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.

72.4% 168/232 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.

60.7 / 100
Cost $44.59
Tokens 578k / 9.9M input / output, all attempts
Duration 50m 42s
Filter:
Per-task results for run ef24c680-60be-43c2-8d4f-fd199d5902b3
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.4s265 / 4.0k
CG-AL-E006easy1100.0 / 1007/7OK31.0s312 / 6.6k
CG-AL-E010easy262.5 / 1000/1OK33.6s783 / 26k
CG-AL-E050easy2100.0 / 10013/13OK18.2s1.9k / 41k
CG-AL-E052easy1100.0 / 10016/16OK11.3s359 / 2.7k
CG-AL-E054easy2100.0 / 1009/9OK17.5s1.4k / 23k
CG-AL-E056easy2100.0 / 10015/15OK11.1s1.8k / 43k
CG-AL-H007hard20.0 / 1000/0FAIL4.1s1.8k / 43k
CG-AL-H011hard2100.0 / 1006/6OK10.9s1.1k / 78k
CG-AL-H014hard20.0 / 1000/0FAIL3.6s1.5k / 25k
CG-AL-H017hard20.0 / 1000/0FAIL8.7s1.2k / 31k
CG-AL-H020hard2100.0 / 10010/10OK10.6s2.2k / 53k
CG-AL-H021hard2100.0 / 10020/20OK11.0s2.0k / 35k
CG-AL-H023hard20.0 / 1000/0FAIL0ms2.4k / 128k
CG-AL-H027hard2100.0 / 1004/4OK11.6s2.7k / 98k
CG-AL-H029hard20.0 / 1000/0FAIL4.1s1.6k / 116k
CG-AL-H030hard2100.0 / 10010/10OK10.9s2.5k / 69k
CG-AL-H031hard20.0 / 1000/0FAIL3.9s3.3k / 56k
CG-AL-H034hard2100.0 / 1003/3OK13.3s1.3k / 11k
CG-AL-H036hard20.0 / 1000/0FAIL3.8s959 / 49k
CG-AL-H037hard20.0 / 1000/0FAIL4.8s1.4k / 72k
CG-AL-H041hard1100.0 / 1003/3OK11.5s587 / 58k
CG-AL-H050hard262.5 / 1002/3OK14.1s1.2k / 70k
CG-AL-H054hard2100.0 / 1005/5OK12.2s2.0k / 33k
CG-AL-H056hard20.0 / 1000/0FAIL3.8s1.4k / 47k
CG-AL-M001medium20.0 / 1000/0FAIL4.1s1.8k / 51k
CG-AL-M003medium262.5 / 1000/1OK27.0s830 / 119k
CG-AL-M004medium1100.0 / 10012/12OK28.7s459 / 47k
CG-AL-M006medium20.0 / 1000/0FAIL0ms4.1k / 128k
CG-AL-M007medium20.0 / 1000/0FAIL0ms860 / 128k
CG-AL-M008medium20.0 / 1000/0FAIL0ms988 / 128k
CG-AL-M009medium20.0 / 1000/0FAIL0ms4.8k / 128k
CG-AL-M010medium20.0 / 1000/0FAIL3.9s3.8k / 89k
CG-AL-M020medium2100.0 / 10017/17OK11.0s2.5k / 82k
CG-AL-M023medium1100.0 / 10011/11OK11.2s490 / 8.6k
CG-AL-M025medium1100.0 / 1008/8OK11.0s409 / 22k
CG-AL-M026medium1100.0 / 1008/8OK11.7s377 / 52k
CG-AL-M027medium20.0 / 1000/0FAIL3.9s3.8k / 84k
CG-AL-M028medium2100.0 / 1003/3OK25.4s1.1k / 49k
CG-AL-M031medium211.1 / 1000/0FAIL3.8s2.6k / 38k
CG-AL-M034medium1100.0 / 1002/2OK10.9s423 / 32k
