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.

86.9 / 100
Cost $4.60
Tokens 480k / 361k input / output, all attempts
Duration 4h 23m
Filter:
Per-task results for run 8d17fba9-10d8-4915-92c4-20a72e2f6726
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK18.2s258 / 341
CG-AL-E006easy1100.0 / 1007/7OK33.2s305 / 432
CG-AL-E010easy1100.0 / 1005/5OK15.5s280 / 211
CG-AL-E050easy2100.0 / 10013/13OK36.2s1.9k / 1.3k
CG-AL-E052easy1100.0 / 10016/16OK16.3s352 / 248
CG-AL-E054easy2100.0 / 1009/9OK30.5s986 / 641
CG-AL-E056easy2100.0 / 10015/15OK37.8s1.7k / 744
CG-AL-H007hard1100.0 / 10011/11OK30.3s545 / 792
CG-AL-H011hard1100.0 / 1006/6OK22.6s352 / 244
CG-AL-H014hard2100.0 / 1007/7OK48.3s1.7k / 1.8k
CG-AL-H017hard1100.0 / 1005/5OK33.1s357 / 474
CG-AL-H020hard1100.0 / 10010/10OK44.8s467 / 1.2k
CG-AL-H021hard2100.0 / 10020/20OK39.4s13k / 1.3k
CG-AL-H023hard1100.0 / 10025/25OK2m 55s1.2k / 8.5k
CG-AL-H027hard1100.0 / 1004/4OK42.5s738 / 438
CG-AL-H029hard1100.0 / 10018/18OK1m 3s815 / 1.6k
CG-AL-H030hard1100.0 / 10010/10OK49.3s669 / 1.3k
CG-AL-H031hard1100.0 / 10022/22OK49.2s939 / 1.3k
CG-AL-H034hard1100.0 / 1003/3OK35.9s431 / 347
CG-AL-H036hard20.0 / 1000/0FAIL21.2s928 / 726
CG-AL-H037hard1100.0 / 1003/3OK38.4s497 / 291
CG-AL-H041hard1100.0 / 1003/3OK47.6s565 / 722
CG-AL-H050hard1100.0 / 1003/3OK48.8s501 / 671
CG-AL-H054hard2100.0 / 1005/5OK18.9s1.8k / 771
CG-AL-H056hard20.0 / 1000/0FAIL15.9s1.4k / 465
CG-AL-M001medium20.0 / 1000/0FAIL1m 40s1.4k / 1.3k
CG-AL-M003medium1100.0 / 1009/9OK1m 49s419 / 1.1k
CG-AL-M004medium1100.0 / 10012/12OK1m 59s449 / 1.9k
CG-AL-M006medium1100.0 / 10018/18OK2m 11s408 / 3.7k
CG-AL-M007medium262.5 / 10013/15OK1m 17s6.2k / 13k
CG-AL-M008medium262.5 / 1001/12OK1m 22s7.9k / 17k
CG-AL-M009medium2100.0 / 10011/11OK1m 32s6.3k / 11k
CG-AL-M010medium1100.0 / 10021/21OK1m 58s596 / 3.0k
CG-AL-M020medium2100.0 / 10017/17OK1m 13s2.4k / 2.6k
CG-AL-M023medium1100.0 / 10011/11OK1m 44s482 / 582
CG-AL-M025medium1100.0 / 1008/8OK2m 0s400 / 1.0k
CG-AL-M026medium1100.0 / 1008/8OK1m 55s370 / 541
CG-AL-M027medium2100.0 / 10018/18OK43.6s3.4k / 2.4k
CG-AL-M028medium1100.0 / 1003/3OK1m 56s357 / 566
CG-AL-M031medium1100.0 / 1002/2OK1m 45s685 / 842
CG-AL-M034medium1100.0 / 1002/2OK1m 42s415 / 367
CG-AL-M036medium211.1 / 1000/0FAIL28.0s1.5k / 696
