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.

57.8% 134/232 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.

49.0 / 100
Cost $26.49
Tokens 341k / 5.9M input / output, all attempts
Duration 39m 38s
Filter:
Per-task results for run 4b623ade-d42d-4504-9488-96daefde9816
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.3s265 / 2.2k
CG-AL-E006easy1100.0 / 1007/7OK30.3s312 / 3.9k
CG-AL-E010easy20.0 / 1000/0FAIL0ms287 / 1.3k
CG-AL-E050easy20.0 / 1000/0FAIL0ms383 / 21k
CG-AL-E052easy1100.0 / 10016/16OK11.1s359 / 1.9k
CG-AL-E054easy20.0 / 1000/0FAIL0ms379 / 13k
CG-AL-E056easy20.0 / 1000/0FAIL0ms439 / 22k
CG-AL-H007hard1100.0 / 10011/11OK11.2s544 / 36k
CG-AL-H011hard20.0 / 1000/0FAIL0ms358 / 31k
CG-AL-H014hard20.0 / 1000/0FAIL0ms435 / 20k
CG-AL-H017hard20.0 / 1000/0FAIL0ms363 / 33k
CG-AL-H020hard20.0 / 1000/0FAIL0ms475 / 30k
CG-AL-H021hard20.0 / 1000/0FAIL0ms603 / 8.7k
CG-AL-H023hard20.0 / 1000/0FAIL0ms1.2k / 64k
CG-AL-H027hard1100.0 / 1004/4OK11.5s754 / 57k
CG-AL-H029hard20.0 / 1000/0FAIL0ms820 / 64k
CG-AL-H030hard20.0 / 1000/0FAIL0ms675 / 63k
CG-AL-H031hard20.0 / 1000/0FAIL0ms957 / 43k
CG-AL-H034hard20.0 / 1000/0FAIL0ms446 / 15k
CG-AL-H036hard20.0 / 1000/0FAIL0ms389 / 14k
CG-AL-H037hard20.0 / 1000/0FAIL0ms506 / 13k
CG-AL-H041hard1100.0 / 1003/3OK12.9s587 / 48k
CG-AL-H050hard20.0 / 1000/0FAIL0ms512 / 45k
CG-AL-H054hard20.0 / 1000/0FAIL0ms531 / 11k
CG-AL-H056hard20.0 / 1000/0FAIL0ms639 / 16k
CG-AL-M001medium20.0 / 1000/0FAIL0ms478 / 35k
CG-AL-M003medium20.0 / 1000/0FAIL0ms426 / 37k
CG-AL-M004medium20.0 / 1000/0FAIL0ms459 / 50k
CG-AL-M006medium20.0 / 1000/0FAIL0ms421 / 64k
CG-AL-M007medium20.0 / 1000/0FAIL0ms441 / 64k
CG-AL-M008medium20.0 / 1000/0FAIL0ms505 / 64k
CG-AL-M009medium20.0 / 1000/0FAIL0ms438 / 64k
CG-AL-M010medium20.0 / 1000/0FAIL0ms605 / 54k
CG-AL-M020medium20.0 / 1000/0FAIL0ms558 / 64k
CG-AL-M023medium1100.0 / 10011/11OK11.5s490 / 15k
CG-AL-M025medium20.0 / 1000/0FAIL0ms409 / 20k
CG-AL-M026medium1100.0 / 1008/8OK11.1s377 / 35k
CG-AL-M027medium20.0 / 1000/0FAIL0ms703 / 37k
CG-AL-M028medium20.0 / 1000/0FAIL0ms364 / 24k
CG-AL-M031medium20.0 / 1000/0FAIL0ms696 / 27k
CG-AL-M034medium1100.0 / 1002/2OK11.0s423 / 22k
CG-AL-M036medium20.0 / 1000/0FAIL0ms540 / 17k
