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.

71.1% 165/232 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.

64.2 / 100
Cost $20.20
Tokens 1.1M / 1.8M input / output, all attempts
Duration 51m 11s
Filter:
Per-task results for run 4c095313-8a6f-482e-9def-e7d3ae395815
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK22.3s413 / 317
CG-AL-E006easy1100.0 / 1007/7OK36.2s494 / 720
CG-AL-E010easy1100.0 / 1005/5OK24.7s466 / 230
CG-AL-E050easy20.0 / 1000/0FAIL8.6s3.0k / 1.6k
CG-AL-E052easy1100.0 / 10016/16OK22.7s610 / 384
CG-AL-E054easy2100.0 / 1009/9OK16.2s1.7k / 1.0k
CG-AL-E056easy2100.0 / 10015/15OK16.2s2.8k / 1.7k
CG-AL-H007hard1100.0 / 10011/11OK16.9s947 / 2.0k
CG-AL-H011hard20.0 / 1000/0FAIL9.0s1.5k / 4.7k
CG-AL-H014hard2100.0 / 1007/7OK16.1s4.2k / 4.5k
CG-AL-H017hard20.0 / 1000/0FAIL4.1s1.7k / 1.4k
CG-AL-H020hard2100.0 / 10010/10OK11.4s3.5k / 2.5k
CG-AL-H021hard2100.0 / 10020/20OK10.8s30k / 3.3k
CG-AL-H023hard20.0 / 1000/0FAIL4.0s12k / 55k
CG-AL-H027hard262.5 / 1002/4OK11.5s3.4k / 26k
CG-AL-H029hard20.0 / 1000/0FAIL4.0s4.4k / 6.1k
CG-AL-H030hard2100.0 / 10010/10OK10.6s3.4k / 8.2k
CG-AL-H031hard1100.0 / 10022/22OK11.1s1.6k / 5.0k
CG-AL-H034hard1100.0 / 1003/3OK10.7s720 / 2.7k
CG-AL-H036hard20.0 / 1000/0FAIL4.1s1.5k / 1.2k
CG-AL-H037hard2100.0 / 1003/3OK10.4s2.2k / 3.1k
CG-AL-H041hard2100.0 / 1003/3OK10.2s3.7k / 6.8k
CG-AL-H050hard262.5 / 1002/3OK13.3s2.3k / 16k
CG-AL-H054hard20.0 / 1000/0FAIL3.8s3.0k / 1.7k
CG-AL-H056hard20.0 / 1000/0FAIL3.8s2.4k / 498
CG-AL-M001medium2100.0 / 10010/10OK28.9s2.2k / 1.8k
CG-AL-M003medium20.0 / 1000/0FAIL5.9s2.8k / 2.8k
CG-AL-M004medium1100.0 / 10012/12OK32.1s773 / 2.1k
CG-AL-M006medium1100.0 / 10018/18OK12.2s705 / 5.5k
CG-AL-M007medium20.0 / 1000/0FAIL0ms4.8k / 37k
CG-AL-M008medium262.5 / 10010/12OK13.4s14k / 28k
CG-AL-M009medium1100.0 / 10011/11OK10.8s746 / 5.1k
CG-AL-M010medium1100.0 / 10021/21OK25.8s958 / 6.8k
CG-AL-M020medium2100.0 / 10017/17OK11.9s3.0k / 2.2k
CG-AL-M023medium1100.0 / 10011/11OK11.2s803 / 836
CG-AL-M025medium2100.0 / 1008/8OK14.4s4.7k / 1.3k
CG-AL-M026medium20.0 / 1000/0FAIL4.5s1.9k / 1.7k
CG-AL-M027medium2100.0 / 10018/18OK13.6s6.0k / 4.3k
CG-AL-M028medium211.1 / 1000/0FAIL4.0s1.7k / 2.5k
CG-AL-M031medium2100.0 / 1002/2OK10.7s3.4k / 2.9k
CG-AL-M034medium1100.0 / 1002/2OK10.3s695 / 916
