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.

80.2% 186/232 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.

71.6 / 100
Cost $0.42
Tokens 639k / 706k input / output, all attempts
Duration 53m 14s
Filter:
Per-task results for run ccbdfd68-50d8-4156-8b52-9a4f38286585
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK15.6s258 / 374
CG-AL-E006easy1100.0 / 1007/7OK55.1s305 / 746
CG-AL-E010easy1100.0 / 1005/5OK15.5s280 / 404
CG-AL-E050easy20.0 / 1000/0FAIL8.7s1.8k / 1.4k
CG-AL-E052easy1100.0 / 10016/16OK11.6s352 / 471
CG-AL-E054easy20.0 / 1000/0FAIL9.1s985 / 1.9k
CG-AL-E056easy2100.0 / 10015/15OK17.9s1.7k / 1.4k
CG-AL-H007hard1100.0 / 10011/11OK10.8s545 / 1.5k
CG-AL-H011hard20.0 / 1000/0FAIL8.8s947 / 2.7k
CG-AL-H014hard20.0 / 1000/0FAIL8.7s1.6k / 1.9k
CG-AL-H017hard20.0 / 1000/0FAIL3.6s966 / 4.2k
CG-AL-H020hard20.0 / 1000/0FAIL3.8s1.8k / 3.7k
CG-AL-H021hard262.5 / 1006/20OK11.4s1.8k / 2.8k
CG-AL-H023hard262.5 / 10024/25OK11.6s6.4k / 13k
CG-AL-H027hard20.0 / 1000/0FAIL4.3s2.1k / 3.4k
CG-AL-H029hard20.0 / 1000/0FAIL4.0s2.6k / 4.9k
CG-AL-H030hard2100.0 / 10010/10OK10.2s2.3k / 7.0k
CG-AL-H031hard1100.0 / 10022/22OK10.5s939 / 3.3k
CG-AL-H034hard2100.0 / 1003/3OK10.0s1.6k / 1.8k
CG-AL-H036hard20.0 / 1000/0FAIL3.8s1.2k / 4.2k
CG-AL-H037hard20.0 / 1000/0FAIL4.0s1.2k / 2.2k
CG-AL-H041hard1100.0 / 1003/3OK10.4s565 / 2.9k
CG-AL-H050hard262.5 / 1002/3OK9.9s1.4k / 4.1k
CG-AL-H054hard2100.0 / 1005/5OK9.9s1.9k / 1.7k
CG-AL-H056hard20.0 / 1000/0FAIL4.6s1.4k / 1.2k
CG-AL-M001medium20.0 / 1000/0FAIL3.9s1.3k / 3.2k
CG-AL-M003medium1100.0 / 1009/9OK10.3s419 / 2.2k
CG-AL-M004medium1100.0 / 10012/12OK30.8s449 / 2.8k
CG-AL-M006medium262.5 / 10017/18OK13.7s2.2k / 7.3k
CG-AL-M007medium20.0 / 1000/0FAIL3.8s3.2k / 9.2k
CG-AL-M008medium262.5 / 1004/12OK11.0s4.6k / 13k
CG-AL-M009medium1100.0 / 10011/11OK15.9s429 / 6.2k
CG-AL-M010medium1100.0 / 10021/21OK24.0s596 / 4.8k
CG-AL-M020medium2100.0 / 10017/17OK14.3s2.2k / 4.0k
CG-AL-M023medium1100.0 / 10011/11OK11.1s482 / 1.3k
CG-AL-M025medium2100.0 / 1008/8OK10.0s2.8k / 2.2k
CG-AL-M026medium1100.0 / 1008/8OK10.7s370 / 1.8k
CG-AL-M027medium2100.0 / 10018/18OK9.8s3.5k / 5.0k
CG-AL-M028medium211.1 / 1000/0FAIL3.7s1.0k / 1.6k
CG-AL-M031medium2100.0 / 1002/2OK9.8s1.9k / 2.0k
CG-AL-M034medium2100.0 / 1002/2OK10.0s1.1k / 3.6k