CG-AL-M036medium211.1 / 1000/0FAIL4.0s1.7k / 54k
CG-AL-M040medium1100.0 / 1002/2OK11.5s313 / 12k
CG-AL-M042medium1100.0 / 1008/8OK10.7s507 / 22k
CG-AL-X001hard1100.0 / 1002/2OK11.1s318 / 12k
CG-AL-X002hard2100.0 / 1004/4OK11.0s2.8k / 76k
CG-AL-X003hard262.5 / 1002/3OK10.6s991 / 65k
CG-AL-X004medium1100.0 / 1003/3OK11.2s372 / 21k
CG-AL-X005hard1100.0 / 1002/2OK11.1s339 / 9.7k
CG-AL-X006hard1100.0 / 1003/3OK11.2s402 / 23k
CG-AL-X007hard1100.0 / 1002/2OK1m 47s381 / 16k
CG-AL-X008hard1100.0 / 1001/1OK11.2s433 / 56k
CG-AL-X009medium1100.0 / 1002/2OK11.2s324 / 5.5k
CG-AL-X010medium1100.0 / 1003/3OK11.8s293 / 5.4k
CG-AL-X011medium1100.0 / 1002/2OK10.9s371 / 6.0k
CG-AL-X012hard1100.0 / 1001/1OK10.8s395 / 36k
CG-AL-X013hard1100.0 / 1002/2OK10.6s271 / 6.8k
CG-AL-X014medium1100.0 / 1004/4OK12.1s302 / 17k
CG-AL-X017medium2100.0 / 1003/3OK11.3s1.5k / 1.6k
CG-AL-X018medium1100.0 / 1003/3OK11.3s400 / 12k
CG-AL-X019medium1100.0 / 1003/3OK12.4s376 / 6.3k
CG-AL-X022medium2100.0 / 1003/3OK11.0s1.4k / 53k
CG-AL-X024medium2100.0 / 1003/3OK11.0s1.1k / 14k
CG-AL-X025medium2100.0 / 1001/1OK10.8s1.3k / 56k
CG-AL-X026medium1100.0 / 1003/3OK11.0s339 / 2.5k
CG-AL-X027medium1100.0 / 1004/4OK10.9s268 / 7.9k
CG-AL-X029medium1100.0 / 1002/2OK11.0s284 / 24k
CG-AL-X030medium1100.0 / 1002/2OK11.2s248 / 1.2k
CG-AL-X031medium1100.0 / 1003/3OK11.8s309 / 1.5k
CG-AL-X033hard1100.0 / 1002/2OK11.5s363 / 4.2k
CG-AL-X034hard1100.0 / 1003/3OK11.4s316 / 13k
CG-AL-X035hard1100.0 / 1003/3OK12.1s345 / 23k
CG-AL-X037hard262.5 / 1000/4OK11.0s2.3k / 88k
CG-AL-X040hard20.0 / 1000/0FAIL0ms2.6k / 110k
CG-AL-X041hard20.0 / 1000/0FAIL0ms2.7k / 102k
CG-AL-X043hard20.0 / 1000/0FAIL4.1s484 / 124k
CG-AL-X044hard262.5 / 1000/3OK11.8s1.6k / 109k
CG-AL-X045hard1100.0 / 1003/3OK11.0s384 / 14k
CG-AL-X046hard2100.0 / 1002/2OK10.9s1.8k / 30k
CG-AL-X047hard20.0 / 1000/0FAIL4.0s2.0k / 102k
CG-AL-X050hard1100.0 / 1002/2OK12.2s422 / 16k
CG-AL-X051hard1100.0 / 1002/2OK11.5s533 / 27k
CG-AL-X052hard1100.0 / 1003/3OK11.1s371 / 20k
CG-AL-X055hard1100.0 / 1005/5OK10.9s353 / 2.6k
CG-AL-X056hard2100.0 / 1005/5OK10.7s768 / 8.8k
CG-AL-X057hard1100.0 / 1005/5OK11.0s259 / 5.7k
CG-AL-X058hard1100.0 / 1005/5OK11.1s326 / 15k
CG-AL-X059hard1100.0 / 1003/3OK11.6s342 / 1.4k
CG-AL-X060hard1100.0 / 1003/3OK11.5s314 / 17k