CG-AL-M040medium20.0 / 1000/0FAIL0ms313 / 17k
CG-AL-M042medium1100.0 / 1008/8OK11.8s507 / 27k
CG-AL-X001hard1100.0 / 1002/2OK11.7s318 / 8.0k
CG-AL-X002hard20.0 / 1000/0FAIL0ms499 / 64k
CG-AL-X003hard20.0 / 1000/0FAIL0ms248 / 27k
CG-AL-X004medium1100.0 / 1003/3OK11.4s372 / 18k
CG-AL-X005hard1100.0 / 1002/2OK11.5s339 / 12k
CG-AL-X006hard1100.0 / 1003/3OK11.7s402 / 26k
CG-AL-X007hard1100.0 / 1002/2OK1m 39s381 / 24k
CG-AL-X008hard1100.0 / 1001/1OK13.0s433 / 56k
CG-AL-X009medium1100.0 / 1002/2OK12.0s324 / 20k
CG-AL-X010medium1100.0 / 1003/3OK11.6s293 / 1.1k
CG-AL-X011medium1100.0 / 1002/2OK11.4s371 / 11k
CG-AL-X012hard1100.0 / 1001/1OK11.6s395 / 38k
CG-AL-X013hard1100.0 / 1002/2OK11.2s271 / 6.7k
CG-AL-X014medium1100.0 / 1004/4OK11.9s302 / 20k
CG-AL-X017medium20.0 / 1000/0FAIL0ms264 / 1.9k
CG-AL-X018medium1100.0 / 1003/3OK12.5s400 / 16k
CG-AL-X019medium1100.0 / 1003/3OK11.2s376 / 9.6k
CG-AL-X022medium20.0 / 1000/0FAIL0ms285 / 15k
CG-AL-X024medium1100.0 / 1003/3OK12.9s344 / 19k
CG-AL-X025medium1100.0 / 1001/1OK11.5s388 / 34k
CG-AL-X026medium1100.0 / 1003/3OK11.6s339 / 1.9k
CG-AL-X027medium1100.0 / 1004/4OK11.6s268 / 11k
CG-AL-X029medium1100.0 / 1002/2OK11.5s284 / 36k
CG-AL-X030medium1100.0 / 1002/2OK11.4s248 / 7.2k
CG-AL-X031medium1100.0 / 1003/3OK13.2s309 / 8.0k
CG-AL-X033hard1100.0 / 1002/2OK11.5s363 / 8.2k
CG-AL-X034hard20.0 / 1000/0FAIL0ms316 / 24k
CG-AL-X035hard20.0 / 1000/0FAIL0ms345 / 34k
CG-AL-X037hard20.0 / 1000/0FAIL0ms423 / 43k
CG-AL-X040hard1100.0 / 1004/4OK13.1s569 / 48k
CG-AL-X041hard20.0 / 1000/0FAIL0ms461 / 42k
CG-AL-X043hard20.0 / 1000/0FAIL0ms253 / 62k
CG-AL-X044hard20.0 / 1000/0FAIL0ms388 / 53k
CG-AL-X045hard1100.0 / 1003/3OK12.0s384 / 11k
CG-AL-X046hard1100.0 / 1002/2OK11.6s388 / 30k
CG-AL-X047hard20.0 / 1000/0FAIL0ms404 / 44k
CG-AL-X050hard1100.0 / 1002/2OK12.0s422 / 8.4k
CG-AL-X051hard1100.0 / 1002/2OK11.9s533 / 19k
CG-AL-X052hard1100.0 / 1003/3OK12.4s371 / 12k
CG-AL-X055hard1100.0 / 1005/5OK11.8s353 / 14k
CG-AL-X056hard1100.0 / 1005/5OK11.6s288 / 8.1k
CG-AL-X057hard1100.0 / 1005/5OK11.4s259 / 3.4k
CG-AL-X058hard1100.0 / 1005/5OK11.4s326 / 24k
CG-AL-X059hard1100.0 / 1003/3OK11.1s342 / 1.8k
CG-AL-X060hard1100.0 / 1003/3OK10.9s314 / 13k
CG-AL-X061hard1100.0 / 1004/4OK11.0s380 / 3.3k