CG-AL-M036medium211.1 / 1000/0FAIL3.7s1.5k / 2.1k
CG-AL-M040medium1100.0 / 1002/2OK10.0s311 / 452
CG-AL-M042medium1100.0 / 1008/8OK10.1s498 / 950
CG-AL-X001hard1100.0 / 1002/2OK10.0s308 / 1.5k
CG-AL-X002hard1100.0 / 1004/4OK10.3s488 / 4.7k
CG-AL-X003hard2100.0 / 1003/3OK9.8s966 / 2.8k
CG-AL-X004medium1100.0 / 1003/3OK11.9s358 / 1.1k
CG-AL-X005hard1100.0 / 1002/2OK10.4s327 / 653
CG-AL-X006hard1100.0 / 1003/3OK10.5s383 / 704
CG-AL-X007hard1100.0 / 1002/2OK1m 20s372 / 870
CG-AL-X008hard1100.0 / 1001/1OK10.6s417 / 2.5k
CG-AL-X009medium1100.0 / 1002/2OK10.4s313 / 304
CG-AL-X010medium1100.0 / 1003/3OK10.8s284 / 409
CG-AL-X011medium1100.0 / 1002/2OK12.0s360 / 761
CG-AL-X012hard1100.0 / 1001/1OK9.8s380 / 2.1k
CG-AL-X013hard1100.0 / 1002/2OK13.9s263 / 316
CG-AL-X014medium1100.0 / 1004/4OK10.5s291 / 280
CG-AL-X017medium2100.0 / 1003/3OK9.6s1.4k / 639
CG-AL-X018medium1100.0 / 1003/3OK10.5s384 / 1.1k
CG-AL-X019medium1100.0 / 1003/3OK10.7s365 / 1.2k
CG-AL-X022medium2100.0 / 1003/3OK10.2s1.3k / 1.6k
CG-AL-X024medium1100.0 / 1003/3OK10.4s333 / 1.0k
CG-AL-X025medium1100.0 / 1001/1OK10.4s371 / 795
CG-AL-X026medium1100.0 / 1003/3OK10.5s327 / 343
CG-AL-X027medium1100.0 / 1004/4OK10.4s258 / 775
CG-AL-X029medium1100.0 / 1002/2OK12.3s276 / 3.0k
CG-AL-X030medium1100.0 / 1002/2OK10.4s239 / 244
CG-AL-X031medium1100.0 / 1003/3OK10.6s297 / 437
CG-AL-X033hard1100.0 / 1002/2OK10.3s348 / 230
CG-AL-X034hard1100.0 / 1003/3OK10.0s304 / 716
CG-AL-X035hard20.0 / 1000/0FAIL4.3s795 / 2.4k
CG-AL-X037hard2100.0 / 1004/4OK10.5s1.0k / 3.9k
CG-AL-X040hard20.0 / 1000/0FAIL4.1s1.4k / 4.2k
CG-AL-X041hard20.0 / 1000/0FAIL4.0s1.2k / 4.5k
CG-AL-X043hard20.0 / 1000/0FAIL3.8s1.3k / 7.3k
CG-AL-X044hard262.5 / 1001/3OK9.7s970 / 2.7k
CG-AL-X045hard1100.0 / 1003/3OK10.2s371 / 1.3k
CG-AL-X046hard1100.0 / 1002/2OK10.1s369 / 996
CG-AL-X047hard262.5 / 1001/2OK9.9s1.2k / 4.8k
CG-AL-X050hard1100.0 / 1002/2OK10.5s405 / 932
CG-AL-X051hard1100.0 / 1002/2OK10.4s509 / 1.5k
CG-AL-X052hard1100.0 / 1003/3OK10.2s358 / 974
CG-AL-X055hard1100.0 / 1005/5OK10.0s344 / 892
CG-AL-X056hard1100.0 / 1005/5OK9.8s280 / 1.2k
CG-AL-X057hard1100.0 / 1005/5OK10.0s250 / 384
CG-AL-X058hard1100.0 / 1005/5OK9.8s314 / 1.2k
CG-AL-X059hard1100.0 / 1003/3OK10.0s327 / 396
CG-AL-X060hard1100.0 / 1003/3OK10.2s302 / 587
