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.

73.3% 170/232 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.

61.8 / 100
Cost $45.52
Tokens 574k / 10.2M input / output, all attempts
Duration 49m 41s
Filter:
Per-task results for run 42894119-b128-46d7-9381-e1c5a0a70fa7
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK17.8s265 / 1.7k
CG-AL-E006easy1100.0 / 1007/7OK36.8s312 / 16k
CG-AL-E010easy1100.0 / 1005/5OK17.9s287 / 5.3k
CG-AL-E050easy20.0 / 1000/0FAIL8.7s1.8k / 53k
CG-AL-E052easy1100.0 / 10016/16OK13.9s359 / 1.5k
CG-AL-E054easy2100.0 / 1009/9OK31.0s1.3k / 7.5k
CG-AL-E056easy2100.0 / 10015/15OK32.5s2.3k / 27k
CG-AL-H007hard2100.0 / 10011/11OK28.3s1.1k / 111k
CG-AL-H011hard20.0 / 1000/0FAIL0ms1.1k / 110k
CG-AL-H014hard20.0 / 1000/0FAIL4.2s1.8k / 64k
CG-AL-H017hard20.0 / 1000/0FAIL4.1s1.2k / 90k
CG-AL-H020hard2100.0 / 10010/10OK11.9s2.4k / 47k
CG-AL-H021hard262.5 / 10016/20OK12.0s2.0k / 60k
CG-AL-H023hard20.0 / 1000/0FAIL0ms2.4k / 128k
CG-AL-H027hard20.0 / 1000/0FAIL4.2s1.5k / 113k
CG-AL-H029hard20.0 / 1000/0FAIL3.8s1.6k / 116k
CG-AL-H030hard2100.0 / 10010/10OK11.9s1.3k / 121k
CG-AL-H031hard1100.0 / 10022/22OK11.8s957 / 48k
CG-AL-H034hard2100.0 / 1003/3OK11.9s1.3k / 22k
CG-AL-H036hard20.0 / 1000/0FAIL4.1s960 / 47k
CG-AL-H037hard20.0 / 1000/0FAIL3.9s1.3k / 15k
CG-AL-H041hard1100.0 / 1003/3OK11.7s587 / 33k
CG-AL-H050hard262.5 / 1002/3OK11.1s1.2k / 67k
CG-AL-H054hard20.0 / 1000/0FAIL8.8s2.2k / 74k
CG-AL-H056hard20.0 / 1000/0FAIL0ms1.4k / 80k
CG-AL-M001medium20.0 / 1000/0FAIL3.9s1.5k / 37k
CG-AL-M003medium2100.0 / 1009/9OK11.7s1.5k / 76k
CG-AL-M004medium1100.0 / 10012/12OK30.4s459 / 37k
CG-AL-M006medium20.0 / 1000/0FAIL0ms820 / 128k
CG-AL-M007medium20.0 / 1000/0FAIL0ms860 / 128k
CG-AL-M008medium20.0 / 1000/0FAIL0ms988 / 128k
CG-AL-M009medium20.0 / 1000/0FAIL0ms859 / 128k
CG-AL-M010medium20.0 / 1000/0FAIL3.7s3.7k / 91k
CG-AL-M020medium2100.0 / 10017/17OK10.6s2.2k / 83k
CG-AL-M023medium1100.0 / 10011/11OK12.0s490 / 8.6k
CG-AL-M025medium20.0 / 1000/0FAIL0ms3.0k / 81k
CG-AL-M026medium1100.0 / 1008/8OK11.0s377 / 35k
CG-AL-M027medium262.5 / 10016/18OK11.1s5.0k / 93k
CG-AL-M028medium2100.0 / 1003/3OK27.9s1.1k / 73k
CG-AL-M031medium211.1 / 1000/0FAIL3.7s2.5k / 31k
CG-AL-M034medium1100.0 / 1002/2OK12.2s423 / 30k
