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.

85.8% 199/232 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.

76.0 / 100
Cost $8.35
Tokens 648k / 586k input / output, all attempts
Duration 59m 26s
Filter:
Per-task results for run af415c12-e427-4f71-9d44-22425f2b1c0c
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.8s258 / 188
CG-AL-E006easy2100.0 / 1007/7OK31.5s951 / 1.1k
CG-AL-E010easy1100.0 / 1005/5OK17.7s280 / 92
CG-AL-E050easy20.0 / 1000/0FAIL9.8s1.8k / 1.3k
CG-AL-E052easy1100.0 / 10016/16OK10.7s352 / 213
CG-AL-E054easy20.0 / 1000/0FAIL9.8s963 / 672
CG-AL-E056easy2100.0 / 10015/15OK11.5s1.7k / 1.3k
CG-AL-H007hard2100.0 / 10011/11OK11.3s1.8k / 1.5k
CG-AL-H011hard20.0 / 1000/0FAIL3.6s909 / 841
CG-AL-H014hard20.0 / 1000/0FAIL4.0s1.5k / 1.4k
CG-AL-H017hard1100.0 / 1005/5OK10.8s357 / 1.3k
CG-AL-H020hard2100.0 / 10010/10OK11.5s2.2k / 3.9k
CG-AL-H021hard262.5 / 1006/20OK11.1s1.9k / 1.9k
CG-AL-H023hard2100.0 / 10025/25OK11.3s6.2k / 11k
CG-AL-H027hard262.5 / 1002/4OK11.3s2.1k / 716
CG-AL-H029hard2100.0 / 10018/18OK10.9s2.8k / 5.3k
CG-AL-H030hard262.5 / 1008/10OK10.9s2.1k / 4.0k
CG-AL-H031hard1100.0 / 10022/22OK10.8s939 / 3.5k
CG-AL-H034hard2100.0 / 1003/3OK11.2s1.3k / 485
CG-AL-H036hard20.0 / 1000/0FAIL3.7s926 / 2.0k
CG-AL-H037hard10.0 / 1000/0FAIL4.2s497 / 1.3k
CG-AL-H041hard2100.0 / 1003/3OK11.1s1.6k / 2.6k
CG-AL-H050hard262.5 / 1002/3OK10.8s1.4k / 2.9k
CG-AL-H054hard20.0 / 1000/0FAIL3.8s1.8k / 1.2k
CG-AL-H056hard20.0 / 1000/0FAIL3.9s1.4k / 807
CG-AL-M001medium20.0 / 1000/0FAIL4.0s1.5k / 3.0k
CG-AL-M003medium1100.0 / 1009/9OK11.5s419 / 2.8k
CG-AL-M004medium2100.0 / 10012/12OK28.1s1.9k / 3.9k
CG-AL-M006medium20.0 / 1000/0FAIL3.6s2.8k / 5.8k
CG-AL-M007medium262.5 / 10013/15OK11.7s4.2k / 11k
CG-AL-M008medium262.5 / 10011/12OK11.4s4.9k / 12k
CG-AL-M009medium20.0 / 1000/0FAIL3.9s3.9k / 9.4k
CG-AL-M010medium1100.0 / 10021/21OK24.9s596 / 4.5k
CG-AL-M020medium2100.0 / 10017/17OK10.5s2.1k / 3.0k
CG-AL-M023medium1100.0 / 10011/11OK16.9s482 / 1.4k
CG-AL-M025medium2100.0 / 1008/8OK10.7s2.8k / 1.5k
CG-AL-M026medium1100.0 / 1008/8OK11.2s370 / 2.1k
CG-AL-M027medium2100.0 / 10018/18OK15.8s3.5k / 3.0k
CG-AL-M028medium211.1 / 1000/0FAIL3.8s1.0k / 1.2k
CG-AL-M031medium2100.0 / 1002/2OK10.7s2.0k / 2.1k
CG-AL-M034medium1100.0 / 1002/2OK11.0s415 / 181
