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.

84.5% 196/232 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.

74.9 / 100
Cost $8.08
Tokens 626k / 566k input / output, all attempts
Duration 57m 17s
Filter:
Per-task results for run 7b948839-87e1-42f5-8a7d-20ca5671bfd4
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.2s258 / 188
CG-AL-E006easy1100.0 / 1007/7OK31.8s305 / 770
CG-AL-E010easy1100.0 / 1005/5OK17.8s280 / 90
CG-AL-E050easy20.0 / 1000/0FAIL8.8s1.8k / 2.5k
CG-AL-E052easy1100.0 / 10016/16OK11.4s352 / 208
CG-AL-E054easy20.0 / 1000/0FAIL9.0s963 / 1.1k
CG-AL-E056easy2100.0 / 10015/15OK16.1s1.7k / 1.4k
CG-AL-H007hard1100.0 / 10011/11OK11.3s545 / 974
CG-AL-H011hard20.0 / 1000/0FAIL3.7s1.1k / 692
CG-AL-H014hard20.0 / 1000/0FAIL4.0s1.6k / 1.6k
CG-AL-H017hard262.5 / 1000/5OK11.0s972 / 2.4k
CG-AL-H020hard2100.0 / 10010/10OK11.0s2.1k / 3.4k
CG-AL-H021hard262.5 / 1006/20OK11.5s1.8k / 1.7k
CG-AL-H023hard262.5 / 10022/25OK11.3s6.3k / 12k
CG-AL-H027hard2100.0 / 1004/4OK11.2s2.1k / 1.0k
CG-AL-H029hard262.5 / 10017/18OK11.2s2.5k / 4.1k
CG-AL-H030hard262.5 / 1008/10OK10.9s2.0k / 3.8k
CG-AL-H031hard1100.0 / 10022/22OK14.9s939 / 3.0k
CG-AL-H034hard1100.0 / 1003/3OK13.4s431 / 634
CG-AL-H036hard20.0 / 1000/0FAIL3.8s911 / 2.6k
CG-AL-H037hard10.0 / 1000/0FAIL4.1s497 / 1.5k
CG-AL-H041hard2100.0 / 1003/3OK10.9s1.7k / 3.6k
CG-AL-H050hard262.5 / 1002/3OK10.9s1.4k / 2.4k
CG-AL-H054hard20.0 / 1000/0FAIL3.8s1.8k / 835
CG-AL-H056hard20.0 / 1000/0FAIL3.8s1.4k / 517
CG-AL-M001medium20.0 / 1000/0FAIL4.0s1.5k / 3.3k
CG-AL-M003medium1100.0 / 1009/9OK12.0s419 / 1.8k
CG-AL-M004medium1100.0 / 10012/12OK29.2s449 / 1.9k
CG-AL-M006medium1100.0 / 10018/18OK11.7s408 / 5.2k
CG-AL-M007medium20.0 / 1000/0FAIL3.7s3.4k / 8.0k
CG-AL-M008medium2100.0 / 10012/12OK12.1s4.2k / 10k
CG-AL-M009medium2100.0 / 10011/11OK10.6s5.1k / 12k
CG-AL-M010medium1100.0 / 10021/21OK27.3s596 / 3.4k
CG-AL-M020medium2100.0 / 10017/17OK15.7s2.0k / 4.7k
CG-AL-M023medium1100.0 / 10011/11OK13.9s482 / 942
CG-AL-M025medium2100.0 / 1008/8OK10.9s2.9k / 1.3k
CG-AL-M026medium1100.0 / 1008/8OK11.3s370 / 2.1k
CG-AL-M027medium20.0 / 1000/0FAIL3.8s3.6k / 4.6k
CG-AL-M028medium211.1 / 1000/0FAIL3.9s1.0k / 1.2k
CG-AL-M031medium2100.0 / 1002/2OK11.4s2.0k / 2.4k
CG-AL-M034medium2100.0 / 1002/2OK11.0s1.3k / 335
