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.

69.8% 141/202 of 202 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.

45.1 / 100
Cost $25.84
Tokens 1.2M / 1.1M input / output, all attempts
Duration 38m 49s
Filter:
Per-task results for run f9fe71d5-78c7-42b4-8088-532451449b15
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK19.7s415 / 627
CG-AL-E006easy1100.0 / 1007/7OK37.0s496 / 809
CG-AL-E010easy2100.0 / 1005/5OK17.6s1.3k / 799
CG-AL-E050easy1100.0 / 10013/13OK14.7s632 / 714
CG-AL-E052easy1100.0 / 10016/16OK12.0s612 / 437
CG-AL-E054easy2100.0 / 1009/9OK16.9s1.8k / 1.4k
CG-AL-E056easy2100.0 / 10015/15OK16.3s2.8k / 1.3k
CG-AL-H007hard1100.0 / 10011/11OK11.2s949 / 1.8k
CG-AL-H011hard2100.0 / 1006/6OK10.1s1.6k / 1.2k
CG-AL-H014hard1100.0 / 1007/7OK10.9s729 / 1.7k
CG-AL-H017hard1100.0 / 1005/5OK11.3s612 / 1.1k
CG-AL-H020hard1100.0 / 10010/10OK16.8s783 / 2.0k
CG-AL-H021hard2100.0 / 10020/20OK10.8s26k / 3.2k
CG-AL-H023hard1100.0 / 10025/25OK12.2s2.0k / 19k
CG-AL-H027hard1100.0 / 1004/4OK11.8s1.1k / 880
CG-AL-H029hard1100.0 / 10018/18OK11.9s1.3k / 3.0k
CG-AL-H030hard1100.0 / 10010/10OK10.7s1.1k / 1.6k
CG-AL-H031hard1100.0 / 10022/22OK11.0s1.6k / 2.3k
CG-AL-H034hard1100.0 / 1003/3OK10.5s722 / 738
CG-AL-H036hard1100.0 / 1005/5OK10.0s640 / 1.1k
CG-AL-H037hard1100.0 / 1003/3OK10.3s807 / 637
CG-AL-H041hard1100.0 / 1003/3OK10.0s925 / 1.6k
CG-AL-H050hard1100.0 / 1003/3OK10.7s815 / 1.2k
CG-AL-H054hard2100.0 / 1005/5OK10.2s3.2k / 2.3k
CG-AL-H056hard2100.0 / 1004/4OK9.9s2.4k / 995
CG-AL-M001medium2100.0 / 10010/10OK22.2s2.6k / 2.8k
CG-AL-M003medium2100.0 / 1009/9OK10.8s3.6k / 5.0k
CG-AL-M004medium1100.0 / 10012/12OK27.7s775 / 3.2k
CG-AL-M006medium2100.0 / 10018/18OK11.0s4.7k / 8.7k
CG-AL-M007medium262.5 / 10013/15OK11.3s8.3k / 15k
CG-AL-M008medium262.5 / 10011/12OK11.6s20k / 39k
CG-AL-M009medium1100.0 / 10011/11OK10.7s748 / 16k
CG-AL-M010medium1100.0 / 10021/21OK23.0s960 / 6.1k
CG-AL-M020medium1100.0 / 10017/17OK11.1s885 / 2.5k
CG-AL-M023medium1100.0 / 10011/11OK11.8s805 / 973
CG-AL-M025medium2100.0 / 1008/8OK10.1s4.9k / 2.8k
CG-AL-M026medium1100.0 / 1008/8OK11.9s626 / 1.2k
CG-AL-M027medium1100.0 / 10018/18OK11.3s1.4k / 3.1k
CG-AL-M028medium2100.0 / 1003/3OK21.0s1.8k / 1.4k
CG-AL-M031medium1100.0 / 1002/2OK10.7s1.2k / 1.3k
CG-AL-M034medium1100.0 / 1002/2OK10.6s697 / 698
CG-AL-M036medium2100.0 / 1002/2OK10.1s2.6k / 2.0k
CG-AL-M040medium2100.0 / 1002/2OK10.4s1.3k / 1.5k
CG-AL-M042medium1100.0 / 1008/8OK10.0s755 / 1.1k
CG-AL-X001hard1100.0 / 1002/2OK10.5s501 / 440