CG-AL-M036medium211.1 / 1000/0FAIL4.0s1.4k / 474
CG-AL-M040medium2100.0 / 1002/2OK10.6s769 / 1.6k
CG-AL-M042medium1100.0 / 1008/8OK10.9s498 / 401
CG-AL-X001hard1100.0 / 1002/2OK11.1s308 / 618
CG-AL-X002hard1100.0 / 1004/4OK11.0s488 / 2.9k
CG-AL-X003hard262.5 / 1002/3OK10.6s648 / 1.1k
CG-AL-X004medium1100.0 / 1003/3OK11.1s358 / 217
CG-AL-X005hard1100.0 / 1002/2OK10.6s327 / 156
CG-AL-X006hard1100.0 / 1003/3OK11.1s383 / 193
CG-AL-X007hard1100.0 / 1002/2OK1m 44s372 / 1.1k
CG-AL-X008hard2100.0 / 1001/1OK10.9s1.3k / 3.1k
CG-AL-X009medium1100.0 / 1002/2OK11.3s313 / 112
CG-AL-X010medium1100.0 / 1003/3OK11.0s284 / 94
CG-AL-X011medium1100.0 / 1002/2OK10.7s360 / 130
CG-AL-X012hard1100.0 / 1001/1OK10.8s380 / 1.1k
CG-AL-X013hard1100.0 / 1002/2OK10.6s263 / 304
CG-AL-X014medium1100.0 / 1004/4OK11.1s291 / 83
CG-AL-X017medium2100.0 / 1003/3OK10.6s1.4k / 464
CG-AL-X018medium1100.0 / 1003/3OK11.2s384 / 441
CG-AL-X019medium1100.0 / 1003/3OK10.9s365 / 171
CG-AL-X022medium2100.0 / 1003/3OK10.7s1.3k / 741
CG-AL-X024medium1100.0 / 1003/3OK11.1s333 / 341
CG-AL-X025medium2100.0 / 1001/1OK10.7s1.1k / 734
CG-AL-X026medium1100.0 / 1003/3OK11.3s327 / 104
CG-AL-X027medium2100.0 / 1004/4OK10.3s710 / 322
CG-AL-X029medium1100.0 / 1002/2OK10.7s276 / 450
CG-AL-X030medium1100.0 / 1002/2OK11.8s239 / 68
CG-AL-X031medium1100.0 / 1003/3OK11.4s297 / 116
CG-AL-X033hard1100.0 / 1002/2OK12.0s348 / 110
CG-AL-X034hard1100.0 / 1003/3OK10.9s304 / 647
CG-AL-X035hard2100.0 / 1003/3OK12.2s1.6k / 1.2k
CG-AL-X037hard262.5 / 1000/4OK11.3s2.1k / 4.8k
CG-AL-X040hard20.0 / 1000/0FAIL4.4s1.4k / 4.1k
CG-AL-X041hard2100.0 / 1005/5OK11.4s2.5k / 4.0k
CG-AL-X043hard2100.0 / 1001/1OK11.9s1.5k / 5.1k
CG-AL-X044hard262.5 / 1000/3OK12.4s1.5k / 5.4k
CG-AL-X045hard1100.0 / 1003/3OK10.6s371 / 469
CG-AL-X046hard1100.0 / 1002/2OK12.3s369 / 550
CG-AL-X047hard1100.0 / 1002/2OK11.2s390 / 3.1k
CG-AL-X050hard1100.0 / 1002/2OK11.2s405 / 577
CG-AL-X051hard1100.0 / 1002/2OK11.1s509 / 759
CG-AL-X052hard1100.0 / 1003/3OK11.1s358 / 484
CG-AL-X055hard1100.0 / 1005/5OK10.7s344 / 214
CG-AL-X056hard1100.0 / 1005/5OK10.6s280 / 913
CG-AL-X057hard1100.0 / 1005/5OK10.4s250 / 275
CG-AL-X058hard1100.0 / 1005/5OK11.0s314 / 1.9k
CG-AL-X059hard1100.0 / 1003/3OK10.9s327 / 63
CG-AL-X060hard1100.0 / 1003/3OK10.9s302 / 536
CG-AL-X061hard1100.0 / 1004/4OK11.2s364 / 104