CG-AL-X061hard1100.0 / 1004/4OK11.1s380 / 2.4k
CG-AL-X062hard1100.0 / 1004/4OK11.6s370 / 6.3k
CG-AL-X063hard1100.0 / 1003/3OK11.5s374 / 4.6k
CG-AL-X064hard1100.0 / 1007/7OK10.9s286 / 11k
CG-AL-X065hard1100.0 / 1006/6OK11.1s730 / 8.0k
CG-AL-X066hard1100.0 / 10014/14OK11.3s1.3k / 6.6k
CG-AL-X067hard262.5 / 1006/7OK10.6s1.8k / 52k
CG-AL-X068hard1100.0 / 10012/12OK11.6s1.2k / 22k
CG-AL-X069hard1100.0 / 1008/8OK11.0s1.1k / 39k
CG-AL-X070hard1100.0 / 10012/12OK11.6s1.2k / 15k
CG-AL-X071hard1100.0 / 1008/8OK11.5s1.4k / 6.4k
CG-AL-X072hard1100.0 / 1007/7OK11.0s1.2k / 3.5k
CG-AL-X073hard1100.0 / 1008/8OK11.1s1.5k / 4.9k
CG-AL-X074hard2100.0 / 1007/7OK10.7s3.5k / 64k
CG-AL-X075hard1100.0 / 1007/7OK11.0s838 / 28k
CG-AL-X076hard2100.0 / 10014/14OK10.9s3.6k / 61k
CG-AL-X077hard1100.0 / 10022/22OK11.3s1.5k / 7.2k
CG-AL-X078hard1100.0 / 10017/17OK11.2s1.2k / 1.3k
CG-AL-X079hard1100.0 / 10011/11OK11.2s1.2k / 14k
CG-AL-X080hard20.0 / 1000/0FAIL3.5s2.6k / 38k
CG-AL-X081hard1100.0 / 1008/8OK11.1s938 / 3.3k
CG-AL-X082hard1100.0 / 10015/15OK12.6s1.3k / 1.2k
CG-AL-X083hard1100.0 / 1009/9OK11.0s1.5k / 3.5k
CG-AL-X084hard1100.0 / 10010/10OK11.7s1.5k / 19k
CG-AL-X085hard1100.0 / 1007/7OK11.1s1.0k / 12k
CG-AL-X086hard1100.0 / 1006/6OK10.9s1.4k / 21k
CG-AL-X087hard1100.0 / 1003/3OK10.8s1.1k / 10k
CG-AL-X088hard1100.0 / 1006/6OK10.8s997 / 6.8k
CG-AL-X089hard1100.0 / 10011/11OK11.5s1.1k / 18k
CG-AL-X090hard262.5 / 1009/10OK11.0s2.2k / 57k
CG-AL-X091hard1100.0 / 1006/6OK11.1s583 / 1.2k
CG-AL-X092hard1100.0 / 10015/15OK11.0s454 / 1.1k
CG-AL-X093hard2100.0 / 10010/10OK15.8s2.7k / 16k
CG-AL-X094hard1100.0 / 1007/7OK10.9s772 / 1.8k
CG-AL-X095hard2100.0 / 1005/5OK11.1s2.3k / 45k
CG-AL-X096hard2100.0 / 10049/49OK13.7s7.2k / 44k
CG-AL-X097hard1100.0 / 10046/46OK12.0s3.5k / 12k
CG-AL-X098hard1100.0 / 10029/29OK11.9s2.7k / 7.7k
CG-AL-X099hard1100.0 / 10039/39OK13.5s3.7k / 49k
CG-AL-X100hard1100.0 / 10035/35OK11.6s3.6k / 25k
CG-AL-X101hard1100.0 / 10010/10OK11.4s1.1k / 10k
CG-AL-X102hard2100.0 / 1008/8OK10.9s2.4k / 20k
CG-AL-X103hard1100.0 / 1007/7OK11.0s736 / 1.7k
CG-AL-X104hard1100.0 / 1006/6OK11.2s1.1k / 2.3k
CG-AL-X105hard1100.0 / 1006/6OK11.1s793 / 5.6k
CG-AL-X106hard1100.0 / 1005/5OK11.1s905 / 26k
CG-AL-X107hard1100.0 / 1004/4OK11.0s818 / 9.8k