CG-AL-X003hard262.5 / 1002/3OK16.6s1.4k / 2.2k
CG-AL-X004medium20.0 / 1000/0FAIL6.0s1.6k / 2.2k
CG-AL-X008hard20.0 / 1000/0FAIL0ms1.3k / 0
CG-AL-X013hard2100.0 / 1002/2OK11.8s918 / 936
CG-AL-X017medium262.5 / 1000/3OK10.2s915 / 553
CG-AL-X022medium2100.0 / 1003/3OK10.4s1.3k / 1.5k
CG-AL-X024medium2100.0 / 1003/3OK15.5s1.7k / 2.3k
CG-AL-X025medium2100.0 / 1001/1OK10.0s1.8k / 2.6k
CG-AL-X027medium2100.0 / 1004/4OK9.9s1.1k / 1.2k
CG-AL-X029medium2100.0 / 1002/2OK9.6s1.2k / 1.8k
CG-AL-X030medium2100.0 / 1002/2OK11.4s917 / 786
CG-AL-X035hard20.0 / 1000/0FAIL0ms1.0k / 116
CG-AL-X041hard2100.0 / 1005/5OK10.4s1.4k / 1.9k
CG-AL-X043hard20.0 / 1000/0FAIL4.9s1.9k / 4.7k
CG-AL-X055hard2100.0 / 1005/5OK10.3s1.4k / 2.0k
CG-AL-X056hard2100.0 / 1005/5OK10.3s1.2k / 1.3k
CG-AL-X057hard2100.0 / 1005/5OK9.8s920 / 573
CG-AL-X064hard2100.0 / 1007/7OK10.4s1.6k / 2.1k
CG-AL-X065hard2100.0 / 1006/6OK9.9s2.4k / 2.9k
CG-AL-X066hard262.5 / 10011/14OK10.1s4.5k / 5.0k
CG-AL-X067hard2100.0 / 1007/7OK10.0s2.1k / 2.0k
CG-AL-X068hard2100.0 / 10012/12OK11.1s4.0k / 3.8k
CG-AL-X069hard262.5 / 1007/8OK11.1s4.3k / 5.7k
CG-AL-X070hard2100.0 / 10012/12OK12.3s3.9k / 4.6k
CG-AL-X071hard262.5 / 1006/8OK10.4s4.6k / 4.6k
CG-AL-X072hard2100.0 / 1007/7OK10.1s4.2k / 4.0k
CG-AL-X073hard2100.0 / 1008/8OK10.6s5.3k / 5.8k
CG-AL-X074hard262.5 / 1006/7OK10.1s5.4k / 5.8k
CG-AL-X075hard20.0 / 1000/0FAIL4.1s2.8k / 2.1k
CG-AL-X076hard20.0 / 1000/0FAIL4.1s3.3k / 3.1k
CG-AL-X077hard2100.0 / 10022/22OK10.1s5.3k / 5.1k
CG-AL-X078hard1100.0 / 10017/17OK19.1s2.0k / 1.5k
CG-AL-X079hard2100.0 / 10011/11OK10.7s4.3k / 4.4k
CG-AL-X080hard2100.0 / 1007/7OK10.3s3.8k / 3.8k
CG-AL-X081hard2100.0 / 1008/8OK10.1s3.0k / 2.8k
CG-AL-X082hard2100.0 / 10015/15OK10.1s4.3k / 4.1k
CG-AL-X083hard262.5 / 1007/9OK10.5s5.6k / 5.5k
CG-AL-X084hard2100.0 / 10010/10OK12.0s5.2k / 6.3k
CG-AL-X085hard2100.0 / 1007/7OK12.9s3.3k / 3.0k
CG-AL-X086hard2100.0 / 1006/6OK11.2s5.1k / 5.1k
CG-AL-X087hard2100.0 / 1003/3OK12.4s3.6k / 4.1k
CG-AL-X088hard2100.0 / 1006/6OK10.4s3.6k / 3.8k
CG-AL-X089hard20.0 / 1000/0FAIL5.5s4.1k / 5.8k
CG-AL-X090hard262.5 / 1009/10OK10.8s3.2k / 5.3k
CG-AL-X091hard262.5 / 1004/6OK10.1s1.9k / 1.6k
CG-AL-X092hard2100.0 / 10015/15OK10.7s1.5k / 1.2k
CG-AL-X093hard2100.0 / 10010/10OK10.1s3.3k / 3.3k
CG-AL-X094hard20.0 / 1000/0FAIL3.8s2.7k / 2.5k
CG-AL-X095hard262.5 / 1002/5OK9.8s2.7k / 3.0k
CG-AL-X096hard2100.0 / 10049/49OK10.5s12k / 12k
CG-AL-X097hard2100.0 / 10046/46OK10.5s12k / 12k
CG-AL-X098hard2100.0 / 10029/29OK10.3s9.6k / 9.2k
