X187hard2100.0 / 10033/33OK1m 33s7.4k / 2.7k
CG-AL-X194hard2100.0 / 10050/50OK1m 23s10.0k / 3.4k
CG-AL-X211hard2100.0 / 10043/43OK1m 27s7.4k / 3.6k
CG-AL-X214hard262.5 / 10031/34OK1m 35s7.7k / 2.6k
CG-AL-X218hard1100.0 / 10027/27OK2m 32s3.5k / 3.3k
CG-AL-X234hard1100.0 / 10035/35OK1m 54s3.7k / 1.9k
CG-AL-X239hard2100.0 / 10037/37OK1m 21s11k / 4.0k
CG-AL-X244hard2100.0 / 10038/38OK1m 58s11k / 5.1k
CG-AL-X245hard1100.0 / 10063/63OK1m 50s4.3k / 2.1k
CG-AL-X248hard1100.0 / 10066/66OK1m 47s4.3k / 1.9k
CG-AL-X249hard2100.0 / 10037/37OK1m 47s9.4k / 3.6k
CG-AL-X254hard2100.0 / 10070/70OK1m 49s13k / 3.8k
CG-AL-X257hard2100.0 / 10053/53OK1m 52s8.7k / 3.4k
CG-AL-X263hard2100.0 / 10061/61OK1m 37s10k / 5.3k
CG-AL-X264hard1100.0 / 10065/65OK2m 22s4.9k / 3.7k
CG-AL-X270hard2100.0 / 10063/63OK1m 46s15k / 5.8k
CG-AL-X271hard2100.0 / 10070/70OK1m 35s16k / 6.5k
CG-AL-X272hard2100.0 / 10079/79OK1m 26s12k / 3.8k
CG-AL-X274hard2100.0 / 10064/64OK1m 46s12k / 5.1k
CG-AL-X276hard2100.0 / 10078/78OK1m 29s14k / 3.5k
CG-AL-X278hard2100.0 / 10071/71OK1m 22s13k / 5.2k
CG-AL-X283hard1100.0 / 10076/76OK2m 30s6.5k / 3.9k
CG-AL-X289hard1100.0 / 10057/57OK3m 2s5.0k / 5.2k
CG-AL-X290hard1100.0 / 10047/47OK2m 20s5.1k / 3.4k
CG-AL-X292hard1100.0 / 10057/57OK1m 51s4.8k / 1.6k
CG-AL-X293hard1100.0 / 10049/49OK2m 20s4.3k / 2.9k
CG-AL-X296hard1100.0 / 10047/47OK2m 23s6.6k / 4.6k
CG-AL-X298hard1100.0 / 10055/55OK1m 29s4.4k / 1.6k