CG-AL-M040medium2100.0 / 1002/2OK23.3s780 / 666
CG-AL-M042medium1100.0 / 1008/8OK59.4s498 / 458
CG-AL-X001hard1100.0 / 1002/2OK26.9s308 / 168
CG-AL-X002hard1100.0 / 1004/4OK40.3s488 / 817
CG-AL-X003hard2100.0 / 1003/3OK21.6s957 / 1.2k
CG-AL-X004medium1100.0 / 1003/3OK1m 2s358 / 529
CG-AL-X005hard1100.0 / 1002/2OK20.8s327 / 245
CG-AL-X006hard1100.0 / 1003/3OK19.3s383 / 343
CG-AL-X007hard1100.0 / 1002/2OK1m 45s372 / 321
CG-AL-X008hard1100.0 / 1001/1OK36.4s417 / 939
CG-AL-X009medium1100.0 / 1002/2OK56.2s313 / 210
CG-AL-X010medium1100.0 / 1003/3OK54.7s284 / 122
CG-AL-X011medium1100.0 / 1002/2OK43.7s360 / 192
CG-AL-X012hard1100.0 / 1001/1OK20.1s380 / 237
CG-AL-X013hard1100.0 / 1002/2OK17.8s263 / 116
CG-AL-X014medium1100.0 / 1004/4OK32.6s291 / 122
CG-AL-X017medium2100.0 / 1003/3OK17.2s1.4k / 231
CG-AL-X018medium1100.0 / 1003/3OK27.6s384 / 319
CG-AL-X019medium2100.0 / 1003/3OK13.8s1.8k / 653
CG-AL-X022medium1100.0 / 1003/3OK27.8s276 / 507
CG-AL-X024medium1100.0 / 1003/3OK31.4s333 / 554
CG-AL-X025medium1100.0 / 1001/1OK25.0s371 / 485
CG-AL-X026medium1100.0 / 1003/3OK20.4s327 / 127
CG-AL-X027medium1100.0 / 1004/4OK27.0s258 / 494
CG-AL-X029medium1100.0 / 1002/2OK24.3s276 / 440
CG-AL-X030medium1100.0 / 1002/2OK25.4s239 / 122
CG-AL-X031medium1100.0 / 1003/3OK19.8s297 / 108
CG-AL-X033hard1100.0 / 1002/2OK20.7s348 / 176
CG-AL-X034hard1100.0 / 1003/3OK15.6s304 / 203
CG-AL-X035hard1100.0 / 1003/3OK17.5s331 / 274
CG-AL-X037hard1100.0 / 1004/4OK28.5s408 / 671
CG-AL-X040hard2100.0 / 1004/4OK19.1s2.7k / 1.6k
CG-AL-X041hard1100.0 / 1005/5OK23.8s446 / 497
CG-AL-X043hard20.0 / 1000/0FAIL22.8s1.5k / 4.0k
CG-AL-X044hard1100.0 / 1003/3OK49.6s377 / 1.7k
CG-AL-X045hard1100.0 / 1003/3OK17.3s371 / 157
CG-AL-X046hard1100.0 / 1002/2OK21.2s369 / 313
CG-AL-X047hard1100.0 / 1002/2OK46.5s390 / 1.2k
CG-AL-X050hard1100.0 / 1002/2OK31.4s405 / 440
CG-AL-X051hard1100.0 / 1002/2OK27.4s509 / 358
CG-AL-X052hard1100.0 / 1003/3OK24.9s358 / 535
CG-AL-X055hard1100.0 / 1005/5OK19.9s344 / 330
CG-AL-X056hard1100.0 / 1005/5OK15.5s280 / 221
CG-AL-X057hard1100.0 / 1005/5OK14.6s250 / 124
CG-AL-X058hard1100.0 / 1005/5OK21.5s314 / 510
CG-AL-X059hard1100.0 / 1003/3OK13.1s327 / 63
CG-AL-X060hard1100.0 / 1003/3OK15.2s302 / 172
CG-AL-X061hard1100.0 / 1004/4OK13.4s364 / 92
CG-AL-X062hard1100.0 / 1004/4OK16.3s358 / 310
