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.

91.4% 212/232 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.

82.5 / 100
Cost $13.78
Tokens 613k / 3.6M input / output, all attempts
Duration 58m 10s
Filter:
Per-task results for run 53112fb9-6519-4cb2-ad56-9468218877bb
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK16.5s263 / 916
CG-AL-E006easy1100.0 / 1007/7OK29.8s309 / 1.3k
CG-AL-E010easy262.5 / 1000/1OK37.1s773 / 3.0k
CG-AL-E050easy2100.0 / 10013/13OK20.6s2.1k / 19k
CG-AL-E052easy1100.0 / 10016/16OK10.8s360 / 913
CG-AL-E054easy2100.0 / 1009/9OK19.9s1.1k / 7.0k
CG-AL-E056easy2100.0 / 10015/15OK11.9s1.9k / 2.8k
CG-AL-H007hard2100.0 / 10011/11OK11.7s1.8k / 29k
CG-AL-H011hard2100.0 / 1006/6OK12.0s980 / 6.1k
CG-AL-H014hard2100.0 / 1007/7OK11.7s1.4k / 12k
CG-AL-H017hard2100.0 / 1005/5OK12.9s1.0k / 19k
CG-AL-H020hard2100.0 / 10010/10OK11.9s1.9k / 8.6k
CG-AL-H021hard1100.0 / 10020/20OK11.2s610 / 1.9k
CG-AL-H023hard20.0 / 1000/0FAIL4.8s7.4k / 27k
CG-AL-H027hard1100.0 / 1004/4OK11.2s783 / 9.3k
CG-AL-H029hard2100.0 / 10018/18OK12.3s3.1k / 34k
CG-AL-H030hard1100.0 / 10010/10OK10.8s696 / 12k
CG-AL-H031hard2100.0 / 10022/22OK12.4s3.2k / 10k
CG-AL-H034hard2100.0 / 1003/3OK11.9s1.4k / 3.3k
CG-AL-H036hard2100.0 / 1005/5OK11.0s1.0k / 10k
CG-AL-H037hard1100.0 / 1003/3OK14.4s512 / 4.5k
CG-AL-H041hard1100.0 / 1003/3OK11.3s618 / 5.8k
CG-AL-H050hard1100.0 / 1003/3OK11.3s528 / 6.3k
CG-AL-H054hard2100.0 / 1005/5OK11.2s2.1k / 8.0k
CG-AL-H056hard2100.0 / 1004/4OK11.5s1.6k / 8.2k
CG-AL-M001medium20.0 / 1000/0FAIL4.1s1.5k / 9.1k
CG-AL-M003medium2100.0 / 1009/9OK12.3s1.7k / 11k
CG-AL-M004medium1100.0 / 10012/12OK30.0s454 / 3.8k
CG-AL-M006medium1100.0 / 10018/18OK11.5s433 / 3.3k
CG-AL-M007medium2100.0 / 10015/15OK15.4s3.1k / 44k
CG-AL-M008medium262.5 / 1003/12OK12.8s5.6k / 14k
CG-AL-M009medium1100.0 / 10011/11OK16.1s437 / 3.5k
CG-AL-M010medium1100.0 / 10021/21OK24.1s644 / 5.0k
CG-AL-M020medium1100.0 / 10017/17OK11.1s579 / 2.3k
CG-AL-M023medium1100.0 / 10011/11OK11.4s498 / 4.3k
CG-AL-M025medium2100.0 / 1008/8OK11.8s3.3k / 20k
CG-AL-M026medium1100.0 / 1008/8OK11.2s381 / 2.1k
CG-AL-M027medium20.0 / 1000/0FAIL3.8s5.4k / 35k
CG-AL-M028medium2100.0 / 1003/3OK27.1s1.2k / 2.5k
CG-AL-M031medium1100.0 / 1002/2OK10.9s737 / 5.3k