CG-AL-X061hard1100.0 / 1004/4OK9.9s364 / 265
CG-AL-X062hard1100.0 / 1004/4OK10.2s358 / 678
CG-AL-X063hard1100.0 / 1003/3OK9.9s360 / 778
CG-AL-X064hard1100.0 / 1007/7OK10.1s277 / 824
CG-AL-X065hard1100.0 / 1006/6OK9.8s709 / 651
CG-AL-X066hard1100.0 / 10014/14OK10.1s1.2k / 1.3k
CG-AL-X067hard20.0 / 1000/0FAIL3.8s1.7k / 3.6k
CG-AL-X068hard1100.0 / 10012/12OK10.1s1.2k / 2.3k
CG-AL-X069hard2100.0 / 1008/8OK10.0s2.5k / 5.8k
CG-AL-X070hard1100.0 / 10012/12OK9.8s1.2k / 1.0k
CG-AL-X071hard1100.0 / 1008/8OK10.1s1.4k / 1.2k
CG-AL-X072hard1100.0 / 1007/7OK9.9s1.1k / 867
CG-AL-X073hard1100.0 / 1008/8OK10.1s1.4k / 1.4k
CG-AL-X074hard262.5 / 1006/7OK10.0s3.7k / 4.8k
CG-AL-X075hard1100.0 / 1007/7OK9.9s810 / 3.2k
CG-AL-X076hard1100.0 / 10014/14OK9.7s954 / 1.7k
CG-AL-X077hard1100.0 / 10022/22OK9.9s1.5k / 1.5k
CG-AL-X078hard1100.0 / 10017/17OK10.0s1.2k / 1.0k
CG-AL-X079hard2100.0 / 10011/11OK10.3s3.3k / 7.9k
CG-AL-X080hard20.0 / 1000/0FAIL4.3s2.4k / 2.6k
CG-AL-X081hard1100.0 / 1008/8OK9.9s902 / 634
CG-AL-X082hard2100.0 / 10015/15OK10.1s3.1k / 2.7k
CG-AL-X083hard1100.0 / 1009/9OK9.8s1.5k / 1.3k
CG-AL-X084hard1100.0 / 10010/10OK10.4s1.4k / 2.6k
CG-AL-X085hard1100.0 / 1007/7OK9.9s980 / 689
CG-AL-X086hard1100.0 / 1006/6OK10.6s1.4k / 2.1k
CG-AL-X087hard1100.0 / 1003/3OK10.3s1.0k / 938
CG-AL-X088hard1100.0 / 1006/6OK9.6s974 / 1.2k
CG-AL-X089hard2100.0 / 10011/11OK10.3s2.6k / 5.9k
CG-AL-X090hard262.5 / 1008/10OK9.9s1.9k / 4.4k
CG-AL-X091hard1100.0 / 1006/6OK9.6s569 / 337
CG-AL-X092hard1100.0 / 10015/15OK9.7s444 / 368
CG-AL-X093hard1100.0 / 10010/10OK10.2s989 / 1.1k
CG-AL-X094hard1100.0 / 1007/7OK9.8s754 / 599
CG-AL-X095hard262.5 / 1003/5OK10.1s2.1k / 2.2k
CG-AL-X096hard1100.0 / 10049/49OK10.2s3.3k / 3.3k
CG-AL-X097hard2100.0 / 10046/46OK12.8s7.1k / 7.7k
CG-AL-X098hard1100.0 / 10029/29OK10.2s2.6k / 2.2k
CG-AL-X099hard1100.0 / 10039/39OK12.3s3.6k / 5.6k
CG-AL-X100hard1100.0 / 10035/35OK10.5s3.5k / 4.2k
CG-AL-X101hard1100.0 / 10010/10OK10.1s1.1k / 1.7k
CG-AL-X102hard1100.0 / 1008/8OK10.0s531 / 2.9k
CG-AL-X103hard1100.0 / 1007/7OK10.0s725 / 665
CG-AL-X104hard1100.0 / 1006/6OK10.0s1.1k / 932
CG-AL-X105hard1100.0 / 1006/6OK10.0s777 / 500
CG-AL-X106hard1100.0 / 1005/5OK9.7s878 / 1.1k
CG-AL-X107hard1100.0 / 1004/4OK10.0s805 / 1.1k
CG-AL-X108hard1100.0 / 1006/6OK10.8s729 / 511