CG-AL-X062hard1100.0 / 1004/4OK11.0s370 / 12k
CG-AL-X063hard1100.0 / 1003/3OK11.0s374 / 17k
CG-AL-X064hard1100.0 / 1007/7OK10.7s286 / 11k
CG-AL-X065hard1100.0 / 1006/6OK10.7s730 / 4.8k
CG-AL-X066hard1100.0 / 10014/14OK11.1s1.3k / 4.2k
CG-AL-X067hard20.0 / 1000/0FAIL0ms628 / 16k
CG-AL-X068hard20.0 / 1000/0FAIL0ms1.2k / 24k
CG-AL-X069hard20.0 / 1000/0FAIL0ms1.1k / 29k
CG-AL-X070hard1100.0 / 10012/12OK11.2s1.2k / 7.3k
CG-AL-X071hard1100.0 / 1008/8OK16.2s1.4k / 4.9k
CG-AL-X072hard1100.0 / 1007/7OK11.4s1.2k / 4.7k
CG-AL-X073hard1100.0 / 1008/8OK11.5s1.5k / 14k
CG-AL-X074hard20.0 / 1000/0FAIL0ms1.6k / 60k
CG-AL-X075hard1100.0 / 1007/7OK11.0s838 / 38k
CG-AL-X076hard20.0 / 1000/0FAIL0ms967 / 38k
CG-AL-X077hard1100.0 / 10022/22OK11.1s1.5k / 11k
CG-AL-X078hard1100.0 / 10017/17OK11.1s1.2k / 1.6k
CG-AL-X079hard1100.0 / 10011/11OK11.3s1.2k / 45k
CG-AL-X080hard20.0 / 1000/0FAIL0ms1.1k / 3.0k
CG-AL-X081hard1100.0 / 1008/8OK12.5s938 / 3.0k
CG-AL-X082hard1100.0 / 10015/15OK11.3s1.3k / 1.6k
CG-AL-X083hard1100.0 / 1009/9OK10.9s1.5k / 11k
CG-AL-X084hard1100.0 / 10010/10OK11.7s1.5k / 27k
CG-AL-X085hard1100.0 / 1007/7OK11.2s1.0k / 6.9k
CG-AL-X086hard1100.0 / 1006/6OK11.2s1.4k / 23k
CG-AL-X087hard1100.0 / 1003/3OK11.7s1.1k / 17k
CG-AL-X088hard1100.0 / 1006/6OK11.1s997 / 6.8k
CG-AL-X089hard20.0 / 1000/0FAIL0ms1.1k / 42k
CG-AL-X090hard20.0 / 1000/0FAIL0ms915 / 18k
CG-AL-X091hard1100.0 / 1006/6OK11.0s583 / 1.3k
CG-AL-X092hard1100.0 / 10015/15OK11.3s454 / 1.3k
CG-AL-X093hard20.0 / 1000/0FAIL0ms1.0k / 11k
CG-AL-X094hard1100.0 / 1007/7OK11.6s772 / 2.5k
CG-AL-X095hard20.0 / 1000/0FAIL0ms828 / 24k
CG-AL-X096hard1100.0 / 10049/49OK11.7s3.4k / 16k
CG-AL-X097hard1100.0 / 10046/46OK11.6s3.5k / 11k
CG-AL-X098hard1100.0 / 10029/29OK11.4s2.7k / 11k
CG-AL-X099hard20.0 / 1000/0FAIL0ms3.7k / 32k
CG-AL-X100hard1100.0 / 10035/35OK11.1s3.6k / 26k
CG-AL-X101hard1100.0 / 10010/10OK11.1s1.1k / 7.5k
CG-AL-X102hard20.0 / 1000/0FAIL0ms540 / 6.7k
CG-AL-X103hard1100.0 / 1007/7OK10.9s736 / 2.9k
CG-AL-X104hard1100.0 / 1006/6OK10.8s1.1k / 2.3k
CG-AL-X105hard1100.0 / 1006/6OK10.9s793 / 3.0k
CG-AL-X106hard1100.0 / 1005/5OK11.1s905 / 7.8k
CG-AL-X107hard1100.0 / 1004/4OK10.9s818 / 14k
CG-AL-X108hard1100.0 / 1006/6OK11.7s736 / 1.8k