CG-AL-M034medium1100.0 / 1002/2OK11.6s437 / 2.2k
CG-AL-M036medium211.1 / 1000/0FAIL4.2s1.6k / 4.2k
CG-AL-M040medium20.0 / 1000/0FAIL5.5s841 / 12k
CG-AL-M042medium1100.0 / 1008/8OK10.7s518 / 1.3k
CG-AL-X001hard1100.0 / 1002/2OK11.4s328 / 1.0k
CG-AL-X002hard2100.0 / 1004/4OK11.9s1.7k / 8.8k
CG-AL-X003hard2100.0 / 1003/3OK11.6s1.1k / 13k
CG-AL-X004medium1100.0 / 1003/3OK11.2s376 / 1.8k
CG-AL-X005hard1100.0 / 1002/2OK11.1s339 / 6.3k
CG-AL-X006hard1100.0 / 1003/3OK11.4s410 / 1.2k
CG-AL-X007hard1100.0 / 1002/2OK1m 26s387 / 2.6k
CG-AL-X008hard1100.0 / 1001/1OK11.2s439 / 1.8k
CG-AL-X009medium1100.0 / 1002/2OK10.8s325 / 761
CG-AL-X010medium1100.0 / 1003/3OK11.0s294 / 1.3k
CG-AL-X011medium1100.0 / 1002/2OK11.0s384 / 754
CG-AL-X012hard1100.0 / 1001/1OK11.4s405 / 1.6k
CG-AL-X013hard1100.0 / 1002/2OK10.3s266 / 504
CG-AL-X014medium1100.0 / 1004/4OK11.2s305 / 873
CG-AL-X017medium2100.0 / 1003/3OK11.9s1.7k / 989
CG-AL-X018medium1100.0 / 1003/3OK11.0s412 / 4.1k
CG-AL-X019medium2100.0 / 1003/3OK11.6s2.0k / 6.2k
CG-AL-X022medium2100.0 / 1003/3OK17.8s1.5k / 2.9k
CG-AL-X024medium1100.0 / 1003/3OK11.1s346 / 1.3k
CG-AL-X025medium1100.0 / 1001/1OK11.0s399 / 1.6k
CG-AL-X026medium1100.0 / 1003/3OK11.1s340 / 2.4k
CG-AL-X027medium1100.0 / 1004/4OK11.5s266 / 1.1k
CG-AL-X029medium1100.0 / 1002/2OK10.9s281 / 11k
CG-AL-X030medium1100.0 / 1002/2OK12.2s243 / 563
CG-AL-X031medium1100.0 / 1003/3OK11.0s309 / 604
CG-AL-X033hard1100.0 / 1002/2OK10.9s369 / 1.2k
CG-AL-X034hard1100.0 / 1003/3OK11.0s317 / 6.2k
CG-AL-X035hard1100.0 / 1003/3OK10.9s346 / 4.1k
CG-AL-X037hard1100.0 / 1004/4OK11.0s427 / 7.8k
CG-AL-X040hard1100.0 / 1004/4OK11.0s579 / 34k
CG-AL-X041hard1100.0 / 1005/5OK10.9s464 / 11k
CG-AL-X043hard20.0 / 1000/0FAIL4.4s1.8k / 43k
CG-AL-X044hard262.5 / 1001/3OK12.4s2.2k / 68k
CG-AL-X045hard1100.0 / 1003/3OK10.7s385 / 926
CG-AL-X046hard2100.0 / 1002/2OK11.5s1.8k / 6.1k
CG-AL-X047hard1100.0 / 1002/2OK11.2s414 / 5.7k
CG-AL-X050hard1100.0 / 1002/2OK10.9s436 / 3.6k
CG-AL-X051hard1100.0 / 1002/2OK10.9s550 / 2.4k
CG-AL-X052hard1100.0 / 1003/3OK10.8s377 / 3.8k
CG-AL-X055hard1100.0 / 1005/5OK11.1s355 / 2.0k
CG-AL-X056hard1100.0 / 1005/5OK10.7s285 / 568
CG-AL-X057hard1100.0 / 1005/5OK10.8s259 / 1.3k
CG-AL-X058hard1100.0 / 1005/5OK10.9s325 / 2.1k