CG-AL-M036medium211.1 / 1000/0FAIL4.0s2.6k / 2.6k
CG-AL-M040medium20.0 / 1000/0FAIL3.9s1.3k / 18k
CG-AL-M042medium1100.0 / 1008/8OK10.6s753 / 514
CG-AL-X001hard1100.0 / 1002/2OK10.4s499 / 216
CG-AL-X002hard2100.0 / 1004/4OK10.8s4.0k / 5.9k
CG-AL-X003hard20.0 / 1000/0FAIL3.8s1.7k / 14k
CG-AL-X004medium1100.0 / 1003/3OK10.3s551 / 516
CG-AL-X005hard1100.0 / 1002/2OK10.8s515 / 229
CG-AL-X006hard1100.0 / 1003/3OK10.3s603 / 728
CG-AL-X007hard1100.0 / 1002/2OK1m 49s575 / 271
CG-AL-X008hard2100.0 / 1001/1OK11.0s2.3k / 3.7k
CG-AL-X009medium1100.0 / 1002/2OK13.0s493 / 210
CG-AL-X010medium1100.0 / 1003/3OK10.2s449 / 251
CG-AL-X011medium1100.0 / 1002/2OK10.0s557 / 234
CG-AL-X012hard1100.0 / 1001/1OK10.5s589 / 1.9k
CG-AL-X013hard1100.0 / 1002/2OK10.8s423 / 135
CG-AL-X014medium1100.0 / 1004/4OK10.3s458 / 163
CG-AL-X017medium2100.0 / 1003/3OK10.9s2.4k / 419
CG-AL-X018medium1100.0 / 1003/3OK10.5s606 / 265
CG-AL-X019medium262.5 / 1000/3OK10.7s2.8k / 1.4k
CG-AL-X022medium2100.0 / 1003/3OK11.2s2.1k / 3.9k
CG-AL-X024medium1100.0 / 1003/3OK10.4s541 / 530
CG-AL-X025medium1100.0 / 1001/1OK10.2s601 / 528
CG-AL-X026medium1100.0 / 1003/3OK10.2s524 / 204
CG-AL-X027medium2100.0 / 1004/4OK10.6s1.1k / 618
CG-AL-X029medium1100.0 / 1002/2OK10.2s435 / 2.3k
CG-AL-X030medium1100.0 / 1002/2OK10.1s408 / 156
CG-AL-X031medium1100.0 / 1003/3OK10.7s465 / 217
CG-AL-X033hard1100.0 / 1002/2OK10.2s558 / 220
CG-AL-X034hard1100.0 / 1003/3OK10.2s486 / 314
CG-AL-X035hard262.5 / 1001/3OK10.8s1.3k / 2.3k
CG-AL-X037hard262.5 / 1000/4OK10.8s1.7k / 15k
CG-AL-X040hard20.0 / 1000/0FAIL4.3s2.2k / 5.5k
CG-AL-X041hard20.0 / 1000/0FAIL4.0s2.1k / 7.6k
CG-AL-X043hard20.0 / 1000/0FAIL3.8s2.3k / 13k
CG-AL-X044hard262.5 / 1001/3OK10.9s3.4k / 8.9k
CG-AL-X045hard1100.0 / 1003/3OK10.2s602 / 283
CG-AL-X046hard262.5 / 1000/2OK10.5s2.5k / 9.4k
CG-AL-X047hard1100.0 / 1002/2OK10.9s650 / 2.6k
CG-AL-X050hard1100.0 / 1002/2OK10.3s658 / 555
CG-AL-X051hard262.5 / 1000/2OK11.0s2.0k / 982
CG-AL-X052hard1100.0 / 1003/3OK10.2s582 / 1.4k
CG-AL-X055hard1100.0 / 1005/5OK10.2s546 / 372
CG-AL-X056hard1100.0 / 1005/5OK10.2s447 / 215
CG-AL-X057hard1100.0 / 1005/5OK10.2s411 / 151
CG-AL-X058hard1100.0 / 1005/5OK10.3s500 / 468
CG-AL-X059hard1100.0 / 1003/3OK10.3s511 / 121
CG-AL-X060hard1100.0 / 1003/3OK10.3s487 / 147
