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.

77.2% 179/232 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.

70.4 / 100
Cost $0.92
Tokens 649k / 657k input / output, all attempts
Duration 1h 2m
Filter:
Per-task results for run 47d9d727-a304-46ed-9e87-0746c36fda38
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK38.6s258 / 702
CG-AL-E006easy1100.0 / 1007/7OK46.6s305 / 811
CG-AL-E010easy1100.0 / 1005/5OK38.9s280 / 370
CG-AL-E050easy20.0 / 1000/0FAIL9.4s1.8k / 2.9k
CG-AL-E052easy1100.0 / 10016/16OK22.6s352 / 562
CG-AL-E054easy2100.0 / 1009/9OK19.8s974 / 1.9k
CG-AL-E056easy20.0 / 1000/0FAIL9.4s1.7k / 2.1k
CG-AL-H007hard1100.0 / 10011/11OK15.3s545 / 2.0k
CG-AL-H011hard20.0 / 1000/0FAIL9.1s1.1k / 3.7k
CG-AL-H014hard20.0 / 1000/0FAIL4.3s1.5k / 1.6k
CG-AL-H017hard20.0 / 1000/0FAIL4.0s1.1k / 3.7k
CG-AL-H020hard20.0 / 1000/0FAIL3.9s1.8k / 4.4k
CG-AL-H021hard20.0 / 1000/0FAIL4.2s1.9k / 3.0k
CG-AL-H023hard20.0 / 1000/0FAIL4.2s6.1k / 9.6k
CG-AL-H027hard262.5 / 1002/4OK12.0s2.1k / 1.3k
CG-AL-H029hard20.0 / 1000/0FAIL4.2s2.6k / 5.8k
CG-AL-H030hard20.0 / 1000/0FAIL4.2s2.1k / 5.2k
CG-AL-H031hard2100.0 / 10022/22OK12.3s3.0k / 5.1k
CG-AL-H034hard1100.0 / 1003/3OK12.8s431 / 2.6k
CG-AL-H036hard20.0 / 1000/0FAIL4.0s958 / 4.0k
CG-AL-H037hard20.0 / 1000/0FAIL4.9s1.2k / 3.6k
CG-AL-H041hard1100.0 / 1003/3OK11.7s565 / 3.6k
CG-AL-H050hard262.5 / 1002/3OK13.6s1.4k / 3.8k
CG-AL-H054hard2100.0 / 1005/5OK12.5s1.9k / 1.4k
CG-AL-H056hard20.0 / 1000/0FAIL4.5s1.4k / 4.7k
CG-AL-M001medium20.0 / 1000/0FAIL4.5s1.3k / 3.2k
CG-AL-M003medium2100.0 / 1009/9OK18.0s1.4k / 3.2k
CG-AL-M004medium1100.0 / 10012/12OK37.1s449 / 2.4k
CG-AL-M006medium2100.0 / 10018/18OK13.4s2.4k / 4.5k
CG-AL-M007medium20.0 / 1000/0FAIL4.2s3.3k / 6.8k
CG-AL-M008medium262.5 / 1001/12OK13.2s4.2k / 8.7k
CG-AL-M009medium2100.0 / 10011/11OK13.2s4.0k / 7.9k
CG-AL-M010medium2100.0 / 10021/21OK27.1s3.1k / 5.8k
CG-AL-M020medium2100.0 / 10017/17OK12.0s1.9k / 3.1k
CG-AL-M023medium2100.0 / 10011/11OK12.5s1.5k / 1.6k
CG-AL-M025medium2100.0 / 1008/8OK12.1s2.9k / 2.8k
CG-AL-M026medium1100.0 / 1008/8OK13.3s370 / 2.3k
CG-AL-M027medium20.0 / 1000/0FAIL4.1s3.5k / 3.7k
CG-AL-M028medium2100.0 / 1003/3OK27.3s1.0k / 1.6k
CG-AL-M031medium211.1 / 1000/0FAIL4.1s2.1k / 2.6k
CG-AL-M034medium1100.0 / 1002/2OK12.7s415 / 1.6k