CG-AL-X059hard1100.0 / 1003/3OK10.9s352 / 805
CG-AL-X060hard1100.0 / 1003/3OK11.1s322 / 721
CG-AL-X061hard1100.0 / 1004/4OK11.0s389 / 509
CG-AL-X062hard1100.0 / 1004/4OK10.7s373 / 1.3k
CG-AL-X063hard1100.0 / 1003/3OK10.8s379 / 1.8k
CG-AL-X064hard1100.0 / 1007/7OK10.5s283 / 1.3k
CG-AL-X065hard1100.0 / 1006/6OK10.8s818 / 9.5k
CG-AL-X066hard2100.0 / 10014/14OK11.8s4.2k / 74k
CG-AL-X067hard1100.0 / 1007/7OK10.7s661 / 2.4k
CG-AL-X068hard1100.0 / 10012/12OK10.8s1.4k / 3.8k
CG-AL-X069hard1100.0 / 1008/8OK11.0s1.3k / 22k
CG-AL-X070hard1100.0 / 10012/12OK11.2s1.3k / 6.1k
CG-AL-X071hard1100.0 / 1008/8OK11.0s1.6k / 3.0k
CG-AL-X072hard1100.0 / 1007/7OK10.6s1.3k / 5.4k
CG-AL-X073hard1100.0 / 1008/8OK11.1s1.7k / 10k
CG-AL-X074hard2100.0 / 1007/7OK11.2s4.0k / 34k
CG-AL-X075hard1100.0 / 1007/7OK10.8s931 / 31k
CG-AL-X076hard1100.0 / 10014/14OK11.2s1.1k / 5.8k
CG-AL-X077hard1100.0 / 10022/22OK11.1s1.6k / 4.6k
CG-AL-X078hard1100.0 / 10017/17OK11.1s1.4k / 2.1k
CG-AL-X079hard1100.0 / 10011/11OK11.1s1.4k / 6.6k
CG-AL-X080hard2100.0 / 1007/7OK12.3s2.9k / 9.0k
CG-AL-X081hard1100.0 / 1008/8OK10.9s1.1k / 1.6k
CG-AL-X082hard1100.0 / 10015/15OK11.0s1.4k / 4.7k
CG-AL-X083hard1100.0 / 1009/9OK11.2s1.7k / 13k
CG-AL-X084hard2100.0 / 10010/10OK11.8s3.7k / 12k
CG-AL-X085hard1100.0 / 1007/7OK10.8s1.1k / 3.7k
CG-AL-X086hard1100.0 / 1006/6OK11.0s1.6k / 5.7k
CG-AL-X087hard1100.0 / 1003/3OK10.8s1.2k / 7.8k
CG-AL-X088hard1100.0 / 1006/6OK11.1s1.1k / 24k
CG-AL-X089hard1100.0 / 10011/11OK11.3s1.2k / 5.9k
CG-AL-X090hard20.0 / 1000/0FAIL3.8s3.2k / 58k
CG-AL-X091hard1100.0 / 1006/6OK10.9s640 / 907
CG-AL-X092hard1100.0 / 10015/15OK10.7s469 / 1.1k
CG-AL-X093hard1100.0 / 10010/10OK10.9s1.1k / 9.2k
CG-AL-X094hard1100.0 / 1007/7OK11.6s854 / 2.7k
CG-AL-X095hard2100.0 / 1005/5OK11.0s3.4k / 16k
CG-AL-X096hard1100.0 / 10049/49OK11.3s3.9k / 12k
CG-AL-X097hard1100.0 / 10046/46OK11.4s3.9k / 6.9k
CG-AL-X098hard1100.0 / 10029/29OK11.3s3.1k / 6.9k
CG-AL-X099hard1100.0 / 10039/39OK12.9s4.3k / 21k
CG-AL-X100hard1100.0 / 10035/35OK11.4s4.2k / 12k
CG-AL-X101hard1100.0 / 10010/10OK11.1s1.3k / 5.1k
CG-AL-X102hard1100.0 / 1008/8OK11.0s586 / 6.8k
CG-AL-X103hard1100.0 / 1007/7OK10.8s820 / 1.4k
CG-AL-X104hard1100.0 / 1006/6OK10.9s1.2k / 3.8k