CG-AL-X063hard1100.0 / 1003/3OK17.0s360 / 287
CG-AL-X064hard1100.0 / 1007/7OK22.1s277 / 480
CG-AL-X065hard1100.0 / 1006/6OK19.8s709 / 562
CG-AL-X066hard1100.0 / 10014/14OK23.1s1.2k / 963
CG-AL-X067hard1100.0 / 1007/7OK16.4s611 / 369
CG-AL-X068hard1100.0 / 10012/12OK22.5s1.2k / 930
CG-AL-X069hard1100.0 / 1008/8OK50.3s1.1k / 2.4k
CG-AL-X070hard1100.0 / 10012/12OK20.8s1.2k / 745
CG-AL-X071hard1100.0 / 1008/8OK23.7s1.4k / 1.1k
CG-AL-X072hard1100.0 / 1007/7OK20.6s1.1k / 768
CG-AL-X073hard1100.0 / 1008/8OK28.1s1.4k / 1.4k
CG-AL-X074hard2100.0 / 1007/7OK39.8s3.4k / 2.9k
CG-AL-X075hard1100.0 / 1007/7OK27.5s810 / 951
CG-AL-X076hard1100.0 / 10014/14OK25.4s954 / 796
CG-AL-X077hard1100.0 / 10022/22OK33.2s1.5k / 1.2k
CG-AL-X078hard1100.0 / 10017/17OK26.2s1.2k / 905
CG-AL-X079hard1100.0 / 10011/11OK35.8s1.2k / 1.3k
CG-AL-X080hard2100.0 / 1007/7OK35.5s2.4k / 1.8k
CG-AL-X081hard1100.0 / 1008/8OK21.2s902 / 564
CG-AL-X082hard1100.0 / 10015/15OK24.2s1.2k / 920
CG-AL-X083hard1100.0 / 1009/9OK28.7s1.5k / 1.2k
CG-AL-X084hard1100.0 / 10010/10OK45.1s1.4k / 1.7k
CG-AL-X085hard1100.0 / 1007/7OK25.5s980 / 622
CG-AL-X086hard1100.0 / 1006/6OK31.5s1.4k / 1.1k
CG-AL-X087hard1100.0 / 1003/3OK28.3s1.0k / 821
CG-AL-X088hard1100.0 / 1006/6OK28.4s974 / 831
CG-AL-X089hard1100.0 / 10011/11OK40.7s1.1k / 1.3k
CG-AL-X090hard1100.0 / 10010/10OK43.2s889 / 1.1k
CG-AL-X091hard1100.0 / 1006/6OK24.5s569 / 286
CG-AL-X092hard1100.0 / 10015/15OK27.0s444 / 191
CG-AL-X093hard1100.0 / 10010/10OK32.7s989 / 741
CG-AL-X094hard1100.0 / 1007/7OK30.1s754 / 497
CG-AL-X095hard262.5 / 1003/5OK46.0s2.4k / 1.4k
CG-AL-X096hard1100.0 / 10049/49OK54.9s3.3k / 2.9k
CG-AL-X097hard1100.0 / 10046/46OK57.7s3.4k / 3.0k
CG-AL-X098hard1100.0 / 10029/29OK45.0s2.6k / 2.1k
CG-AL-X099hard1100.0 / 10039/39OK1m 3s3.6k / 3.4k
CG-AL-X100hard1100.0 / 10035/35OK59.7s3.5k / 3.0k
CG-AL-X101hard1100.0 / 10010/10OK50.1s1.1k / 810
CG-AL-X102hard1100.0 / 1008/8OK52.2s531 / 682
CG-AL-X103hard1100.0 / 1007/7OK46.0s725 / 458
CG-AL-X104hard1100.0 / 1006/6OK53.3s1.1k / 851
CG-AL-X105hard1100.0 / 1006/6OK49.6s777 / 448
CG-AL-X106hard1100.0 / 1005/5OK53.5s878 / 748
CG-AL-X107hard1100.0 / 1004/4OK49.3s805 / 605
CG-AL-X108hard1100.0 / 1006/6OK47.9s729 / 374
CG-AL-X109hard1100.0 / 1005/5OK47.2s548 / 332
CG-AL-X110hard1100.0 / 10017/17OK53.8s1.2k / 960