CG-AL-M036medium211.1 / 1000/0FAIL4.1s1.5k / 1.6k
CG-AL-M040medium20.0 / 1000/0FAIL4.1s797 / 3.1k
CG-AL-M042medium1100.0 / 1008/8OK12.3s498 / 721
CG-AL-X001hard1100.0 / 1002/2OK12.2s308 / 2.0k
CG-AL-X002hard262.5 / 1000/4OK12.5s1.3k / 4.1k
CG-AL-X003hard2100.0 / 1003/3OK12.0s875 / 4.3k
CG-AL-X004medium1100.0 / 1003/3OK12.1s358 / 1.2k
CG-AL-X005hard1100.0 / 1002/2OK12.8s327 / 663
CG-AL-X006hard1100.0 / 1003/3OK12.8s383 / 1.2k
CG-AL-X007hard1100.0 / 1002/2OK1m 42s372 / 1.2k
CG-AL-X008hard1100.0 / 1001/1OK13.5s417 / 1.9k
CG-AL-X009medium1100.0 / 1002/2OK12.7s313 / 399
CG-AL-X010medium1100.0 / 1003/3OK12.1s284 / 390
CG-AL-X011medium1100.0 / 1002/2OK11.2s360 / 673
CG-AL-X012hard1100.0 / 1001/1OK12.6s380 / 2.3k
CG-AL-X013hard1100.0 / 1002/2OK12.7s263 / 299
CG-AL-X014medium1100.0 / 1004/4OK11.9s291 / 402
CG-AL-X017medium262.5 / 1000/3OK12.0s650 / 475
CG-AL-X018medium1100.0 / 1003/3OK11.5s384 / 497
CG-AL-X019medium1100.0 / 1003/3OK11.3s365 / 711
CG-AL-X022medium2100.0 / 1003/3OK11.5s1.2k / 1.2k
CG-AL-X024medium1100.0 / 1003/3OK11.6s333 / 786
CG-AL-X025medium1100.0 / 1001/1OK11.6s371 / 1.3k
CG-AL-X026medium1100.0 / 1003/3OK10.9s327 / 368
CG-AL-X027medium2100.0 / 1004/4OK12.8s783 / 1.6k
CG-AL-X029medium1100.0 / 1002/2OK11.0s276 / 1.7k
CG-AL-X030medium1100.0 / 1002/2OK11.1s239 / 286
CG-AL-X031medium1100.0 / 1003/3OK11.5s297 / 553
CG-AL-X033hard1100.0 / 1002/2OK12.1s348 / 398
CG-AL-X034hard1100.0 / 1003/3OK11.1s304 / 623
CG-AL-X035hard1100.0 / 1003/3OK11.1s331 / 1.1k
CG-AL-X037hard20.0 / 1000/0FAIL4.8s1.1k / 4.0k
CG-AL-X040hard20.0 / 1000/0FAIL4.9s1.4k / 2.9k
CG-AL-X041hard262.5 / 1000/5OK12.5s1.2k / 4.7k
CG-AL-X043hard20.0 / 1000/0FAIL4.5s1.4k / 5.3k
CG-AL-X044hard20.0 / 1000/0FAIL4.4s1.0k / 3.5k
CG-AL-X045hard1100.0 / 1003/3OK11.1s371 / 648
CG-AL-X046hard2100.0 / 1002/2OK12.6s1.5k / 1.1k
CG-AL-X047hard262.5 / 1001/2OK13.3s1.3k / 5.5k
CG-AL-X050hard1100.0 / 1002/2OK11.2s405 / 1.3k
CG-AL-X051hard1100.0 / 1002/2OK11.8s509 / 2.3k
CG-AL-X052hard1100.0 / 1003/3OK10.9s358 / 1.1k
CG-AL-X055hard1100.0 / 1005/5OK11.0s344 / 669
CG-AL-X056hard2100.0 / 1005/5OK12.8s812 / 1.9k
CG-AL-X057hard1100.0 / 1005/5OK11.1s250 / 352
CG-AL-X058hard1100.0 / 1005/5OK11.3s314 / 724
CG-AL-X059hard1100.0 / 1003/3OK11.0s327 / 488
CG-AL-X060hard1100.0 / 1003/3OK11.1s302 / 587