CG-AL-X109hard1100.0 / 1005/5OK11.4s557 / 6.9k
CG-AL-X110hard1100.0 / 10017/17OK12.0s1.2k / 9.6k
CG-AL-X111hard1100.0 / 1008/8OK11.3s1.2k / 34k
CG-AL-X112hard1100.0 / 10012/12OK12.2s925 / 24k
CG-AL-X113hard1100.0 / 10013/13OK11.3s713 / 5.6k
CG-AL-X114hard1100.0 / 1007/7OK11.0s736 / 2.2k
CG-AL-X115hard1100.0 / 10013/13OK10.8s481 / 21k
CG-AL-X116hard20.0 / 1000/0FAIL0ms935 / 53k
CG-AL-X117hard1100.0 / 1008/8OK11.9s1.0k / 1.9k
CG-AL-X118hard1100.0 / 10017/17OK11.3s1.4k / 13k
CG-AL-X119hard1100.0 / 10015/15OK11.4s1.7k / 3.1k
CG-AL-X120hard1100.0 / 10012/12OK11.4s1.2k / 6.1k
CG-AL-X121hard1100.0 / 1006/6OK10.7s1.0k / 1.1k
CG-AL-X122hard20.0 / 1000/0FAIL0ms1.5k / 8.0k
CG-AL-X123hard1100.0 / 1005/5OK13.0s612 / 797
CG-AL-X124hard1100.0 / 10010/10OK11.6s1.0k / 3.3k
CG-AL-X125hard1100.0 / 1008/8OK11.3s1.4k / 41k
CG-AL-X126hard1100.0 / 10014/14OK11.1s718 / 8.0k
CG-AL-X127hard1100.0 / 1005/5OK10.9s677 / 1.7k
CG-AL-X128hard1100.0 / 1008/8OK11.1s1.2k / 1.3k
CG-AL-X129hard1100.0 / 10014/14OK11.1s1.2k / 6.9k
CG-AL-X130hard20.0 / 1000/0FAIL0ms542 / 41k
CG-AL-X131hard1100.0 / 10013/13OK11.0s949 / 9.6k
CG-AL-X132hard1100.0 / 10010/10OK10.9s719 / 1.0k
CG-AL-X133hard20.0 / 1000/0FAIL0ms1.6k / 60k
CG-AL-X134hard20.0 / 1000/0FAIL0ms1.2k / 22k
CG-AL-X135hard1100.0 / 1004/4OK10.9s879 / 1.0k
CG-AL-X136hard1100.0 / 1007/7OK10.9s769 / 11k
CG-AL-X137hard1100.0 / 1004/4OK11.4s931 / 6.6k
CG-AL-X138hard1100.0 / 1009/9OK11.2s1.4k / 31k
CG-AL-X139hard1100.0 / 10011/11OK12.8s1.6k / 4.3k
CG-AL-X140hard1100.0 / 1007/7OK11.7s1.5k / 48k
CG-AL-X141hard1100.0 / 10039/39OK13.3s3.6k / 18k
CG-AL-X142hard1100.0 / 10048/48OK13.2s4.1k / 62k
CG-AL-X143hard1100.0 / 10035/35OK17.6s4.1k / 15k
CG-AL-X144hard1100.0 / 10043/43OK11.7s3.7k / 24k
CG-AL-X145hard1100.0 / 10032/32OK11.7s4.2k / 6.0k
CG-AL-X146hard20.0 / 1000/0FAIL0ms1.7k / 64k
CG-AL-X147hard1100.0 / 1008/8OK10.8s1.3k / 10k
CG-AL-X148hard1100.0 / 1006/6OK11.4s1.2k / 976
CG-AL-X149hard1100.0 / 1007/7OK11.5s1.1k / 11k
CG-AL-X150hard1100.0 / 1009/9OK12.3s1.9k / 63k
CG-AL-X151hard1100.0 / 1006/6OK11.1s827 / 1.6k
CG-AL-X152hard1100.0 / 1008/8OK12.2s1.1k / 1.7k
CG-AL-X153hard20.0 / 1000/0FAIL0ms901 / 49k
CG-AL-X154hard1100.0 / 1009/9OK11.1s1.2k / 7.1k
CG-AL-X155hard1100.0 / 10011/11OK11.8s949 / 4.4k