CG-AL-X062hard1100.0 / 1004/4OK11.2s358 / 761
CG-AL-X063hard1100.0 / 1003/3OK11.4s360 / 657
CG-AL-X064hard2100.0 / 1007/7OK11.4s791 / 294
CG-AL-X065hard1100.0 / 1006/6OK10.9s709 / 711
CG-AL-X066hard1100.0 / 10014/14OK11.0s1.2k / 1.3k
CG-AL-X067hard262.5 / 1006/7OK10.5s1.6k / 3.9k
CG-AL-X068hard1100.0 / 10012/12OK10.9s1.2k / 1.1k
CG-AL-X069hard1100.0 / 1008/8OK11.0s1.1k / 3.1k
CG-AL-X070hard1100.0 / 10012/12OK10.9s1.2k / 854
CG-AL-X071hard1100.0 / 1008/8OK10.9s1.4k / 1.1k
CG-AL-X072hard1100.0 / 1007/7OK10.8s1.1k / 818
CG-AL-X073hard1100.0 / 1008/8OK11.2s1.4k / 1.3k
CG-AL-X074hard2100.0 / 1007/7OK10.9s3.4k / 4.9k
CG-AL-X075hard1100.0 / 1007/7OK11.2s810 / 1.4k
CG-AL-X076hard1100.0 / 10014/14OK11.2s954 / 900
CG-AL-X077hard1100.0 / 10022/22OK11.0s1.5k / 1.2k
CG-AL-X078hard1100.0 / 10017/17OK11.0s1.2k / 905
CG-AL-X079hard1100.0 / 10011/11OK11.3s1.2k / 4.0k
CG-AL-X080hard20.0 / 1000/0FAIL4.1s2.4k / 2.3k
CG-AL-X081hard1100.0 / 1008/8OK11.0s902 / 564
CG-AL-X082hard1100.0 / 10015/15OK11.1s1.2k / 920
CG-AL-X083hard1100.0 / 1009/9OK10.8s1.5k / 1.2k
CG-AL-X084hard1100.0 / 10010/10OK11.4s1.4k / 2.8k
CG-AL-X085hard1100.0 / 1007/7OK11.0s980 / 613
CG-AL-X086hard1100.0 / 1006/6OK10.7s1.4k / 1.5k
CG-AL-X087hard1100.0 / 1003/3OK10.8s1.0k / 928
CG-AL-X088hard1100.0 / 1006/6OK11.1s974 / 1.1k
CG-AL-X089hard1100.0 / 10011/11OK11.1s1.1k / 2.4k
CG-AL-X090hard1100.0 / 10010/10OK11.3s889 / 3.5k
CG-AL-X091hard1100.0 / 1006/6OK11.2s569 / 286
CG-AL-X092hard1100.0 / 10015/15OK10.7s444 / 465
CG-AL-X093hard1100.0 / 10010/10OK10.7s989 / 838
CG-AL-X094hard1100.0 / 1007/7OK11.2s754 / 588
CG-AL-X095hard262.5 / 1003/5OK10.7s2.1k / 2.2k
CG-AL-X096hard1100.0 / 10049/49OK11.4s3.3k / 2.9k
CG-AL-X097hard1100.0 / 10046/46OK11.6s3.4k / 3.1k
CG-AL-X098hard1100.0 / 10029/29OK11.5s2.6k / 2.2k
CG-AL-X099hard1100.0 / 10039/39OK13.0s3.6k / 3.6k
CG-AL-X100hard1100.0 / 10035/35OK12.1s3.5k / 3.5k
CG-AL-X101hard1100.0 / 10010/10OK12.2s1.1k / 939
CG-AL-X102hard2100.0 / 1008/8OK11.3s2.3k / 2.6k
CG-AL-X103hard1100.0 / 1007/7OK12.3s725 / 426
CG-AL-X104hard1100.0 / 1006/6OK12.7s1.1k / 890
CG-AL-X105hard1100.0 / 1006/6OK12.8s777 / 448
CG-AL-X106hard1100.0 / 1005/5OK13.9s878 / 852
CG-AL-X107hard1100.0 / 1004/4OK13.0s805 / 589
CG-AL-X108hard1100.0 / 1006/6OK14.1s729 / 349