CG-AL-X061hard1100.0 / 1004/4OK11.1s364 / 310
CG-AL-X062hard1100.0 / 1004/4OK11.3s358 / 782
CG-AL-X063hard1100.0 / 1003/3OK11.2s360 / 1.2k
CG-AL-X064hard1100.0 / 1007/7OK11.0s277 / 639
CG-AL-X065hard1100.0 / 1006/6OK11.2s709 / 749
CG-AL-X066hard1100.0 / 10014/14OK11.3s1.2k / 1.2k
CG-AL-X067hard262.5 / 1006/7OK11.8s1.6k / 4.3k
CG-AL-X068hard1100.0 / 10012/12OK12.3s1.2k / 1.4k
CG-AL-X069hard1100.0 / 1008/8OK12.3s1.1k / 3.8k
CG-AL-X070hard1100.0 / 10012/12OK11.5s1.2k / 2.0k
CG-AL-X071hard1100.0 / 1008/8OK10.9s1.4k / 1.3k
CG-AL-X072hard1100.0 / 1007/7OK11.3s1.1k / 858
CG-AL-X073hard1100.0 / 1008/8OK11.2s1.4k / 1.4k
CG-AL-X074hard2100.0 / 1007/7OK11.6s3.4k / 6.3k
CG-AL-X075hard1100.0 / 1007/7OK11.2s810 / 2.3k
CG-AL-X076hard2100.0 / 10014/14OK11.5s3.4k / 4.2k
CG-AL-X077hard1100.0 / 10022/22OK11.6s1.5k / 1.4k
CG-AL-X078hard1100.0 / 10017/17OK11.0s1.2k / 985
CG-AL-X079hard1100.0 / 10011/11OK11.8s1.2k / 3.5k
CG-AL-X080hard262.5 / 1006/7OK11.1s2.4k / 2.6k
CG-AL-X081hard1100.0 / 1008/8OK10.8s902 / 663
CG-AL-X082hard1100.0 / 10015/15OK11.0s1.2k / 997
CG-AL-X083hard1100.0 / 1009/9OK11.2s1.5k / 1.3k
CG-AL-X084hard1100.0 / 10010/10OK11.5s1.4k / 3.8k
CG-AL-X085hard1100.0 / 1007/7OK10.9s980 / 775
CG-AL-X086hard1100.0 / 1006/6OK11.0s1.4k / 2.1k
CG-AL-X087hard1100.0 / 1003/3OK11.4s1.0k / 1.0k
CG-AL-X088hard1100.0 / 1006/6OK10.8s974 / 1.5k
CG-AL-X089hard1100.0 / 10011/11OK11.2s1.1k / 3.3k
CG-AL-X090hard262.5 / 1008/10OK11.3s1.9k / 4.9k
CG-AL-X091hard1100.0 / 1006/6OK10.7s569 / 474
CG-AL-X092hard1100.0 / 10015/15OK12.3s444 / 684
CG-AL-X093hard1100.0 / 10010/10OK11.4s989 / 2.0k
CG-AL-X094hard1100.0 / 1007/7OK11.0s754 / 813
CG-AL-X095hard1100.0 / 1005/5OK11.3s797 / 620
CG-AL-X096hard1100.0 / 10049/49OK11.5s3.3k / 3.1k
CG-AL-X097hard2100.0 / 10046/46OK12.3s6.8k / 7.1k
CG-AL-X098hard1100.0 / 10029/29OK12.6s2.6k / 2.6k
CG-AL-X099hard1100.0 / 10039/39OK13.9s3.6k / 4.4k
CG-AL-X100hard1100.0 / 10035/35OK12.2s3.5k / 3.8k
CG-AL-X101hard1100.0 / 10010/10OK11.8s1.1k / 1.3k
CG-AL-X102hard2100.0 / 1008/8OK11.4s2.3k / 2.0k
CG-AL-X103hard1100.0 / 1007/7OK11.3s725 / 675
CG-AL-X104hard1100.0 / 1006/6OK11.7s1.1k / 944
CG-AL-X105hard1100.0 / 1006/6OK11.5s777 / 559
CG-AL-X106hard1100.0 / 1005/5OK11.3s878 / 1.4k
CG-AL-X107hard1100.0 / 1004/4OK11.6s805 / 1.1k
CG-AL-X108hard1100.0 / 1006/6OK12.4s729 / 431