CG-AL-X109hard1100.0 / 1005/5OK9.9s548 / 532
CG-AL-X110hard1100.0 / 10017/17OK10.1s1.2k / 997
CG-AL-X111hard1100.0 / 1008/8OK10.3s1.2k / 4.3k
CG-AL-X112hard1100.0 / 10012/12OK10.1s906 / 2.3k
CG-AL-X113hard1100.0 / 10013/13OK11.1s705 / 3.6k
CG-AL-X114hard1100.0 / 1007/7OK9.9s718 / 492
CG-AL-X115hard1100.0 / 10013/13OK9.6s478 / 787
CG-AL-X116hard1100.0 / 10017/17OK10.1s926 / 2.8k
CG-AL-X117hard1100.0 / 1008/8OK10.0s1.0k / 967
CG-AL-X118hard1100.0 / 10017/17OK10.1s1.4k / 1.6k
CG-AL-X119hard1100.0 / 10015/15OK10.2s1.7k / 1.7k
CG-AL-X120hard1100.0 / 10012/12OK10.0s1.2k / 1.1k
CG-AL-X121hard1100.0 / 1006/6OK10.2s1.0k / 835
CG-AL-X122hard1100.0 / 10010/10OK10.5s1.5k / 2.2k
CG-AL-X123hard1100.0 / 1005/5OK11.1s603 / 632
CG-AL-X124hard1100.0 / 10010/10OK10.4s994 / 913
CG-AL-X125hard1100.0 / 1008/8OK10.4s1.4k / 1.4k
CG-AL-X126hard1100.0 / 10014/14OK10.0s711 / 988
CG-AL-X127hard1100.0 / 1005/5OK9.9s666 / 523
CG-AL-X128hard1100.0 / 1008/8OK10.1s1.1k / 852
CG-AL-X129hard1100.0 / 10014/14OK10.1s1.2k / 1.2k
CG-AL-X130hard1100.0 / 1005/5OK10.2s529 / 1.0k
CG-AL-X131hard1100.0 / 10013/13OK9.9s941 / 717
CG-AL-X132hard1100.0 / 10010/10OK10.1s709 / 485
CG-AL-X133hard2100.0 / 1008/8OK10.3s3.5k / 5.8k
CG-AL-X134hard1100.0 / 1006/6OK10.4s1.2k / 2.3k
CG-AL-X135hard1100.0 / 1004/4OK10.1s866 / 670
CG-AL-X136hard1100.0 / 1007/7OK9.9s754 / 521
CG-AL-X137hard1100.0 / 1004/4OK10.1s915 / 1.2k
CG-AL-X138hard1100.0 / 1009/9OK10.7s1.4k / 1.8k
CG-AL-X139hard1100.0 / 10011/11OK10.4s1.6k / 1.5k
CG-AL-X140hard1100.0 / 1007/7OK10.0s1.5k / 4.5k
CG-AL-X141hard1100.0 / 10039/39OK11.0s3.5k / 3.3k
CG-AL-X142hard2100.0 / 10048/48OK11.0s9.1k / 13k
CG-AL-X143hard1100.0 / 10035/35OK15.2s4.0k / 4.4k
CG-AL-X144hard1100.0 / 10043/43OK10.8s3.6k / 3.6k
CG-AL-X145hard1100.0 / 10032/32OK10.7s4.2k / 4.1k
CG-AL-X146hard20.0 / 1000/0FAIL3.6s3.9k / 8.4k
CG-AL-X147hard1100.0 / 1008/8OK10.2s1.3k / 1.0k
CG-AL-X148hard1100.0 / 1006/6OK9.9s1.1k / 791
CG-AL-X149hard1100.0 / 1007/7OK10.0s1.1k / 983
CG-AL-X150hard262.5 / 1007/9OK10.3s4.8k / 8.6k
CG-AL-X151hard1100.0 / 1006/6OK9.8s818 / 583
CG-AL-X152hard1100.0 / 1008/8OK9.9s1.1k / 951
CG-AL-X153hard2100.0 / 1009/9OK19.4s2.0k / 5.9k
CG-AL-X154hard1100.0 / 1009/9OK10.2s1.2k / 1.2k
CG-AL-X155hard1100.0 / 10011/11OK10.2s923 / 1.0k
CG-AL-X156hard1100.0 / 1007/7OK10.7s884 / 581