CG-AL-M036medium20.0 / 1000/0FAIL0ms1.8k / 79k
CG-AL-M040medium20.0 / 1000/0FAIL0ms878 / 79k
CG-AL-M042medium1100.0 / 1008/8OK11.2s507 / 19k
CG-AL-X001hard1100.0 / 1002/2OK11.3s318 / 9.6k
CG-AL-X002hard2100.0 / 1004/4OK11.0s976 / 127k
CG-AL-X003hard2100.0 / 1003/3OK10.6s862 / 81k
CG-AL-X004medium1100.0 / 1003/3OK11.7s372 / 16k
CG-AL-X005hard1100.0 / 1002/2OK11.3s339 / 15k
CG-AL-X006hard1100.0 / 1003/3OK11.3s402 / 9.1k
CG-AL-X007hard1100.0 / 1002/2OK1m 41s381 / 9.4k
CG-AL-X008hard1100.0 / 1001/1OK11.1s433 / 49k
CG-AL-X009medium1100.0 / 1002/2OK11.0s324 / 20k
CG-AL-X010medium1100.0 / 1003/3OK11.1s293 / 2.7k
CG-AL-X011medium1100.0 / 1002/2OK11.1s371 / 1.9k
CG-AL-X012hard1100.0 / 1001/1OK11.2s395 / 37k
CG-AL-X013hard1100.0 / 1002/2OK10.5s271 / 6.7k
CG-AL-X014medium1100.0 / 1004/4OK10.7s302 / 13k
CG-AL-X017medium2100.0 / 1003/3OK10.5s1.5k / 2.5k
CG-AL-X018medium1100.0 / 1003/3OK11.3s400 / 22k
CG-AL-X019medium2100.0 / 1003/3OK10.6s2.0k / 55k
CG-AL-X022medium2100.0 / 1003/3OK11.0s1.4k / 60k
CG-AL-X024medium2100.0 / 1003/3OK10.7s1.0k / 16k
CG-AL-X025medium2100.0 / 1001/1OK11.0s1.2k / 25k
CG-AL-X026medium1100.0 / 1003/3OK11.4s339 / 2.7k
CG-AL-X027medium1100.0 / 1004/4OK11.0s268 / 17k
CG-AL-X029medium1100.0 / 1002/2OK11.2s284 / 20k
CG-AL-X030medium1100.0 / 1002/2OK10.8s248 / 3.0k
CG-AL-X031medium1100.0 / 1003/3OK11.4s309 / 1.4k
CG-AL-X033hard1100.0 / 1002/2OK11.3s363 / 27k
CG-AL-X034hard1100.0 / 1003/3OK11.3s316 / 17k
CG-AL-X035hard2100.0 / 1003/3OK11.0s1.7k / 60k
CG-AL-X037hard262.5 / 1000/4OK11.0s1.2k / 62k
CG-AL-X040hard2100.0 / 1004/4OK11.2s1.1k / 118k
CG-AL-X041hard20.0 / 1000/0FAIL0ms2.7k / 91k
CG-AL-X043hard20.0 / 1000/0FAIL0ms1.1k / 128k
CG-AL-X044hard262.5 / 1000/3OK11.0s1.5k / 112k
CG-AL-X045hard1100.0 / 1003/3OK11.7s384 / 25k
CG-AL-X046hard262.5 / 1000/2OK10.9s1.8k / 81k
CG-AL-X047hard262.5 / 1001/2OK11.4s1.9k / 75k
CG-AL-X050hard1100.0 / 1002/2OK11.4s422 / 17k
CG-AL-X051hard1100.0 / 1002/2OK11.6s533 / 59k
CG-AL-X052hard1100.0 / 1003/3OK11.7s371 / 18k
CG-AL-X055hard1100.0 / 1005/5OK11.0s353 / 16k
CG-AL-X056hard1100.0 / 1005/5OK11.2s288 / 10.0k
CG-AL-X057hard1100.0 / 1005/5OK11.2s259 / 9.0k
CG-AL-X058hard1100.0 / 1005/5OK11.3s326 / 7.3k
CG-AL-X059hard1100.0 / 1003/3OK11.2s342 / 4.2k
CG-AL-X060hard20.0 / 1000/0FAIL4.2s606 / 75k