CG-AL-X109hard1100.0 / 1005/5OK11.7s548 / 777
CG-AL-X110hard1100.0 / 10017/17OK11.5s1.2k / 1.0k
CG-AL-X111hard2100.0 / 1008/8OK11.1s2.7k / 5.3k
CG-AL-X112hard1100.0 / 10012/12OK11.6s906 / 3.5k
CG-AL-X113hard1100.0 / 10013/13OK11.6s705 / 687
CG-AL-X114hard1100.0 / 1007/7OK11.4s718 / 538
CG-AL-X115hard1100.0 / 10013/13OK12.6s478 / 909
CG-AL-X116hard1100.0 / 10017/17OK11.1s926 / 3.5k
CG-AL-X117hard1100.0 / 1008/8OK11.2s1.0k / 1.1k
CG-AL-X118hard1100.0 / 10017/17OK11.5s1.4k / 1.4k
CG-AL-X119hard1100.0 / 10015/15OK11.6s1.7k / 1.7k
CG-AL-X120hard2100.0 / 10012/12OK11.3s4.3k / 2.4k
CG-AL-X121hard1100.0 / 1006/6OK11.3s1.0k / 844
CG-AL-X122hard262.5 / 1009/10OK11.5s3.3k / 4.8k
CG-AL-X123hard1100.0 / 1005/5OK11.1s603 / 561
CG-AL-X124hard1100.0 / 10010/10OK12.0s994 / 1.2k
CG-AL-X125hard1100.0 / 1008/8OK11.4s1.4k / 1.2k
CG-AL-X126hard1100.0 / 10014/14OK11.2s711 / 1.5k
CG-AL-X127hard1100.0 / 1005/5OK11.1s666 / 908
CG-AL-X128hard1100.0 / 1008/8OK10.9s1.1k / 897
CG-AL-X129hard1100.0 / 10014/14OK11.4s1.2k / 1.2k
CG-AL-X130hard1100.0 / 1005/5OK11.1s529 / 1.2k
CG-AL-X131hard1100.0 / 10013/13OK12.0s941 / 997
CG-AL-X132hard1100.0 / 10010/10OK12.4s709 / 474
CG-AL-X133hard2100.0 / 1008/8OK11.9s3.4k / 5.5k
CG-AL-X134hard1100.0 / 1006/6OK11.9s1.2k / 1.8k
CG-AL-X135hard1100.0 / 1004/4OK10.9s866 / 683
CG-AL-X136hard1100.0 / 1007/7OK10.8s754 / 427
CG-AL-X137hard1100.0 / 1004/4OK11.1s915 / 1.0k
CG-AL-X138hard1100.0 / 1009/9OK11.5s1.4k / 2.5k
CG-AL-X139hard1100.0 / 10011/11OK11.4s1.6k / 1.6k
CG-AL-X140hard2100.0 / 1007/7OK13.1s4.0k / 7.1k
CG-AL-X141hard1100.0 / 10039/39OK12.1s3.5k / 3.2k
CG-AL-X142hard2100.0 / 10048/48OK12.5s9.6k / 10k
CG-AL-X143hard1100.0 / 10035/35OK16.2s4.0k / 3.6k
CG-AL-X144hard1100.0 / 10043/43OK11.8s3.6k / 3.3k
CG-AL-X145hard1100.0 / 10032/32OK12.1s4.2k / 3.9k
CG-AL-X146hard1100.0 / 1009/9OK11.2s1.7k / 4.4k
CG-AL-X147hard1100.0 / 1008/8OK11.1s1.3k / 1.1k
CG-AL-X148hard1100.0 / 1006/6OK11.1s1.1k / 813
CG-AL-X149hard1100.0 / 1007/7OK11.2s1.1k / 971
CG-AL-X150hard1100.0 / 1009/9OK11.4s1.9k / 4.0k
CG-AL-X151hard1100.0 / 1006/6OK11.2s818 / 563
CG-AL-X152hard1100.0 / 1008/8OK11.3s1.1k / 1.2k
CG-AL-X153hard1100.0 / 1009/9OK19.8s888 / 2.7k
CG-AL-X154hard1100.0 / 1009/9OK11.5s1.2k / 1.2k
CG-AL-X155hard1100.0 / 10011/11OK11.7s923 / 1.6k
CG-AL-X156hard1100.0 / 1007/7OK11.2s884 / 592