CG-AL-X109hard1100.0 / 1005/5OK12.2s548 / 438
CG-AL-X110hard1100.0 / 10017/17OK12.6s1.2k / 994
CG-AL-X111hard1100.0 / 1008/8OK13.2s1.2k / 2.4k
CG-AL-X112hard1100.0 / 10012/12OK12.4s906 / 2.2k
CG-AL-X113hard1100.0 / 10013/13OK12.5s705 / 2.2k
CG-AL-X114hard1100.0 / 1007/7OK11.7s718 / 471
CG-AL-X115hard1100.0 / 10013/13OK11.4s478 / 497
CG-AL-X116hard1100.0 / 10017/17OK11.3s926 / 2.1k
CG-AL-X117hard1100.0 / 1008/8OK11.5s1.0k / 982
CG-AL-X118hard1100.0 / 10017/17OK11.7s1.4k / 1.2k
CG-AL-X119hard1100.0 / 10015/15OK13.0s1.7k / 1.6k
CG-AL-X120hard1100.0 / 10012/12OK11.9s1.2k / 1.1k
CG-AL-X121hard1100.0 / 1006/6OK11.8s1.0k / 875
CG-AL-X122hard1100.0 / 10010/10OK11.3s1.5k / 1.4k
CG-AL-X123hard1100.0 / 1005/5OK10.9s603 / 361
CG-AL-X124hard1100.0 / 10010/10OK11.7s994 / 888
CG-AL-X125hard1100.0 / 1008/8OK11.8s1.4k / 1.0k
CG-AL-X126hard2100.0 / 10014/14OK10.4s3.4k / 2.2k
CG-AL-X127hard1100.0 / 1005/5OK11.2s666 / 419
CG-AL-X128hard1100.0 / 1008/8OK10.9s1.1k / 811
CG-AL-X129hard1100.0 / 10014/14OK11.0s1.2k / 1.0k
CG-AL-X130hard2100.0 / 1005/5OK10.5s1.1k / 1.8k
CG-AL-X131hard1100.0 / 10013/13OK11.2s941 / 663
CG-AL-X132hard1100.0 / 10010/10OK11.0s709 / 410
CG-AL-X133hard2100.0 / 1008/8OK10.6s3.4k / 7.0k
CG-AL-X134hard1100.0 / 1006/6OK11.4s1.2k / 1.1k
CG-AL-X135hard1100.0 / 1004/4OK10.7s866 / 630
CG-AL-X136hard1100.0 / 1007/7OK10.8s754 / 604
CG-AL-X137hard1100.0 / 1004/4OK11.0s915 / 779
CG-AL-X138hard1100.0 / 1009/9OK10.9s1.4k / 1.8k
CG-AL-X139hard1100.0 / 10011/11OK11.8s1.6k / 1.4k
CG-AL-X140hard2100.0 / 1007/7OK10.9s4.2k / 8.1k
CG-AL-X141hard2100.0 / 10039/39OK11.6s8.3k / 6.6k
CG-AL-X142hard2100.0 / 10048/48OK11.5s8.8k / 9.6k
CG-AL-X143hard1100.0 / 10035/35OK16.1s4.0k / 3.3k
CG-AL-X144hard1100.0 / 10043/43OK11.7s3.6k / 3.2k
CG-AL-X145hard1100.0 / 10032/32OK11.8s4.2k / 3.9k
CG-AL-X146hard1100.0 / 1009/9OK11.2s1.7k / 3.6k
CG-AL-X147hard1100.0 / 1008/8OK11.1s1.3k / 948
CG-AL-X148hard1100.0 / 1006/6OK11.2s1.1k / 788
CG-AL-X149hard1100.0 / 1007/7OK11.2s1.1k / 918
CG-AL-X150hard1100.0 / 1009/9OK11.6s1.9k / 4.4k
CG-AL-X151hard1100.0 / 1006/6OK10.8s818 / 511
CG-AL-X152hard1100.0 / 1008/8OK10.9s1.1k / 890
CG-AL-X153hard2100.0 / 1009/9OK19.4s2.6k / 4.3k
CG-AL-X154hard1100.0 / 1009/9OK10.9s1.2k / 970
CG-AL-X155hard1100.0 / 10011/11OK11.1s923 / 787
CG-AL-X156hard1100.0 / 1007/7OK11.1s884 / 541