CG-AL-M036medium211.1 / 1000/0FAIL3.7s1.4k / 864
CG-AL-M040medium2100.0 / 1002/2OK10.6s781 / 1.8k
CG-AL-M042medium1100.0 / 1008/8OK11.6s498 / 1.2k
CG-AL-X001hard1100.0 / 1002/2OK10.9s308 / 398
CG-AL-X002hard1100.0 / 1004/4OK10.7s488 / 2.8k
CG-AL-X003hard20.0 / 1000/0FAIL3.9s651 / 3.2k
CG-AL-X004medium1100.0 / 1003/3OK11.6s358 / 217
CG-AL-X005hard1100.0 / 1002/2OK12.5s327 / 159
CG-AL-X006hard1100.0 / 1003/3OK10.7s383 / 193
CG-AL-X007hard1100.0 / 1002/2OK1m 28s372 / 1.1k
CG-AL-X008hard1100.0 / 1001/1OK11.5s417 / 2.0k
CG-AL-X009medium1100.0 / 1002/2OK10.6s313 / 112
CG-AL-X010medium1100.0 / 1003/3OK10.7s284 / 94
CG-AL-X011medium1100.0 / 1002/2OK10.6s360 / 153
CG-AL-X012hard1100.0 / 1001/1OK10.5s380 / 1.0k
CG-AL-X013hard1100.0 / 1002/2OK10.8s263 / 227
CG-AL-X014medium1100.0 / 1004/4OK10.9s291 / 84
CG-AL-X017medium2100.0 / 1003/3OK10.4s1.4k / 501
CG-AL-X018medium1100.0 / 1003/3OK10.9s384 / 583
CG-AL-X019medium2100.0 / 1003/3OK10.8s1.8k / 871
CG-AL-X022medium2100.0 / 1003/3OK10.6s1.3k / 809
CG-AL-X024medium1100.0 / 1003/3OK10.9s333 / 307
CG-AL-X025medium2100.0 / 1001/1OK10.7s1.1k / 579
CG-AL-X026medium1100.0 / 1003/3OK11.1s327 / 132
CG-AL-X027medium2100.0 / 1004/4OK11.1s711 / 322
CG-AL-X029medium1100.0 / 1002/2OK10.5s276 / 667
CG-AL-X030medium1100.0 / 1002/2OK10.5s239 / 58
CG-AL-X031medium1100.0 / 1003/3OK11.1s297 / 107
CG-AL-X033hard1100.0 / 1002/2OK10.7s348 / 110
CG-AL-X034hard2100.0 / 1003/3OK11.4s1.5k / 154
CG-AL-X035hard262.5 / 1000/3OK10.6s1.5k / 2.0k
CG-AL-X037hard2100.0 / 1004/4OK10.9s2.1k / 3.4k
CG-AL-X040hard20.0 / 1000/0FAIL4.0s1.4k / 5.0k
CG-AL-X041hard1100.0 / 1005/5OK11.6s446 / 1.2k
CG-AL-X043hard2100.0 / 1001/1OK11.0s1.4k / 3.9k
CG-AL-X044hard262.5 / 1001/3OK11.1s1.5k / 5.6k
CG-AL-X045hard1100.0 / 1003/3OK10.9s371 / 363
CG-AL-X046hard1100.0 / 1002/2OK11.0s369 / 601
CG-AL-X047hard2100.0 / 1002/2OK11.1s1.2k / 4.1k
CG-AL-X050hard1100.0 / 1002/2OK11.2s405 / 527
CG-AL-X051hard1100.0 / 1002/2OK11.3s509 / 779
CG-AL-X052hard1100.0 / 1003/3OK11.8s358 / 677
CG-AL-X055hard1100.0 / 1005/5OK11.0s344 / 714
CG-AL-X056hard1100.0 / 1005/5OK11.8s280 / 580
CG-AL-X057hard1100.0 / 1005/5OK11.0s250 / 83
CG-AL-X058hard1100.0 / 1005/5OK11.3s314 / 215
CG-AL-X059hard1100.0 / 1003/3OK10.6s327 / 63
CG-AL-X060hard1100.0 / 1003/3OK10.9s302 / 73
CG-AL-X061hard1100.0 / 1004/4OK11.8s364 / 104