CG-AL-X111hard1100.0 / 1008/8OK42.3s1.2k / 1.2k
CG-AL-X112hard1100.0 / 10012/12OK37.3s906 / 951
CG-AL-X113hard1100.0 / 10013/13OK30.4s705 / 729
CG-AL-X114hard1100.0 / 1007/7OK26.4s718 / 413
CG-AL-X115hard1100.0 / 10013/13OK27.3s478 / 373
CG-AL-X116hard1100.0 / 10017/17OK29.2s926 / 684
CG-AL-X117hard1100.0 / 1008/8OK29.3s1.0k / 764
CG-AL-X118hard1100.0 / 10017/17OK33.0s1.4k / 1.1k
CG-AL-X119hard1100.0 / 10015/15OK36.2s1.7k / 1.6k
CG-AL-X120hard1100.0 / 10012/12OK29.7s1.2k / 1.0k
CG-AL-X121hard1100.0 / 1006/6OK30.9s1.0k / 792
CG-AL-X122hard1100.0 / 10010/10OK32.8s1.5k / 1.3k
CG-AL-X123hard1100.0 / 1005/5OK26.9s603 / 345
CG-AL-X124hard1100.0 / 10010/10OK31.1s994 / 782
CG-AL-X125hard1100.0 / 1008/8OK40.1s1.4k / 1.2k
CG-AL-X126hard1100.0 / 10014/14OK27.0s711 / 447
CG-AL-X127hard1100.0 / 1005/5OK29.3s666 / 539
CG-AL-X128hard1100.0 / 1008/8OK32.2s1.1k / 811
CG-AL-X129hard1100.0 / 10014/14OK34.7s1.2k / 1.0k
CG-AL-X130hard1100.0 / 1005/5OK24.5s529 / 345
CG-AL-X131hard1100.0 / 10013/13OK28.3s941 / 610
CG-AL-X132hard1100.0 / 10010/10OK26.8s709 / 410
CG-AL-X133hard20.0 / 1000/0FAIL1m 38s3.0k / 2.9k
CG-AL-X134hard1100.0 / 1006/6OK35.5s1.2k / 1.2k
CG-AL-X135hard1100.0 / 1004/4OK26.4s866 / 554
CG-AL-X136hard1100.0 / 1007/7OK24.8s754 / 324
CG-AL-X137hard1100.0 / 1004/4OK26.7s915 / 649
CG-AL-X138hard1100.0 / 1009/9OK36.2s1.4k / 1.3k
CG-AL-X139hard1100.0 / 10011/11OK33.6s1.6k / 1.4k
CG-AL-X140hard1100.0 / 1007/7OK1m 9s1.5k / 2.8k
CG-AL-X141hard1100.0 / 10039/39OK55.3s3.5k / 3.1k
CG-AL-X142hard1100.0 / 10048/48OK1m 35s4.0k / 4.8k
CG-AL-X143hard1100.0 / 10035/35OK1m 15s4.0k / 3.7k
CG-AL-X144hard1100.0 / 10043/43OK1m 4s3.6k / 3.3k
CG-AL-X145hard1100.0 / 10032/32OK1m 31s4.2k / 3.9k
CG-AL-X146hard1100.0 / 1009/9OK1m 38s1.7k / 2.2k
CG-AL-X147hard1100.0 / 1008/8OK1m 8s1.3k / 948
CG-AL-X148hard1100.0 / 1006/6OK1m 8s1.1k / 788
CG-AL-X149hard1100.0 / 1007/7OK1m 15s1.1k / 850
CG-AL-X150hard1100.0 / 1009/9OK1m 49s1.9k / 2.9k
CG-AL-X151hard1100.0 / 1006/6OK1m 14s818 / 511
CG-AL-X152hard1100.0 / 1008/8OK1m 21s1.1k / 731
CG-AL-X153hard1100.0 / 1009/9OK1m 28s888 / 921
CG-AL-X154hard1100.0 / 1009/9OK1m 29s1.2k / 1.0k
CG-AL-X155hard1100.0 / 10011/11OK60.0s923 / 700
CG-AL-X156hard1100.0 / 1007/7OK52.2s884 / 541
CG-AL-X157hard1100.0 / 10010/10OK58.8s1.3k / 917