CG-AL-X157hard1100.0 / 10010/10OK11.0s1.3k / 978
CG-AL-X158hard1100.0 / 1007/7OK11.4s801 / 446
CG-AL-X159hard1100.0 / 1007/7OK11.6s849 / 771
CG-AL-X160hard1100.0 / 10013/13OK10.9s1.2k / 1.2k
CG-AL-X161hard1100.0 / 10010/10OK11.4s1.4k / 1.3k
CG-AL-X162hard1100.0 / 1007/7OK11.2s956 / 774
CG-AL-X163hard1100.0 / 1007/7OK11.0s1.0k / 788
CG-AL-X164hard1100.0 / 1007/7OK11.3s945 / 994
CG-AL-X165hard2100.0 / 10013/13OK14.0s6.1k / 7.4k
CG-AL-X166hard1100.0 / 10014/14OK12.6s1.6k / 1.5k
CG-AL-X167hard2100.0 / 10013/13OK11.6s3.6k / 7.5k
CG-AL-X168hard2100.0 / 1009/9OK11.2s3.6k / 7.4k
CG-AL-X169hard2100.0 / 10011/11OK12.0s3.9k / 4.2k
CG-AL-X170hard1100.0 / 10011/11OK11.7s3.1k / 5.6k
CG-AL-X171hard1100.0 / 1009/9OK11.4s1.4k / 3.0k
CG-AL-X172hard2100.0 / 10011/11OK11.2s5.9k / 7.7k
CG-AL-X173hard2100.0 / 10019/19OK12.3s7.3k / 9.7k
CG-AL-X174hard2100.0 / 10016/16OK11.2s8.3k / 8.3k
CG-AL-X185hard262.5 / 10041/43OK11.9s6.9k / 3.7k
CG-AL-X187hard2100.0 / 10033/33OK11.5s7.5k / 5.6k
CG-AL-X194hard2100.0 / 10050/50OK11.9s9.9k / 5.5k
CG-AL-X211hard2100.0 / 10043/43OK11.7s9.5k / 6.2k
CG-AL-X214hard2100.0 / 10034/34OK11.5s7.9k / 3.8k
CG-AL-X218hard2100.0 / 10027/27OK11.7s7.8k / 4.1k
CG-AL-X234hard2100.0 / 10035/35OK11.5s9.0k / 3.5k
CG-AL-X239hard2100.0 / 10037/37OK12.1s11k / 5.0k
CG-AL-X244hard2100.0 / 10038/38OK11.7s11k / 6.8k
CG-AL-X245hard2100.0 / 10063/63OK11.7s9.8k / 3.9k
CG-AL-X248hard262.5 / 10060/66OK12.2s14k / 3.9k
CG-AL-X249hard262.5 / 10034/37OK11.8s9.7k / 6.0k
CG-AL-X254hard262.5 / 10064/70OK12.0s15k / 7.1k
CG-AL-X257hard20.0 / 1000/0FAIL4.0s9.8k / 8.3k
CG-AL-X263hard2100.0 / 10061/61OK12.1s11k / 6.6k
CG-AL-X264hard2100.0 / 10065/65OK11.9s11k / 5.4k
CG-AL-X270hard2100.0 / 10063/63OK12.1s17k / 8.3k
CG-AL-X271hard2100.0 / 10070/70OK12.4s17k / 9.8k
CG-AL-X272hard2100.0 / 10079/79OK11.8s14k / 6.5k
CG-AL-X274hard2100.0 / 10064/64OK12.7s14k / 6.9k
CG-AL-X276hard2100.0 / 10078/78OK12.8s15k / 6.6k
CG-AL-X278hard262.5 / 10068/71OK13.2s14k / 6.4k
CG-AL-X283hard2100.0 / 10076/76OK11.8s16k / 7.5k
CG-AL-X289hard2100.0 / 10057/57OK13.0s12k / 6.5k
CG-AL-X290hard2100.0 / 10047/47OK11.1s14k / 8.4k
CG-AL-X292hard2100.0 / 10057/57OK12.2s16k / 3.9k
CG-AL-X293hard2100.0 / 10049/49OK11.9s10k / 4.5k
CG-AL-X296hard262.5 / 10046/47OK12.3s13k / 10k
CG-AL-X298hard2100.0 / 10055/55OK11.7s9.3k / 4.5k