CG-AL-X156hard1100.0 / 1007/7OK12.2s903 / 674
CG-AL-X157hard1100.0 / 10010/10OK11.1s1.3k / 2.1k
CG-AL-X158hard1100.0 / 1007/7OK11.0s819 / 632
CG-AL-X159hard1100.0 / 1007/7OK11.5s860 / 8.4k
CG-AL-X160hard1100.0 / 10013/13OK11.3s1.2k / 3.8k
CG-AL-X161hard1100.0 / 10010/10OK11.3s1.4k / 2.2k
CG-AL-X162hard1100.0 / 1007/7OK11.3s970 / 3.8k
CG-AL-X163hard1100.0 / 1007/7OK11.4s1.0k / 3.1k
CG-AL-X164hard1100.0 / 1007/7OK11.6s963 / 5.7k
CG-AL-X165hard20.0 / 1000/0FAIL0ms2.7k / 39k
CG-AL-X166hard1100.0 / 10014/14OK12.3s1.6k / 7.1k
CG-AL-X167hard20.0 / 1000/0FAIL0ms1.4k / 39k
CG-AL-X168hard20.0 / 1000/0FAIL0ms1.3k / 20k
CG-AL-X169hard20.0 / 1000/0FAIL0ms1.7k / 12k
CG-AL-X170hard1100.0 / 10011/11OK11.7s3.2k / 54k
CG-AL-X171hard1100.0 / 1009/9OK11.5s1.4k / 53k
CG-AL-X172hard1100.0 / 10011/11OK11.8s2.2k / 48k
CG-AL-X173hard20.0 / 1000/0FAIL0ms3.2k / 64k
CG-AL-X174hard1100.0 / 10016/16OK11.7s3.9k / 33k
CG-AL-X185hard20.0 / 1000/0FAIL0ms2.5k / 19k
CG-AL-X187hard20.0 / 1000/0FAIL0ms3.3k / 54k
CG-AL-X194hard20.0 / 1000/0FAIL0ms5.0k / 61k
CG-AL-X211hard20.0 / 1000/0FAIL0ms3.5k / 64k
CG-AL-X214hard20.0 / 1000/0FAIL0ms3.7k / 64k
CG-AL-X218hard20.0 / 1000/0FAIL0ms3.6k / 28k
CG-AL-X234hard20.0 / 1000/0FAIL0ms3.8k / 46k
CG-AL-X239hard20.0 / 1000/0FAIL0ms5.0k / 36k
CG-AL-X244hard20.0 / 1000/0FAIL0ms5.3k / 64k
CG-AL-X245hard20.0 / 1000/0FAIL0ms4.4k / 43k
CG-AL-X248hard20.0 / 1000/0FAIL0ms4.3k / 59k
CG-AL-X249hard20.0 / 1000/0FAIL0ms4.5k / 60k
CG-AL-X254hard20.0 / 1000/0FAIL0ms5.8k / 37k
CG-AL-X257hard20.0 / 1000/0FAIL0ms4.1k / 64k
CG-AL-X263hard20.0 / 1000/0FAIL0ms4.4k / 61k
CG-AL-X264hard20.0 / 1000/0FAIL0ms5.0k / 61k
CG-AL-X270hard20.0 / 1000/0FAIL0ms7.6k / 64k
CG-AL-X271hard20.0 / 1000/0FAIL0ms7.7k / 64k
CG-AL-X272hard20.0 / 1000/0FAIL0ms6.1k / 52k
CG-AL-X274hard20.0 / 1000/0FAIL0ms5.9k / 53k
CG-AL-X276hard20.0 / 1000/0FAIL0ms6.4k / 63k
CG-AL-X278hard20.0 / 1000/0FAIL0ms6.5k / 64k
CG-AL-X283hard20.0 / 1000/0FAIL0ms6.6k / 64k
CG-AL-X289hard20.0 / 1000/0FAIL0ms5.1k / 64k
CG-AL-X290hard20.0 / 1000/0FAIL0ms5.2k / 44k
CG-AL-X292hard20.0 / 1000/0FAIL0ms4.9k / 50k
CG-AL-X293hard20.0 / 1000/0FAIL0ms4.4k / 64k
CG-AL-X296hard20.0 / 1000/0FAIL0ms6.8k / 59k
CG-AL-X298hard20.0 / 1000/0FAIL0ms4.5k / 64k