CG-AL-X099hard2100.0 / 10039/39OK11.9s13k / 14k
CG-AL-X100hard2100.0 / 10035/35OK10.6s12k / 12k
CG-AL-X101hard2100.0 / 10010/10OK11.6s4.0k / 4.4k
CG-AL-X102hard20.0 / 1000/0FAIL4.9s2.0k / 2.3k
CG-AL-X103hard262.5 / 1003/7OK10.8s2.5k / 2.4k
CG-AL-X104hard2100.0 / 1006/6OK10.8s3.6k / 3.0k
CG-AL-X105hard2100.0 / 1006/6OK10.4s2.8k / 2.6k
CG-AL-X106hard20.0 / 1000/0FAIL3.8s3.2k / 2.9k
CG-AL-X107hard2100.0 / 1004/4OK10.2s2.9k / 2.7k
CG-AL-X108hard20.0 / 1000/0FAIL3.7s2.7k / 3.1k
CG-AL-X109hard2100.0 / 1005/5OK10.6s1.9k / 1.9k
CG-AL-X110hard2100.0 / 10017/17OK11.2s4.3k / 4.5k
CG-AL-X111hard20.0 / 1000/0FAIL5.4s4.1k / 4.9k
CG-AL-X112hard2100.0 / 10012/12OK11.7s3.2k / 4.4k
CG-AL-X113hard2100.0 / 10013/13OK11.4s2.7k / 2.8k
CG-AL-X114hard20.0 / 1000/0FAIL5.2s2.5k / 1.7k
CG-AL-X115hard2100.0 / 10013/13OK10.2s1.8k / 1.6k
CG-AL-X116hard2100.0 / 10017/17OK10.4s3.3k / 3.1k
CG-AL-X117hard2100.0 / 1008/8OK10.6s3.6k / 4.8k
CG-AL-X118hard2100.0 / 10017/17OK11.6s4.6k / 4.0k
CG-AL-X119hard262.5 / 1002/15OK10.1s5.9k / 7.1k
CG-AL-X120hard2100.0 / 10012/12OK10.6s4.5k / 5.0k
CG-AL-X121hard262.5 / 1005/6OK10.3s3.4k / 3.3k
CG-AL-X122hard262.5 / 1009/10OK10.3s5.3k / 5.2k
CG-AL-X123hard20.0 / 1000/0FAIL4.1s2.0k / 1.6k
CG-AL-X124hard2100.0 / 10010/10OK10.0s3.4k / 2.7k
CG-AL-X125hard2100.0 / 1008/8OK10.0s4.8k / 5.5k
CG-AL-X126hard2100.0 / 10014/14OK10.4s2.6k / 2.3k
CG-AL-X127hard262.5 / 1002/5OK10.4s2.1k / 1.9k
CG-AL-X128hard20.0 / 1000/0FAIL4.0s4.0k / 3.2k
CG-AL-X129hard2100.0 / 10014/14OK10.3s4.2k / 4.0k
CG-AL-X130hard2100.0 / 1005/5OK10.5s1.8k / 1.7k
CG-AL-X131hard2100.0 / 10013/13OK11.6s3.3k / 2.5k
CG-AL-X132hard262.5 / 1005/10OK10.7s2.5k / 2.4k
CG-AL-X133hard20.0 / 1000/0FAIL4.1s5.8k / 5.6k
CG-AL-X134hard2100.0 / 1006/6OK13.3s4.3k / 4.4k
CG-AL-X135hard2100.0 / 1004/4OK10.0s2.9k / 2.5k
CG-AL-X136hard2100.0 / 1007/7OK9.7s2.5k / 2.2k
CG-AL-X137hard2100.0 / 1004/4OK10.4s3.1k / 2.9k
CG-AL-X138hard2100.0 / 1009/9OK9.9s5.1k / 4.8k
CG-AL-X139hard2100.0 / 10011/11OK10.1s5.9k / 6.9k
CG-AL-X140hard2100.0 / 1007/7OK10.1s5.9k / 8.0k
CG-AL-X141hard2100.0 / 10039/39OK10.8s12k / 13k
CG-AL-X142hard2100.0 / 10048/48OK10.6s13k / 15k
CG-AL-X143hard262.5 / 10034/35OK15.0s15k / 14k
CG-AL-X144hard2100.0 / 10043/43OK11.2s13k / 13k
CG-AL-X145hard2100.0 / 10032/32OK10.5s15k / 16k
CG-AL-X146hard2100.0 / 1009/9OK10.8s6.2k / 6.3k
CG-AL-X147hard2100.0 / 1008/8OK10.4s4.5k / 5.0k
CG-AL-X148hard2100.0 / 1006/6OK10.1s3.8k / 4.0k
CG-AL-X149hard2100.0 / 1007/7OK11.6s3.8k / 4.3k
CG-AL-X150hard2100.0 / 1009/9OK10.7s7.3k / 8.5k