CG-AL-X157hard1100.0 / 10010/10OK10.3s1.3k / 1.1k
CG-AL-X158hard1100.0 / 1007/7OK10.3s801 / 483
CG-AL-X159hard1100.0 / 1007/7OK11.4s849 / 917
CG-AL-X160hard1100.0 / 10013/13OK10.6s1.2k / 2.0k
CG-AL-X161hard1100.0 / 10010/10OK10.4s1.4k / 1.4k
CG-AL-X162hard1100.0 / 1007/7OK10.6s956 / 791
CG-AL-X163hard1100.0 / 1007/7OK10.3s1.0k / 820
CG-AL-X164hard1100.0 / 1007/7OK10.4s945 / 886
CG-AL-X165hard20.0 / 1000/0FAIL3.7s5.5k / 8.7k
CG-AL-X166hard1100.0 / 10014/14OK11.4s1.6k / 1.5k
CG-AL-X167hard1100.0 / 10013/13OK11.2s1.4k / 4.3k
CG-AL-X168hard2100.0 / 1009/9OK10.0s5.2k / 5.4k
CG-AL-X169hard2100.0 / 10011/11OK10.6s3.9k / 4.9k
CG-AL-X170hard1100.0 / 10011/11OK11.0s3.1k / 4.5k
CG-AL-X171hard1100.0 / 1009/9OK10.8s1.4k / 3.9k
CG-AL-X172hard1100.0 / 10011/11OK11.2s2.2k / 4.5k
CG-AL-X173hard20.0 / 1000/0FAIL4.0s7.3k / 7.8k
CG-AL-X174hard2100.0 / 10016/16OK10.8s8.8k / 13k
CG-AL-X185hard2100.0 / 10043/43OK10.3s6.9k / 4.0k
CG-AL-X187hard2100.0 / 10033/33OK10.5s7.5k / 5.6k
CG-AL-X194hard2100.0 / 10050/50OK10.7s9.9k / 5.1k
CG-AL-X211hard2100.0 / 10043/43OK11.1s9.7k / 7.6k
CG-AL-X214hard2100.0 / 10034/34OK10.4s10.0k / 6.5k
CG-AL-X218hard2100.0 / 10027/27OK10.7s9.8k / 5.4k
CG-AL-X234hard2100.0 / 10035/35OK10.9s9.0k / 6.0k
CG-AL-X239hard262.5 / 10034/37OK11.4s12k / 7.0k
CG-AL-X244hard262.5 / 10035/38OK10.6s12k / 9.1k
CG-AL-X245hard262.5 / 10061/63OK10.8s15k / 5.3k
CG-AL-X248hard262.5 / 10065/66OK11.4s15k / 7.7k
CG-AL-X249hard2100.0 / 10037/37OK10.8s9.7k / 7.1k
CG-AL-X254hard262.5 / 10060/70OK11.3s12k / 6.3k
CG-AL-X257hard262.5 / 10046/53OK10.5s9.6k / 8.5k
CG-AL-X263hard2100.0 / 10061/61OK11.2s11k / 6.5k
CG-AL-X264hard262.5 / 10064/65OK11.2s11k / 7.7k
CG-AL-X270hard262.5 / 10061/63OK12.8s17k / 8.4k
CG-AL-X271hard262.5 / 10069/70OK11.5s19k / 11k
CG-AL-X272hard2100.0 / 10079/79OK11.4s13k / 6.3k
CG-AL-X274hard2100.0 / 10064/64OK11.9s14k / 7.2k
CG-AL-X276hard2100.0 / 10078/78OK11.5s15k / 9.0k
CG-AL-X278hard2100.0 / 10071/71OK11.8s14k / 8.2k
CG-AL-X283hard2100.0 / 10076/76OK11.1s15k / 6.1k
CG-AL-X289hard262.5 / 10053/57OK10.9s11k / 13k
CG-AL-X290hard2100.0 / 10047/47OK11.3s12k / 5.4k
CG-AL-X292hard2100.0 / 10057/57OK11.5s13k / 6.5k
CG-AL-X293hard2100.0 / 10049/49OK10.9s10k / 4.9k
CG-AL-X296hard2100.0 / 10047/47OK11.3s17k / 9.2k
CG-AL-X298hard262.5 / 10054/55OK10.9s9.0k / 7.2k