CG-AL-X061hard1100.0 / 1004/4OK11.3s380 / 1.7k
CG-AL-X062hard1100.0 / 1004/4OK11.4s370 / 23k
CG-AL-X063hard1100.0 / 1003/3OK11.0s374 / 8.0k
CG-AL-X064hard1100.0 / 1007/7OK11.6s286 / 22k
CG-AL-X065hard1100.0 / 1006/6OK11.0s730 / 5.4k
CG-AL-X066hard1100.0 / 10014/14OK11.2s1.3k / 10k
CG-AL-X067hard262.5 / 1006/7OK10.7s1.9k / 41k
CG-AL-X068hard1100.0 / 10012/12OK11.2s1.2k / 26k
CG-AL-X069hard1100.0 / 1008/8OK11.5s1.1k / 38k
CG-AL-X070hard1100.0 / 10012/12OK11.4s1.2k / 8.5k
CG-AL-X071hard1100.0 / 1008/8OK11.7s1.4k / 4.2k
CG-AL-X072hard1100.0 / 1007/7OK11.4s1.2k / 3.2k
CG-AL-X073hard1100.0 / 1008/8OK11.2s1.5k / 6.5k
CG-AL-X074hard2100.0 / 1007/7OK10.8s3.6k / 66k
CG-AL-X075hard1100.0 / 1007/7OK11.2s838 / 25k
CG-AL-X076hard1100.0 / 10014/14OK11.3s967 / 47k
CG-AL-X077hard1100.0 / 10022/22OK11.1s1.5k / 10k
CG-AL-X078hard1100.0 / 10017/17OK11.2s1.2k / 2.3k
CG-AL-X079hard1100.0 / 10011/11OK11.2s1.2k / 17k
CG-AL-X080hard2100.0 / 1007/7OK11.1s2.6k / 46k
CG-AL-X081hard1100.0 / 1008/8OK11.4s938 / 2.2k
CG-AL-X082hard1100.0 / 10015/15OK11.1s1.3k / 1.3k
CG-AL-X083hard2100.0 / 1009/9OK10.8s3.4k / 45k
CG-AL-X084hard1100.0 / 10010/10OK11.5s1.5k / 26k
CG-AL-X085hard1100.0 / 1007/7OK11.0s1.0k / 5.1k
CG-AL-X086hard1100.0 / 1006/6OK11.3s1.4k / 32k
CG-AL-X087hard1100.0 / 1003/3OK11.0s1.1k / 15k
CG-AL-X088hard1100.0 / 1006/6OK11.1s997 / 11k
CG-AL-X089hard1100.0 / 10011/11OK11.3s1.1k / 39k
CG-AL-X090hard20.0 / 1000/0FAIL0ms2.3k / 78k
CG-AL-X091hard1100.0 / 1006/6OK11.0s583 / 781
CG-AL-X092hard1100.0 / 10015/15OK11.3s454 / 879
CG-AL-X093hard2100.0 / 10010/10OK12.7s2.7k / 43k
CG-AL-X094hard1100.0 / 1007/7OK10.8s772 / 12k
CG-AL-X095hard2100.0 / 1005/5OK10.8s2.3k / 28k
CG-AL-X096hard1100.0 / 10049/49OK11.6s3.4k / 33k
CG-AL-X097hard1100.0 / 10046/46OK11.5s3.5k / 16k
CG-AL-X098hard1100.0 / 10029/29OK11.3s2.7k / 12k
CG-AL-X099hard1100.0 / 10039/39OK13.0s3.7k / 41k
CG-AL-X100hard1100.0 / 10035/35OK11.8s3.6k / 28k
CG-AL-X101hard1100.0 / 10010/10OK11.2s1.1k / 6.0k
CG-AL-X102hard20.0 / 1000/0FAIL0ms2.3k / 69k
CG-AL-X103hard1100.0 / 1007/7OK11.1s736 / 1.6k
CG-AL-X104hard1100.0 / 1006/6OK11.4s1.1k / 2.8k
CG-AL-X105hard1100.0 / 1006/6OK11.2s793 / 1.6k
CG-AL-X106hard1100.0 / 1005/5OK11.3s905 / 5.6k
CG-AL-X107hard1100.0 / 1004/4OK10.9s818 / 9.0k