CG-AL-X061hard1100.0 / 1004/4OK10.2s572 / 192
CG-AL-X062hard1100.0 / 1004/4OK10.2s601 / 697
CG-AL-X063hard1100.0 / 1003/3OK10.4s559 / 1.3k
CG-AL-X064hard1100.0 / 1007/7OK10.1s457 / 396
CG-AL-X065hard1100.0 / 1006/6OK10.3s1.2k / 1.1k
CG-AL-X066hard1100.0 / 10014/14OK10.3s2.2k / 2.0k
CG-AL-X067hard262.5 / 1006/7OK10.6s2.9k / 16k
CG-AL-X068hard2100.0 / 10012/12OK11.0s9.1k / 6.6k
CG-AL-X069hard1100.0 / 1008/8OK10.4s1.9k / 3.0k
CG-AL-X070hard1100.0 / 10012/12OK10.4s1.9k / 1.4k
CG-AL-X071hard1100.0 / 1008/8OK10.3s2.2k / 2.1k
CG-AL-X072hard1100.0 / 1007/7OK10.4s2.1k / 1.6k
CG-AL-X073hard1100.0 / 1008/8OK10.7s2.5k / 2.3k
CG-AL-X074hard1100.0 / 1007/7OK10.5s2.6k / 32k
CG-AL-X075hard1100.0 / 1007/7OK10.3s1.4k / 3.0k
CG-AL-X076hard2100.0 / 10014/14OK10.7s5.8k / 21k
CG-AL-X077hard1100.0 / 10022/22OK10.3s2.6k / 2.3k
CG-AL-X078hard1100.0 / 10017/17OK10.2s2.0k / 1.6k
CG-AL-X079hard1100.0 / 10011/11OK10.5s2.0k / 2.1k
CG-AL-X080hard20.0 / 1000/0FAIL4.1s4.3k / 5.8k
CG-AL-X081hard1100.0 / 1008/8OK10.2s1.5k / 1.1k
CG-AL-X082hard1100.0 / 10015/15OK10.3s2.1k / 1.7k
CG-AL-X083hard1100.0 / 1009/9OK10.2s2.8k / 2.5k
CG-AL-X084hard1100.0 / 10010/10OK10.6s2.5k / 5.3k
CG-AL-X085hard1100.0 / 1007/7OK10.2s1.6k / 1.7k
CG-AL-X086hard1100.0 / 1006/6OK10.3s2.4k / 7.6k
CG-AL-X087hard1100.0 / 1003/3OK10.6s1.8k / 2.0k
CG-AL-X088hard1100.0 / 1006/6OK10.2s1.7k / 2.4k
CG-AL-X089hard1100.0 / 10011/11OK10.6s1.8k / 12k
CG-AL-X090hard262.5 / 1008/10OK11.3s3.7k / 20k
CG-AL-X091hard1100.0 / 1006/6OK10.0s941 / 616
CG-AL-X092hard1100.0 / 10015/15OK10.1s716 / 513
CG-AL-X093hard1100.0 / 10010/10OK10.4s1.7k / 1.5k
CG-AL-X094hard1100.0 / 1007/7OK10.5s1.3k / 1.0k
CG-AL-X095hard1100.0 / 1005/5OK10.1s1.3k / 1.0k
CG-AL-X096hard2100.0 / 10049/49OK12.0s13k / 14k
CG-AL-X097hard1100.0 / 10046/46OK11.4s6.0k / 5.5k
CG-AL-X098hard1100.0 / 10029/29OK10.6s4.8k / 4.8k
CG-AL-X099hard1100.0 / 10039/39OK12.4s6.4k / 10k
CG-AL-X100hard1100.0 / 10035/35OK10.7s6.0k / 13k
CG-AL-X101hard2100.0 / 10010/10OK10.9s7.0k / 17k
CG-AL-X102hard2100.0 / 1008/8OK11.0s3.8k / 1.6k
CG-AL-X103hard1100.0 / 1007/7OK10.2s1.2k / 894
CG-AL-X104hard1100.0 / 1006/6OK10.5s1.7k / 1.4k
CG-AL-X105hard1100.0 / 1006/6OK10.3s1.3k / 901
CG-AL-X106hard1100.0 / 1005/5OK10.3s1.5k / 1.7k
CG-AL-X107hard1100.0 / 1004/4OK10.1s1.4k / 1.7k