CG-AL-X062hard1100.0 / 1004/4OK10.9s358 / 588
CG-AL-X063hard1100.0 / 1003/3OK11.8s360 / 699
CG-AL-X064hard1100.0 / 1007/7OK10.7s277 / 625
CG-AL-X065hard1100.0 / 1006/6OK11.1s709 / 681
CG-AL-X066hard1100.0 / 10014/14OK11.8s1.2k / 1.1k
CG-AL-X067hard262.5 / 1006/7OK10.7s1.6k / 4.5k
CG-AL-X068hard1100.0 / 10012/12OK11.3s1.2k / 1.0k
CG-AL-X069hard1100.0 / 1008/8OK14.0s1.1k / 3.5k
CG-AL-X070hard1100.0 / 10012/12OK11.5s1.2k / 1.2k
CG-AL-X071hard1100.0 / 1008/8OK12.0s1.4k / 1.1k
CG-AL-X072hard1100.0 / 1007/7OK10.6s1.1k / 807
CG-AL-X073hard1100.0 / 1008/8OK11.1s1.4k / 1.3k
CG-AL-X074hard2100.0 / 1007/7OK11.1s3.4k / 5.3k
CG-AL-X075hard1100.0 / 1007/7OK11.1s810 / 1.2k
CG-AL-X076hard1100.0 / 10014/14OK11.6s954 / 1.9k
CG-AL-X077hard1100.0 / 10022/22OK10.8s1.5k / 1.3k
CG-AL-X078hard1100.0 / 10017/17OK11.3s1.2k / 905
CG-AL-X079hard1100.0 / 10011/11OK11.1s1.2k / 3.6k
CG-AL-X080hard20.0 / 1000/0FAIL3.9s2.4k / 2.1k
CG-AL-X081hard1100.0 / 1008/8OK11.2s902 / 564
CG-AL-X082hard1100.0 / 10015/15OK10.7s1.2k / 963
CG-AL-X083hard1100.0 / 1009/9OK11.5s1.5k / 1.2k
CG-AL-X084hard1100.0 / 10010/10OK11.4s1.4k / 3.8k
CG-AL-X085hard1100.0 / 1007/7OK10.7s980 / 629
CG-AL-X086hard1100.0 / 1006/6OK10.6s1.4k / 1.6k
CG-AL-X087hard1100.0 / 1003/3OK11.3s1.0k / 830
CG-AL-X088hard1100.0 / 1006/6OK11.5s974 / 969
CG-AL-X089hard1100.0 / 10011/11OK11.3s1.1k / 3.4k
CG-AL-X090hard1100.0 / 10010/10OK11.7s889 / 3.5k
CG-AL-X091hard1100.0 / 1006/6OK11.1s569 / 286
CG-AL-X092hard1100.0 / 10015/15OK10.5s444 / 376
CG-AL-X093hard1100.0 / 10010/10OK10.6s989 / 914
CG-AL-X094hard1100.0 / 1007/7OK10.8s754 / 605
CG-AL-X095hard262.5 / 1003/5OK11.0s2.1k / 3.5k
CG-AL-X096hard1100.0 / 10049/49OK11.7s3.3k / 3.1k
CG-AL-X097hard1100.0 / 10046/46OK12.0s3.4k / 3.1k
CG-AL-X098hard1100.0 / 10029/29OK11.6s2.6k / 2.2k
CG-AL-X099hard1100.0 / 10039/39OK12.9s3.6k / 3.8k
CG-AL-X100hard1100.0 / 10035/35OK11.8s3.5k / 3.2k
CG-AL-X101hard1100.0 / 10010/10OK11.5s1.1k / 1.3k
CG-AL-X102hard1100.0 / 1008/8OK10.6s531 / 1.9k
CG-AL-X103hard1100.0 / 1007/7OK11.2s725 / 426
CG-AL-X104hard1100.0 / 1006/6OK10.9s1.1k / 851
CG-AL-X105hard1100.0 / 1006/6OK10.8s777 / 448
CG-AL-X106hard1100.0 / 1005/5OK10.9s878 / 800
CG-AL-X107hard1100.0 / 1004/4OK10.5s805 / 589
CG-AL-X108hard1100.0 / 1006/6OK11.3s729 / 446
CG-AL-X109hard1100.0 / 1005/5OK11.0s548 / 379