CG-AL-X108hard1100.0 / 1006/6OK11.8s736 / 4.9k
CG-AL-X109hard1100.0 / 1005/5OK11.2s557 / 6.4k
CG-AL-X110hard1100.0 / 10017/17OK11.3s1.2k / 6.0k
CG-AL-X111hard1100.0 / 1008/8OK11.7s1.2k / 11k
CG-AL-X112hard1100.0 / 10012/12OK11.3s925 / 27k
CG-AL-X113hard1100.0 / 10013/13OK11.3s713 / 4.2k
CG-AL-X114hard1100.0 / 1007/7OK11.4s736 / 876
CG-AL-X115hard1100.0 / 10013/13OK11.2s481 / 40k
CG-AL-X116hard1100.0 / 10017/17OK11.2s935 / 38k
CG-AL-X117hard1100.0 / 1008/8OK11.3s1.0k / 2.0k
CG-AL-X118hard1100.0 / 10017/17OK11.5s1.4k / 14k
CG-AL-X119hard1100.0 / 10015/15OK11.5s1.7k / 3.7k
CG-AL-X120hard1100.0 / 10012/12OK11.5s1.2k / 5.2k
CG-AL-X121hard1100.0 / 1006/6OK10.9s1.0k / 1.3k
CG-AL-X122hard1100.0 / 10010/10OK11.1s1.5k / 18k
CG-AL-X123hard1100.0 / 1005/5OK11.0s612 / 2.5k
CG-AL-X124hard1100.0 / 10010/10OK11.6s1.0k / 2.6k
CG-AL-X125hard1100.0 / 1008/8OK11.5s1.4k / 11k
CG-AL-X126hard1100.0 / 10014/14OK11.4s718 / 2.4k
CG-AL-X127hard1100.0 / 1005/5OK10.9s677 / 5.5k
CG-AL-X128hard1100.0 / 1008/8OK11.0s1.2k / 1.4k
CG-AL-X129hard1100.0 / 10014/14OK11.3s1.2k / 13k
CG-AL-X130hard2100.0 / 1005/5OK10.7s1.4k / 58k
CG-AL-X131hard1100.0 / 10013/13OK11.4s949 / 17k
CG-AL-X132hard1100.0 / 10010/10OK11.1s719 / 616
CG-AL-X133hard20.0 / 1000/0FAIL0ms3.5k / 88k
CG-AL-X134hard1100.0 / 1006/6OK11.8s1.2k / 19k
CG-AL-X135hard1100.0 / 1004/4OK11.2s879 / 1.7k
CG-AL-X136hard1100.0 / 1007/7OK11.1s769 / 2.7k
CG-AL-X137hard1100.0 / 1004/4OK10.9s931 / 12k
CG-AL-X138hard1100.0 / 1009/9OK12.6s1.4k / 17k
CG-AL-X139hard1100.0 / 10011/11OK11.5s1.6k / 3.2k
CG-AL-X140hard20.0 / 1000/0FAIL0ms4.3k / 85k
CG-AL-X141hard1100.0 / 10039/39OK12.1s3.6k / 17k
CG-AL-X142hard20.0 / 1000/0FAIL0ms4.6k / 128k
CG-AL-X143hard1100.0 / 10035/35OK16.8s4.1k / 24k
CG-AL-X144hard1100.0 / 10043/43OK11.5s3.7k / 18k
CG-AL-X145hard1100.0 / 10032/32OK12.2s4.2k / 6.7k
CG-AL-X146hard1100.0 / 1009/9OK11.6s1.7k / 54k
CG-AL-X147hard1100.0 / 1008/8OK12.8s1.3k / 21k
CG-AL-X148hard1100.0 / 1006/6OK11.1s1.2k / 976
CG-AL-X149hard1100.0 / 1007/7OK11.4s1.1k / 5.9k
CG-AL-X150hard1100.0 / 1009/9OK11.8s1.9k / 52k
CG-AL-X151hard1100.0 / 1006/6OK11.3s827 / 1.7k
CG-AL-X152hard1100.0 / 1008/8OK11.1s1.1k / 4.3k
CG-AL-X153hard1100.0 / 1009/9OK15.0s901 / 44k
CG-AL-X154hard1100.0 / 1009/9OK11.3s1.2k / 1.9k
CG-AL-X155hard1100.0 / 10011/11OK11.2s949 / 3.7k