CG-AL-X105hard1100.0 / 1006/6OK11.0s877 / 1.3k
CG-AL-X106hard1100.0 / 1005/5OK10.9s1.0k / 4.4k
CG-AL-X107hard1100.0 / 1004/4OK11.0s934 / 3.3k
CG-AL-X108hard1100.0 / 1006/6OK11.7s812 / 1.4k
CG-AL-X109hard1100.0 / 1005/5OK11.6s602 / 2.1k
CG-AL-X110hard1100.0 / 10017/17OK11.0s1.4k / 2.9k
CG-AL-X111hard1100.0 / 1008/8OK11.1s1.3k / 7.5k
CG-AL-X112hard1100.0 / 10012/12OK11.1s1.0k / 19k
CG-AL-X113hard1100.0 / 10013/13OK11.2s796 / 5.2k
CG-AL-X114hard1100.0 / 1007/7OK10.9s794 / 2.1k
CG-AL-X115hard1100.0 / 10013/13OK11.0s493 / 4.7k
CG-AL-X116hard2100.0 / 10017/17OK11.6s4.4k / 19k
CG-AL-X117hard1100.0 / 1008/8OK11.5s1.2k / 1.8k
CG-AL-X118hard1100.0 / 10017/17OK11.3s1.6k / 17k
CG-AL-X119hard1100.0 / 10015/15OK11.3s2.0k / 4.1k
CG-AL-X120hard1100.0 / 10012/12OK11.4s1.4k / 2.3k
CG-AL-X121hard1100.0 / 1006/6OK11.2s1.1k / 1.9k
CG-AL-X122hard262.5 / 1009/10OK11.5s3.8k / 67k
CG-AL-X123hard1100.0 / 1005/5OK11.3s671 / 4.2k
CG-AL-X124hard1100.0 / 10010/10OK11.3s1.1k / 2.9k
CG-AL-X125hard1100.0 / 1008/8OK11.2s1.6k / 30k
CG-AL-X126hard1100.0 / 10014/14OK10.9s786 / 2.8k
CG-AL-X127hard1100.0 / 1005/5OK11.1s764 / 1.7k
CG-AL-X128hard1100.0 / 1008/8OK11.0s1.3k / 1.9k
CG-AL-X129hard1100.0 / 10014/14OK11.0s1.3k / 3.1k
CG-AL-X130hard1100.0 / 1005/5OK11.0s578 / 4.0k
CG-AL-X131hard1100.0 / 10013/13OK11.2s1.0k / 5.7k
CG-AL-X132hard1100.0 / 10010/10OK11.1s788 / 864
CG-AL-X133hard20.0 / 1000/0FAIL3.8s4.4k / 83k
CG-AL-X134hard1100.0 / 1006/6OK12.6s1.4k / 12k
CG-AL-X135hard1100.0 / 1004/4OK11.5s991 / 1.4k
CG-AL-X136hard1100.0 / 1007/7OK12.5s831 / 3.0k
CG-AL-X137hard1100.0 / 1004/4OK13.0s1.0k / 2.8k
CG-AL-X138hard1100.0 / 1009/9OK12.8s1.6k / 5.5k
CG-AL-X139hard1100.0 / 10011/11OK11.4s1.9k / 3.3k
CG-AL-X140hard2100.0 / 1007/7OK11.4s4.4k / 89k
CG-AL-X141hard1100.0 / 10039/39OK13.4s4.1k / 11k
CG-AL-X142hard262.5 / 10044/48OK12.3s11k / 40k
CG-AL-X143hard1100.0 / 10035/35OK17.1s4.8k / 12k
CG-AL-X144hard1100.0 / 10043/43OK11.7s4.2k / 17k
CG-AL-X145hard1100.0 / 10032/32OK11.8s4.9k / 8.1k
CG-AL-X146hard1100.0 / 1009/9OK11.0s1.9k / 29k
CG-AL-X147hard1100.0 / 1008/8OK11.4s1.4k / 4.2k
CG-AL-X148hard1100.0 / 1006/6OK11.0s1.3k / 2.0k
CG-AL-X149hard1100.0 / 1007/7OK10.9s1.3k / 1.7k
CG-AL-X150hard262.5 / 1008/9OK11.7s5.4k / 36k
CG-AL-X151hard1100.0 / 1006/6OK10.7s918 / 1.1k