CG-AL-X110hard1100.0 / 10017/17OK11.2s1.2k / 1.0k
CG-AL-X111hard1100.0 / 1008/8OK10.9s1.2k / 3.5k
CG-AL-X112hard2100.0 / 10012/12OK11.0s2.6k / 3.5k
CG-AL-X113hard1100.0 / 10013/13OK11.3s705 / 1.5k
CG-AL-X114hard1100.0 / 1007/7OK12.8s718 / 469
CG-AL-X115hard2100.0 / 10013/13OK12.0s1.2k / 1.1k
CG-AL-X116hard1100.0 / 10017/17OK11.1s926 / 1.4k
CG-AL-X117hard1100.0 / 1008/8OK11.0s1.0k / 923
CG-AL-X118hard1100.0 / 10017/17OK11.3s1.4k / 1.3k
CG-AL-X119hard1100.0 / 10015/15OK11.1s1.7k / 1.6k
CG-AL-X120hard1100.0 / 10012/12OK10.9s1.2k / 1.1k
CG-AL-X121hard1100.0 / 1006/6OK10.6s1.0k / 882
CG-AL-X122hard1100.0 / 10010/10OK12.9s1.5k / 1.6k
CG-AL-X123hard1100.0 / 1005/5OK10.5s603 / 518
CG-AL-X124hard1100.0 / 10010/10OK11.0s994 / 690
CG-AL-X125hard1100.0 / 1008/8OK10.7s1.4k / 1.4k
CG-AL-X126hard1100.0 / 10014/14OK10.7s711 / 710
CG-AL-X127hard1100.0 / 1005/5OK11.3s666 / 360
CG-AL-X128hard1100.0 / 1008/8OK10.7s1.1k / 861
CG-AL-X129hard1100.0 / 10014/14OK10.9s1.2k / 1.1k
CG-AL-X130hard2100.0 / 1005/5OK10.7s1.1k / 981
CG-AL-X131hard1100.0 / 10013/13OK10.6s941 / 677
CG-AL-X132hard1100.0 / 10010/10OK10.5s709 / 410
CG-AL-X133hard20.0 / 1000/0FAIL3.8s3.3k / 5.4k
CG-AL-X134hard1100.0 / 1006/6OK11.2s1.2k / 1.8k
CG-AL-X135hard1100.0 / 1004/4OK10.7s866 / 629
CG-AL-X136hard1100.0 / 1007/7OK10.6s754 / 474
CG-AL-X137hard1100.0 / 1004/4OK11.0s915 / 980
CG-AL-X138hard1100.0 / 1009/9OK10.9s1.4k / 2.1k
CG-AL-X139hard1100.0 / 10011/11OK11.0s1.6k / 1.5k
CG-AL-X140hard2100.0 / 1007/7OK10.9s4.1k / 7.8k
CG-AL-X141hard2100.0 / 10039/39OK11.9s8.4k / 6.8k
CG-AL-X142hard262.5 / 10044/48OK16.9s9.0k / 9.5k
CG-AL-X143hard1100.0 / 10035/35OK16.2s4.0k / 3.4k
CG-AL-X144hard1100.0 / 10043/43OK11.1s3.6k / 3.1k
CG-AL-X145hard1100.0 / 10032/32OK11.5s4.2k / 3.9k
CG-AL-X146hard1100.0 / 1009/9OK11.1s1.7k / 3.1k
CG-AL-X147hard1100.0 / 1008/8OK10.9s1.3k / 914
CG-AL-X148hard1100.0 / 1006/6OK10.9s1.1k / 788
CG-AL-X149hard1100.0 / 1007/7OK10.7s1.1k / 1.0k
CG-AL-X150hard1100.0 / 1009/9OK10.9s1.9k / 3.9k
CG-AL-X151hard1100.0 / 1006/6OK10.6s818 / 511
CG-AL-X152hard1100.0 / 1008/8OK10.7s1.1k / 754
CG-AL-X153hard1100.0 / 1009/9OK14.8s888 / 1.6k
CG-AL-X154hard1100.0 / 1009/9OK11.0s1.2k / 1.1k
CG-AL-X155hard1100.0 / 10011/11OK11.3s923 / 759
CG-AL-X156hard1100.0 / 1007/7OK10.6s884 / 541