CG-AL-X158hard1100.0 / 1007/7OK46.0s801 / 446
CG-AL-X159hard1100.0 / 1007/7OK49.4s849 / 600
CG-AL-X160hard1100.0 / 10013/13OK54.8s1.2k / 1.0k
CG-AL-X161hard1100.0 / 10010/10OK51.4s1.4k / 1.3k
CG-AL-X162hard1100.0 / 1007/7OK39.1s956 / 694
CG-AL-X163hard1100.0 / 1007/7OK38.2s1.0k / 713
CG-AL-X164hard1100.0 / 1007/7OK36.1s945 / 653
CG-AL-X165hard1100.0 / 10013/13OK1m 15s2.6k / 3.0k
CG-AL-X166hard1100.0 / 10014/14OK36.9s1.6k / 1.1k
CG-AL-X167hard1100.0 / 10013/13OK47.8s1.4k / 1.8k
CG-AL-X168hard1100.0 / 1009/9OK51.1s1.3k / 2.0k
CG-AL-X169hard1100.0 / 10011/11OK44.7s1.6k / 1.7k
CG-AL-X170hard1100.0 / 10011/11OK1m 9s3.1k / 2.9k
CG-AL-X171hard1100.0 / 1009/9OK1m 14s1.4k / 2.1k
CG-AL-X172hard1100.0 / 10011/11OK1m 22s2.2k / 2.8k
CG-AL-X173hard1100.0 / 10019/19OK1m 27s3.1k / 3.4k
CG-AL-X174hard1100.0 / 10016/16OK1m 38s3.9k / 4.1k
CG-AL-X185hard2100.0 / 10043/43OK1m 16s5.3k / 1.7k
CG-AL-X187hard262.5 / 10030/33OK1m 20s6.6k / 2.2k
CG-AL-X194hard2100.0 / 10050/50OK1m 9s10.0k / 3.7k
CG-AL-X211hard1100.0 / 10043/43OK1m 55s3.5k / 2.8k
CG-AL-X214hard262.5 / 10031/34OK1m 8s7.7k / 2.5k
CG-AL-X218hard20.0 / 1000/0FAIL1m 53s4.2k / 3.5k
CG-AL-X234hard1100.0 / 10035/35OK1m 43s3.7k / 1.8k
CG-AL-X239hard2100.0 / 10037/37OK1m 28s11k / 3.8k
CG-AL-X244hard262.5 / 10035/38OK1m 54s12k / 5.9k
CG-AL-X245hard1100.0 / 10063/63OK1m 51s4.3k / 2.0k
CG-AL-X248hard1100.0 / 10066/66OK1m 39s4.3k / 1.8k
CG-AL-X249hard2100.0 / 10037/37OK1m 46s9.5k / 3.7k
CG-AL-X254hard1100.0 / 10070/70OK1m 50s5.6k / 2.4k
CG-AL-X257hard2100.0 / 10053/53OK1m 39s8.7k / 3.1k
CG-AL-X263hard2100.0 / 10061/61OK1m 54s10.0k / 5.1k
CG-AL-X264hard1100.0 / 10065/65OK2m 19s4.9k / 4.0k
CG-AL-X270hard2100.0 / 10063/63OK1m 47s15k / 4.8k
CG-AL-X271hard2100.0 / 10070/70OK1m 54s16k / 5.9k
CG-AL-X272hard1100.0 / 10079/79OK1m 52s6.0k / 3.4k
CG-AL-X274hard2100.0 / 10064/64OK1m 36s12k / 5.5k
CG-AL-X276hard2100.0 / 10078/78OK1m 41s14k / 3.5k
CG-AL-X278hard2100.0 / 10071/71OK1m 27s13k / 5.3k
CG-AL-X283hard1100.0 / 10076/76OK2m 11s6.5k / 3.6k
CG-AL-X289hard1100.0 / 10057/57OK2m 41s5.0k / 4.3k
CG-AL-X290hard2100.0 / 10047/47OK1m 46s12k / 5.8k
CG-AL-X292hard1100.0 / 10057/57OK2m 0s4.8k / 1.7k
CG-AL-X293hard1100.0 / 10049/49OK2m 8s4.3k / 2.7k
CG-AL-X296hard1100.0 / 10047/47OK2m 56s6.6k / 5.1k
CG-AL-X298hard1100.0 / 10055/55OK1m 53s4.4k / 1.8k