CG-AL-X108hard1100.0 / 1006/6OK10.5s1.2k / 654
CG-AL-X109hard1100.0 / 1005/5OK10.5s916 / 1.0k
CG-AL-X110hard1100.0 / 10017/17OK10.2s2.1k / 1.8k
CG-AL-X111hard1100.0 / 1008/8OK10.7s2.0k / 6.3k
CG-AL-X112hard2100.0 / 10012/12OK11.1s4.2k / 12k
CG-AL-X113hard1100.0 / 10013/13OK10.7s1.3k / 991
CG-AL-X114hard1100.0 / 1007/7OK10.2s1.2k / 994
CG-AL-X115hard2100.0 / 10013/13OK11.1s1.9k / 1.5k
CG-AL-X116hard1100.0 / 10017/17OK10.6s1.5k / 2.0k
CG-AL-X117hard1100.0 / 1008/8OK10.6s1.7k / 1.6k
CG-AL-X118hard1100.0 / 10017/17OK10.6s2.4k / 4.8k
CG-AL-X119hard1100.0 / 10015/15OK10.4s2.8k / 2.7k
CG-AL-X120hard1100.0 / 10012/12OK10.4s2.2k / 2.0k
CG-AL-X121hard1100.0 / 1006/6OK10.1s1.7k / 1.4k
CG-AL-X122hard1100.0 / 10010/10OK10.3s2.6k / 3.2k
CG-AL-X123hard1100.0 / 1005/5OK10.2s981 / 507
CG-AL-X124hard1100.0 / 10010/10OK10.4s1.7k / 1.3k
CG-AL-X125hard1100.0 / 1008/8OK10.7s2.3k / 4.2k
CG-AL-X126hard1100.0 / 10014/14OK10.0s1.2k / 1.8k
CG-AL-X127hard1100.0 / 1005/5OK10.4s1.1k / 739
CG-AL-X128hard1100.0 / 1008/8OK10.2s2.0k / 1.6k
CG-AL-X129hard1100.0 / 10014/14OK10.6s2.0k / 1.8k
CG-AL-X130hard1100.0 / 1005/5OK10.1s845 / 6.9k
CG-AL-X131hard1100.0 / 10013/13OK10.3s1.6k / 5.4k
CG-AL-X132hard1100.0 / 10010/10OK10.4s1.2k / 778
CG-AL-X133hard20.0 / 1000/0FAIL4.4s6.0k / 32k
CG-AL-X134hard1100.0 / 1006/6OK10.7s2.0k / 2.6k
CG-AL-X135hard1100.0 / 1004/4OK10.2s1.4k / 999
CG-AL-X136hard1100.0 / 1007/7OK10.2s1.2k / 9.1k
CG-AL-X137hard1100.0 / 1004/4OK10.5s1.5k / 2.7k
CG-AL-X138hard1100.0 / 1009/9OK10.9s2.4k / 3.1k
CG-AL-X139hard1100.0 / 10011/11OK10.4s2.8k / 2.7k
CG-AL-X140hard1100.0 / 1007/7OK10.6s2.5k / 14k
CG-AL-X141hard20.0 / 1000/0FAIL799ms15k / 26k
CG-AL-X142hard20.0 / 1000/0FAIL4.4s15k / 41k
CG-AL-X143hard1100.0 / 10035/35OK15.5s7.2k / 7.1k
CG-AL-X144hard1100.0 / 10043/43OK11.2s6.4k / 7.7k
CG-AL-X145hard1100.0 / 10032/32OK10.9s7.4k / 7.4k
CG-AL-X146hard1100.0 / 1009/9OK10.5s2.9k / 11k
CG-AL-X147hard1100.0 / 1008/8OK10.3s2.2k / 1.9k
CG-AL-X148hard1100.0 / 1006/6OK10.6s1.9k / 1.4k
CG-AL-X149hard1100.0 / 1007/7OK10.4s1.9k / 1.6k
CG-AL-X150hard1100.0 / 1009/9OK11.0s3.2k / 12k
CG-AL-X151hard1100.0 / 1006/6OK10.2s1.4k / 975
CG-AL-X152hard1100.0 / 1008/8OK10.2s1.9k / 1.4k
CG-AL-X153hard1100.0 / 1009/9OK14.1s1.5k / 1.7k
CG-AL-X154hard1100.0 / 1009/9OK10.6s2.1k / 1.8k