CG-AL-X157hard1100.0 / 10010/10OK11.0s1.3k / 981
CG-AL-X158hard1100.0 / 1007/7OK10.9s801 / 415
CG-AL-X159hard1100.0 / 1007/7OK10.8s849 / 580
CG-AL-X160hard1100.0 / 10013/13OK10.9s1.2k / 1.2k
CG-AL-X161hard1100.0 / 10010/10OK11.0s1.4k / 1.3k
CG-AL-X162hard1100.0 / 1007/7OK10.7s956 / 775
CG-AL-X163hard1100.0 / 1007/7OK12.5s1.0k / 770
CG-AL-X164hard1100.0 / 1007/7OK13.2s945 / 775
CG-AL-X165hard2100.0 / 10013/13OK13.4s6.0k / 7.3k
CG-AL-X166hard1100.0 / 10014/14OK11.9s1.6k / 1.5k
CG-AL-X167hard20.0 / 1000/0FAIL4.2s1.8k / 3.5k
CG-AL-X168hard2100.0 / 1009/9OK14.6s3.4k / 4.7k
CG-AL-X169hard2100.0 / 10011/11OK12.3s3.8k / 3.9k
CG-AL-X170hard1100.0 / 10011/11OK11.0s3.1k / 5.2k
CG-AL-X171hard1100.0 / 1009/9OK11.7s1.4k / 3.6k
CG-AL-X172hard2100.0 / 10011/11OK14.1s5.4k / 6.7k
CG-AL-X173hard1100.0 / 10019/19OK12.3s3.1k / 4.7k
CG-AL-X174hard2100.0 / 10016/16OK11.4s8.3k / 8.3k
CG-AL-X185hard262.5 / 10041/43OK11.5s6.9k / 3.3k
CG-AL-X187hard262.5 / 10030/33OK12.2s6.8k / 3.1k
CG-AL-X194hard2100.0 / 10050/50OK11.5s9.9k / 4.6k
CG-AL-X211hard2100.0 / 10043/43OK11.8s9.4k / 6.7k
CG-AL-X214hard2100.0 / 10034/34OK11.3s7.9k / 4.2k
CG-AL-X218hard2100.0 / 10027/27OK11.4s7.8k / 4.4k
CG-AL-X234hard2100.0 / 10035/35OK11.5s11k / 6.2k
CG-AL-X239hard2100.0 / 10037/37OK11.7s11k / 6.6k
CG-AL-X244hard2100.0 / 10038/38OK11.9s11k / 8.2k
CG-AL-X245hard2100.0 / 10063/63OK12.6s9.8k / 3.8k
CG-AL-X248hard2100.0 / 10066/66OK12.9s9.8k / 4.1k
CG-AL-X249hard2100.0 / 10037/37OK12.4s11k / 6.7k
CG-AL-X254hard262.5 / 10064/70OK12.7s15k / 6.4k
CG-AL-X257hard20.0 / 1000/0FAIL4.2s9.8k / 6.4k
CG-AL-X263hard2100.0 / 10061/61OK12.6s13k / 8.2k
CG-AL-X264hard2100.0 / 10065/65OK11.6s12k / 5.3k
CG-AL-X270hard2100.0 / 10063/63OK12.3s18k / 8.0k
CG-AL-X271hard2100.0 / 10070/70OK12.4s17k / 9.0k
CG-AL-X272hard2100.0 / 10079/79OK12.4s13k / 5.9k
CG-AL-X274hard2100.0 / 10064/64OK12.1s14k / 6.3k
CG-AL-X276hard262.5 / 10076/78OK12.9s19k / 8.8k
CG-AL-X278hard2100.0 / 10071/71OK13.7s15k / 6.7k
CG-AL-X283hard2100.0 / 10076/76OK13.4s15k / 6.2k
CG-AL-X289hard262.5 / 10047/57OK13.9s10k / 6.5k
CG-AL-X290hard2100.0 / 10047/47OK12.7s12k / 5.3k
CG-AL-X292hard2100.0 / 10057/57OK11.9s16k / 4.4k
CG-AL-X293hard2100.0 / 10049/49OK11.6s10k / 4.5k
CG-AL-X296hard262.5 / 10046/47OK11.8s13k / 10.0k
CG-AL-X298hard1100.0 / 10055/55OK12.0s4.4k / 4.1k