CG-AL-X157hard1100.0 / 10010/10OK11.6s1.3k / 1.1k
CG-AL-X158hard1100.0 / 1007/7OK11.3s801 / 506
CG-AL-X159hard1100.0 / 1007/7OK13.4s849 / 717
CG-AL-X160hard1100.0 / 10013/13OK12.1s1.2k / 1.7k
CG-AL-X161hard1100.0 / 10010/10OK11.3s1.4k / 1.3k
CG-AL-X162hard1100.0 / 1007/7OK11.1s956 / 791
CG-AL-X163hard1100.0 / 1007/7OK11.2s1.0k / 845
CG-AL-X164hard1100.0 / 1007/7OK12.5s945 / 718
CG-AL-X165hard1100.0 / 10013/13OK13.6s2.6k / 4.5k
CG-AL-X166hard2100.0 / 10014/14OK12.8s3.8k / 3.7k
CG-AL-X167hard20.0 / 1000/0FAIL4.2s3.6k / 8.1k
CG-AL-X168hard20.0 / 1000/0FAIL4.0s3.7k / 5.5k
CG-AL-X169hard2100.0 / 10011/11OK12.2s4.2k / 5.9k
CG-AL-X170hard1100.0 / 10011/11OK11.7s3.1k / 5.0k
CG-AL-X171hard1100.0 / 1009/9OK11.4s1.4k / 3.2k
CG-AL-X172hard2100.0 / 10011/11OK11.9s5.4k / 7.2k
CG-AL-X173hard2100.0 / 10019/19OK13.2s6.7k / 8.0k
CG-AL-X174hard2100.0 / 10016/16OK12.5s8.4k / 9.2k
CG-AL-X185hard262.5 / 10041/43OK12.2s6.9k / 3.5k
CG-AL-X187hard262.5 / 10030/33OK12.4s7.5k / 6.0k
CG-AL-X194hard262.5 / 10048/50OK13.9s9.9k / 6.3k
CG-AL-X211hard2100.0 / 10043/43OK14.2s8.9k / 4.2k
CG-AL-X214hard2100.0 / 10034/34OK14.4s7.9k / 5.7k
CG-AL-X218hard2100.0 / 10027/27OK13.4s7.8k / 4.6k
CG-AL-X234hard2100.0 / 10035/35OK13.0s11k / 5.6k
CG-AL-X239hard2100.0 / 10037/37OK13.2s11k / 5.9k
CG-AL-X244hard2100.0 / 10038/38OK12.8s11k / 6.2k
CG-AL-X245hard2100.0 / 10063/63OK13.6s11k / 6.2k
CG-AL-X248hard2100.0 / 10066/66OK13.4s9.8k / 4.2k
CG-AL-X249hard2100.0 / 10037/37OK12.8s10k / 5.7k
CG-AL-X254hard262.5 / 10060/70OK12.8s12k / 5.1k
CG-AL-X257hard262.5 / 10052/53OK12.8s10k / 6.6k
CG-AL-X263hard262.5 / 10058/61OK13.5s14k / 8.0k
CG-AL-X264hard262.5 / 10064/65OK13.0s12k / 5.9k
CG-AL-X270hard262.5 / 10060/63OK13.8s18k / 6.0k
CG-AL-X271hard262.5 / 10069/70OK15.0s18k / 11k
CG-AL-X272hard2100.0 / 10079/79OK14.3s14k / 7.2k
CG-AL-X274hard262.5 / 10061/64OK14.4s15k / 6.7k
CG-AL-X276hard262.5 / 10063/78OK14.8s14k / 6.4k
CG-AL-X278hard262.5 / 10068/71OK14.2s14k / 6.1k
CG-AL-X283hard262.5 / 10063/76OK14.2s15k / 7.5k
CG-AL-X289hard262.5 / 10055/57OK14.1s17k / 9.0k
CG-AL-X290hard2100.0 / 10047/47OK13.5s12k / 4.8k
CG-AL-X292hard262.5 / 10040/57OK14.6s9.3k / 1.8k
CG-AL-X293hard2100.0 / 10049/49OK13.3s10k / 4.2k
CG-AL-X296hard262.5 / 10032/47OK15.0s17k / 8.7k
CG-AL-X298hard262.5 / 10041/55OK14.4s13k / 5.5k