CG-AL-X155hard1100.0 / 10011/11OK10.2s1.5k / 1.3k
CG-AL-X156hard1100.0 / 1007/7OK10.4s1.5k / 964
CG-AL-X157hard1100.0 / 10010/10OK10.4s2.2k / 1.8k
CG-AL-X158hard1100.0 / 1007/7OK10.2s1.3k / 779
CG-AL-X159hard1100.0 / 1007/7OK10.6s1.4k / 968
CG-AL-X160hard1100.0 / 10013/13OK10.5s2.0k / 2.1k
CG-AL-X161hard1100.0 / 10010/10OK10.7s2.4k / 2.4k
CG-AL-X162hard1100.0 / 1007/7OK10.3s1.6k / 1.3k
CG-AL-X163hard1100.0 / 1007/7OK10.3s1.7k / 1.5k
CG-AL-X164hard1100.0 / 1007/7OK10.6s1.5k / 1.3k
CG-AL-X165hard20.0 / 1000/0FAIL4.1s11k / 21k
CG-AL-X166hard20.0 / 1000/0FAIL740ms6.8k / 4.2k
CG-AL-X167hard20.0 / 1000/0FAIL173ms6.3k / 14k
CG-AL-X168hard1100.0 / 1009/9OK11.1s2.2k / 5.9k
CG-AL-X169hard20.0 / 1000/0FAIL138ms6.6k / 11k
CG-AL-X170hard1100.0 / 10011/11OK10.9s5.2k / 9.7k
CG-AL-X171hard1100.0 / 1009/9OK10.8s2.5k / 10k
CG-AL-X172hard20.0 / 1000/0FAIL133ms11k / 20k
CG-AL-X173hard1100.0 / 10019/19OK12.1s5.4k / 47k
CG-AL-X174hard20.0 / 1000/0FAIL132ms15k / 14k
CG-AL-X185hard20.0 / 1000/0FAIL131ms12k / 8.3k
CG-AL-X187hard20.0 / 1000/0FAIL130ms11k / 7.4k
CG-AL-X194hard1100.0 / 10050/50OK11.4s8.7k / 10k
CG-AL-X211hard20.0 / 1000/0FAIL131ms16k / 21k
CG-AL-X214hard20.0 / 1000/0FAIL129ms14k / 12k
CG-AL-X218hard20.0 / 1000/0FAIL132ms13k / 12k
CG-AL-X234hard20.0 / 1000/0FAIL127ms16k / 13k
CG-AL-X239hard20.0 / 1000/0FAIL134ms19k / 20k
CG-AL-X244hard20.0 / 1000/0FAIL174ms20k / 23k
CG-AL-X245hard20.0 / 1000/0FAIL125ms20k / 19k
CG-AL-X248hard20.0 / 1000/0FAIL122ms19k / 16k
CG-AL-X249hard20.0 / 1000/0FAIL147ms17k / 19k
CG-AL-X254hard20.0 / 1000/0FAIL129ms23k / 24k
CG-AL-X257hard20.0 / 1000/0FAIL0ms18k / 86k
CG-AL-X263hard20.0 / 1000/0FAIL125ms16k / 21k
CG-AL-X264hard20.0 / 1000/0FAIL124ms19k / 33k
CG-AL-X270hard20.0 / 1000/0FAIL125ms31k / 36k
CG-AL-X271hard20.0 / 1000/0FAIL122ms27k / 27k
CG-AL-X272hard20.0 / 1000/0FAIL235ms27k / 18k
CG-AL-X274hard20.0 / 1000/0FAIL232ms25k / 23k
CG-AL-X276hard20.0 / 1000/0FAIL123ms26k / 26k
CG-AL-X278hard20.0 / 1000/0FAIL237ms26k / 27k
CG-AL-X283hard20.0 / 1000/0FAIL235ms26k / 56k
CG-AL-X289hard20.0 / 1000/0FAIL125ms20k / 18k
CG-AL-X290hard20.0 / 1000/0FAIL243ms24k / 39k
CG-AL-X292hard20.0 / 1000/0FAIL238ms21k / 24k
CG-AL-X293hard20.0 / 1000/0FAIL132ms18k / 17k
CG-AL-X296hard20.0 / 1000/0FAIL249ms29k / 31k
CG-AL-X298hard20.0 / 1000/0FAIL248ms16k / 50k