CG-AL-X108hard1100.0 / 1006/6OK12.3s736 / 2.7k
CG-AL-X109hard1100.0 / 1005/5OK11.6s557 / 7.2k
CG-AL-X110hard1100.0 / 10017/17OK11.1s1.2k / 2.0k
CG-AL-X111hard20.0 / 1000/0FAIL3.7s2.6k / 54k
CG-AL-X112hard2100.0 / 10012/12OK12.6s2.2k / 68k
CG-AL-X113hard1100.0 / 10013/13OK11.6s713 / 9.0k
CG-AL-X114hard1100.0 / 1007/7OK11.4s736 / 3.9k
CG-AL-X115hard1100.0 / 10013/13OK12.6s481 / 37k
CG-AL-X116hard1100.0 / 10017/17OK11.3s935 / 27k
CG-AL-X117hard1100.0 / 1008/8OK11.6s1.0k / 2.7k
CG-AL-X118hard1100.0 / 10017/17OK12.0s1.4k / 17k
CG-AL-X119hard1100.0 / 10015/15OK11.5s1.7k / 2.3k
CG-AL-X120hard1100.0 / 10012/12OK12.4s1.2k / 4.4k
CG-AL-X121hard1100.0 / 1006/6OK11.6s1.0k / 1.6k
CG-AL-X122hard20.0 / 1000/0FAIL0ms3.5k / 83k
CG-AL-X123hard1100.0 / 1005/5OK11.4s612 / 5.2k
CG-AL-X124hard1100.0 / 10010/10OK11.9s1.0k / 2.6k
CG-AL-X125hard1100.0 / 1008/8OK11.6s1.4k / 42k
CG-AL-X126hard1100.0 / 10014/14OK12.9s718 / 12k
CG-AL-X127hard1100.0 / 1005/5OK11.6s677 / 3.3k
CG-AL-X128hard1100.0 / 1008/8OK11.3s1.2k / 1.3k
CG-AL-X129hard1100.0 / 10014/14OK11.4s1.2k / 2.8k
CG-AL-X130hard262.5 / 1002/5OK19.6s1.2k / 96k
CG-AL-X131hard1100.0 / 10013/13OK11.1s949 / 11k
CG-AL-X132hard1100.0 / 10010/10OK10.9s719 / 774
CG-AL-X133hard20.0 / 1000/0FAIL0ms3.6k / 93k
CG-AL-X134hard1100.0 / 1006/6OK11.8s1.2k / 30k
CG-AL-X135hard1100.0 / 1004/4OK12.2s879 / 1.8k
CG-AL-X136hard1100.0 / 1007/7OK10.9s769 / 3.4k
CG-AL-X137hard1100.0 / 1004/4OK11.0s931 / 7.8k
CG-AL-X138hard1100.0 / 1009/9OK11.4s1.4k / 18k
CG-AL-X139hard1100.0 / 10011/11OK11.1s1.6k / 3.3k
CG-AL-X140hard1100.0 / 1007/7OK11.3s1.5k / 60k
CG-AL-X141hard1100.0 / 10039/39OK12.0s3.6k / 15k
CG-AL-X142hard20.0 / 1000/0FAIL0ms7.8k / 128k
CG-AL-X143hard262.5 / 10033/35OK16.2s8.2k / 58k
CG-AL-X144hard1100.0 / 10043/43OK12.4s3.7k / 21k
CG-AL-X145hard1100.0 / 10032/32OK11.9s4.2k / 6.3k
CG-AL-X146hard1100.0 / 1009/9OK11.5s1.7k / 63k
CG-AL-X147hard1100.0 / 1008/8OK11.5s1.3k / 8.1k
CG-AL-X148hard1100.0 / 1006/6OK11.7s1.2k / 974
CG-AL-X149hard1100.0 / 1007/7OK12.1s1.1k / 10k
CG-AL-X150hard1100.0 / 1009/9OK11.7s1.9k / 53k
CG-AL-X151hard1100.0 / 1006/6OK11.0s827 / 1.1k
CG-AL-X152hard1100.0 / 1008/8OK11.5s1.1k / 1.6k
CG-AL-X153hard1100.0 / 1009/9OK15.8s901 / 45k
CG-AL-X154hard1100.0 / 1009/9OK12.0s1.2k / 7.0k
CG-AL-X155hard1100.0 / 10011/11OK11.1s949 / 4.2k