CG-AL-X156hard1100.0 / 1007/7OK11.2s903 / 617
CG-AL-X157hard1100.0 / 10010/10OK11.3s1.3k / 3.8k
CG-AL-X158hard1100.0 / 1007/7OK11.7s819 / 824
CG-AL-X159hard1100.0 / 1007/7OK11.7s860 / 6.5k
CG-AL-X160hard1100.0 / 10013/13OK11.7s1.2k / 4.3k
CG-AL-X161hard1100.0 / 10010/10OK12.6s1.4k / 2.4k
CG-AL-X162hard1100.0 / 1007/7OK11.5s970 / 8.3k
CG-AL-X163hard1100.0 / 1007/7OK11.5s1.0k / 4.0k
CG-AL-X164hard2100.0 / 1007/7OK10.9s2.0k / 30k
CG-AL-X165hard1100.0 / 10013/13OK14.3s2.7k / 59k
CG-AL-X166hard1100.0 / 10014/14OK11.9s1.6k / 4.9k
CG-AL-X167hard20.0 / 1000/0FAIL4.1s3.7k / 96k
CG-AL-X168hard2100.0 / 1009/9OK10.9s3.3k / 73k
CG-AL-X169hard2100.0 / 10011/11OK11.6s4.0k / 35k
CG-AL-X170hard1100.0 / 10011/11OK12.0s3.2k / 47k
CG-AL-X171hard1100.0 / 1009/9OK11.4s1.4k / 48k
CG-AL-X172hard1100.0 / 10011/11OK11.6s2.2k / 59k
CG-AL-X173hard20.0 / 1000/0FAIL0ms6.9k / 100k
CG-AL-X174hard1100.0 / 10016/16OK11.8s3.9k / 26k
CG-AL-X185hard20.0 / 1000/0FAIL0ms7.1k / 88k
CG-AL-X187hard20.0 / 1000/0FAIL0ms7.7k / 99k
CG-AL-X194hard20.0 / 1000/0FAIL0ms11k / 119k
CG-AL-X211hard20.0 / 1000/0FAIL0ms4.2k / 128k
CG-AL-X214hard20.0 / 1000/0FAIL0ms8.4k / 97k
CG-AL-X218hard20.0 / 1000/0FAIL0ms8.2k / 122k
CG-AL-X234hard2100.0 / 10035/35OK11.7s9.4k / 99k
CG-AL-X239hard20.0 / 1000/0FAIL0ms11k / 115k
CG-AL-X244hard20.0 / 1000/0FAIL0ms12k / 117k
CG-AL-X245hard20.0 / 1000/0FAIL3.5s12k / 102k
CG-AL-X248hard2100.0 / 10066/66OK12.6s12k / 99k
CG-AL-X249hard20.0 / 1000/0FAIL0ms10.0k / 116k
CG-AL-X254hard2100.0 / 10070/70OK12.2s13k / 79k
CG-AL-X257hard20.0 / 1000/0FAIL0ms4.9k / 128k
CG-AL-X263hard20.0 / 1000/0FAIL0ms5.3k / 128k
CG-AL-X264hard20.0 / 1000/0FAIL0ms12k / 115k
CG-AL-X270hard20.0 / 1000/0FAIL0ms8.5k / 128k
CG-AL-X271hard20.0 / 1000/0FAIL0ms18k / 124k
CG-AL-X272hard2100.0 / 10079/79OK12.7s14k / 80k
CG-AL-X274hard20.0 / 1000/0FAIL0ms14k / 108k
CG-AL-X276hard2100.0 / 10078/78OK12.6s14k / 62k
CG-AL-X278hard20.0 / 1000/0FAIL0ms14k / 115k
CG-AL-X283hard20.0 / 1000/0FAIL0ms7.6k / 128k
CG-AL-X289hard20.0 / 1000/0FAIL0ms5.9k / 128k
CG-AL-X290hard2100.0 / 10047/47OK12.2s12k / 101k
CG-AL-X292hard20.0 / 1000/0FAIL0ms9.5k / 127k
CG-AL-X293hard20.0 / 1000/0FAIL0ms5.2k / 128k
CG-AL-X296hard20.0 / 1000/0FAIL0ms16k / 108k
CG-AL-X298hard20.0 / 1000/0FAIL0ms5.3k / 128k