CG-AL-X151hard2100.0 / 1006/6OK10.4s3.0k / 2.9k
CG-AL-X152hard2100.0 / 1008/8OK10.0s3.8k / 3.9k
CG-AL-X153hard2100.0 / 1009/9OK14.2s3.2k / 3.5k
CG-AL-X154hard2100.0 / 1009/9OK10.0s4.4k / 4.4k
CG-AL-X155hard2100.0 / 10011/11OK10.2s3.4k / 3.8k
CG-AL-X156hard20.0 / 1000/0FAIL3.9s3.0k / 2.5k
CG-AL-X157hard262.5 / 1000/10OK9.7s4.4k / 3.9k
CG-AL-X158hard2100.0 / 1007/7OK9.8s2.7k / 2.3k
CG-AL-X159hard2100.0 / 1007/7OK10.4s2.9k / 3.1k
CG-AL-X160hard2100.0 / 10013/13OK10.0s4.5k / 4.7k
CG-AL-X161hard2100.0 / 10010/10OK10.2s5.3k / 5.5k
CG-AL-X162hard262.5 / 1000/7OK12.1s3.3k / 3.7k
CG-AL-X163hard2100.0 / 1007/7OK10.5s3.5k / 3.7k
CG-AL-X164hard262.5 / 1003/7OK10.4s3.1k / 3.1k
CG-AL-X165hard20.0 / 1000/0FAIL3.9s9.6k / 9.8k
CG-AL-X166hard20.0 / 1000/0FAIL3.7s5.2k / 4.4k
CG-AL-X167hard20.0 / 1000/0FAIL3.9s5.1k / 5.9k
CG-AL-X168hard2100.0 / 1009/9OK10.2s4.9k / 6.0k
CG-AL-X169hard262.5 / 1009/11OK11.7s6.1k / 6.7k
CG-AL-X170hard2100.0 / 10011/11OK10.4s11k / 11k
CG-AL-X171hard2100.0 / 1009/9OK10.4s5.6k / 6.2k
CG-AL-X172hard2100.0 / 10011/11OK10.8s8.9k / 11k
CG-AL-X173hard20.0 / 1000/0FAIL3.9s12k / 13k
CG-AL-X174hard2100.0 / 10016/16OK10.9s14k / 14k
CG-AL-X185hard20.0 / 1000/0FAIL4.2s8.2k / 4.6k
CG-AL-X187hard262.5 / 10030/33OK11.8s11k / 5.4k
CG-AL-X194hard262.5 / 10049/50OK12.2s18k / 11k
CG-AL-X211hard2100.0 / 10043/43OK12.8s12k / 8.5k
CG-AL-X214hard262.5 / 10028/34OK10.7s12k / 6.6k
CG-AL-X218hard262.5 / 10019/27OK10.6s12k / 9.2k
CG-AL-X234hard2100.0 / 10035/35OK10.7s13k / 8.4k
CG-AL-X239hard262.5 / 10034/37OK10.8s17k / 9.3k
CG-AL-X244hard262.5 / 10034/38OK11.0s18k / 13k
CG-AL-X245hard262.5 / 10059/63OK11.1s14k / 8.0k
CG-AL-X248hard2100.0 / 10066/66OK11.4s14k / 8.4k
CG-AL-X249hard262.5 / 10034/37OK10.8s15k / 7.6k
CG-AL-X254hard2100.0 / 10070/70OK11.6s20k / 10k
CG-AL-X257hard262.5 / 10050/53OK10.8s14k / 7.0k
CG-AL-X263hard2100.0 / 10061/61OK11.6s16k / 13k
CG-AL-X264hard262.5 / 10064/65OK11.2s17k / 11k
CG-AL-X270hard20.0 / 1000/0FAIL4.0s26k / 13k
CG-AL-X271hard262.5 / 10065/70OK11.7s25k / 14k
CG-AL-X272hard2100.0 / 10079/79OK12.0s21k / 11k
CG-AL-X274hard262.5 / 10060/64OK11.5s20k / 12k
CG-AL-X276hard262.5 / 10074/78OK11.3s22k / 13k
CG-AL-X278hard262.5 / 10068/71OK11.6s22k / 13k
CG-AL-X283hard2100.0 / 10076/76OK11.4s22k / 11k
CG-AL-X289hard2100.0 / 10057/57OK11.0s18k / 14k
CG-AL-X290hard2100.0 / 10047/47OK11.0s18k / 13k
CG-AL-X292hard2100.0 / 10057/57OK11.1s16k / 7.0k
CG-AL-X293hard2100.0 / 10049/49OK11.0s15k / 9.3k
CG-AL-X296hard262.5 / 10046/47OK11.4s24k / 17k
CG-AL-X298hard2100.0 / 10055/55OK10.7s15k / 9.7k