CG-AL-X156hard1100.0 / 1007/7OK11.2s903 / 652
CG-AL-X157hard1100.0 / 10010/10OK11.4s1.3k / 4.0k
CG-AL-X158hard1100.0 / 1007/7OK11.3s819 / 632
CG-AL-X159hard1100.0 / 1007/7OK11.5s860 / 8.9k
CG-AL-X160hard1100.0 / 10013/13OK11.4s1.2k / 4.5k
CG-AL-X161hard1100.0 / 10010/10OK11.5s1.4k / 2.0k
CG-AL-X162hard1100.0 / 1007/7OK11.3s970 / 6.0k
CG-AL-X163hard1100.0 / 1007/7OK11.4s1.0k / 2.7k
CG-AL-X164hard2100.0 / 1007/7OK10.9s2.0k / 38k
CG-AL-X165hard20.0 / 1000/0FAIL4.1s6.2k / 104k
CG-AL-X166hard1100.0 / 10014/14OK12.7s1.6k / 4.9k
CG-AL-X167hard20.0 / 1000/0FAIL0ms3.7k / 91k
CG-AL-X168hard2100.0 / 1009/9OK12.4s3.6k / 70k
CG-AL-X169hard20.0 / 1000/0FAIL0ms4.0k / 79k
CG-AL-X170hard20.0 / 1000/0FAIL0ms3.8k / 128k
CG-AL-X171hard2100.0 / 1009/9OK12.0s3.6k / 93k
CG-AL-X172hard1100.0 / 10011/11OK11.5s2.2k / 49k
CG-AL-X173hard20.0 / 1000/0FAIL3.8s6.9k / 104k
CG-AL-X174hard1100.0 / 10016/16OK11.9s3.9k / 35k
CG-AL-X185hard2100.0 / 10043/43OK11.5s7.1k / 109k
CG-AL-X187hard20.0 / 1000/0FAIL0ms7.8k / 105k
CG-AL-X194hard20.0 / 1000/0FAIL0ms10k / 128k
CG-AL-X211hard20.0 / 1000/0FAIL0ms7.7k / 128k
CG-AL-X214hard20.0 / 1000/0FAIL0ms8.3k / 92k
CG-AL-X218hard20.0 / 1000/0FAIL0ms8.1k / 102k
CG-AL-X234hard2100.0 / 10035/35OK12.0s9.7k / 107k
CG-AL-X239hard20.0 / 1000/0FAIL0ms5.7k / 128k
CG-AL-X244hard20.0 / 1000/0FAIL0ms6.0k / 128k
CG-AL-X245hard2100.0 / 10063/63OK12.3s12k / 87k
CG-AL-X248hard20.0 / 1000/0FAIL0ms5.0k / 128k
CG-AL-X249hard20.0 / 1000/0FAIL0ms9.9k / 124k
CG-AL-X254hard2100.0 / 10070/70OK12.8s13k / 101k
CG-AL-X257hard20.0 / 1000/0FAIL0ms4.9k / 128k
CG-AL-X263hard20.0 / 1000/0FAIL0ms5.3k / 128k
CG-AL-X264hard20.0 / 1000/0FAIL0ms5.9k / 128k
CG-AL-X270hard20.0 / 1000/0FAIL0ms19k / 111k
CG-AL-X271hard20.0 / 1000/0FAIL0ms8.7k / 128k
CG-AL-X272hard2100.0 / 10079/79OK12.4s14k / 90k
CG-AL-X274hard20.0 / 1000/0FAIL0ms6.8k / 128k
CG-AL-X276hard2100.0 / 10078/78OK12.7s14k / 70k
CG-AL-X278hard20.0 / 1000/0FAIL0ms15k / 120k
CG-AL-X283hard20.0 / 1000/0FAIL0ms7.6k / 128k
CG-AL-X289hard20.0 / 1000/0FAIL0ms5.9k / 128k
CG-AL-X290hard20.0 / 1000/0FAIL0ms6.0k / 128k
CG-AL-X292hard2100.0 / 10057/57OK11.8s11k / 111k
CG-AL-X293hard20.0 / 1000/0FAIL3.6s10k / 72k
CG-AL-X296hard20.0 / 1000/0FAIL3.9s16k / 106k
CG-AL-X298hard20.0 / 1000/0FAIL0ms5.3k / 128k