CG-AL-X152hard1100.0 / 1008/8OK11.0s1.2k / 2.7k
CG-AL-X153hard1100.0 / 1009/9OK14.8s999 / 8.4k
CG-AL-X154hard1100.0 / 1009/9OK11.1s1.4k / 2.6k
CG-AL-X155hard1100.0 / 10011/11OK11.0s1.0k / 2.7k
CG-AL-X156hard1100.0 / 1007/7OK11.1s986 / 1.1k
CG-AL-X157hard1100.0 / 10010/10OK11.2s1.5k / 3.2k
CG-AL-X158hard1100.0 / 1007/7OK11.1s916 / 1.3k
CG-AL-X159hard1100.0 / 1007/7OK11.4s973 / 4.0k
CG-AL-X160hard1100.0 / 10013/13OK11.1s1.3k / 11k
CG-AL-X161hard1100.0 / 10010/10OK11.4s1.6k / 2.6k
CG-AL-X162hard1100.0 / 1007/7OK11.3s1.1k / 2.1k
CG-AL-X163hard1100.0 / 1007/7OK11.2s1.2k / 2.8k
CG-AL-X164hard1100.0 / 1007/7OK11.0s1.1k / 2.7k
CG-AL-X165hard1100.0 / 10013/13OK14.5s3.0k / 30k
CG-AL-X166hard1100.0 / 10014/14OK12.9s1.8k / 6.0k
CG-AL-X167hard2100.0 / 10013/13OK12.4s4.2k / 39k
CG-AL-X168hard1100.0 / 1009/9OK11.5s1.5k / 34k
CG-AL-X169hard1100.0 / 10011/11OK12.0s1.9k / 32k
CG-AL-X170hard1100.0 / 10011/11OK11.3s3.5k / 21k
CG-AL-X171hard1100.0 / 1009/9OK16.8s1.6k / 33k
CG-AL-X172hard2100.0 / 10011/11OK12.4s6.4k / 41k
CG-AL-X173hard2100.0 / 10019/19OK13.2s8.0k / 60k
CG-AL-X174hard1100.0 / 10016/16OK12.0s4.5k / 10k
CG-AL-X185hard262.5 / 10041/43OK12.6s6.2k / 20k
CG-AL-X187hard262.5 / 10032/33OK12.7s8.8k / 54k
CG-AL-X194hard262.5 / 10049/50OK13.5s11k / 48k
CG-AL-X211hard2100.0 / 10043/43OK12.7s9.4k / 36k
CG-AL-X214hard2100.0 / 10034/34OK12.9s9.3k / 60k
CG-AL-X218hard2100.0 / 10027/27OK12.2s9.1k / 53k
CG-AL-X234hard1100.0 / 10035/35OK14.1s4.3k / 26k
CG-AL-X239hard2100.0 / 10037/37OK12.7s13k / 93k
CG-AL-X244hard262.5 / 10037/38OK12.2s13k / 79k
CG-AL-X245hard1100.0 / 10063/63OK12.6s5.0k / 25k
CG-AL-X248hard1100.0 / 10066/66OK12.6s4.9k / 28k
CG-AL-X249hard2100.0 / 10037/37OK12.4s11k / 55k
CG-AL-X254hard1100.0 / 10070/70OK12.6s6.5k / 31k
CG-AL-X257hard2100.0 / 10053/53OK12.0s10k / 54k
CG-AL-X263hard2100.0 / 10061/61OK12.9s11k / 45k
CG-AL-X264hard1100.0 / 10065/65OK12.3s5.7k / 37k
CG-AL-X270hard2100.0 / 10063/63OK12.8s18k / 83k
CG-AL-X271hard2100.0 / 10070/70OK12.9s18k / 43k
CG-AL-X272hard1100.0 / 10079/79OK12.9s7.0k / 29k
CG-AL-X274hard2100.0 / 10064/64OK12.5s14k / 40k
CG-AL-X276hard262.5 / 10072/78OK14.2s19k / 74k
CG-AL-X278hard2100.0 / 10071/71OK13.5s18k / 65k
CG-AL-X283hard1100.0 / 10076/76OK12.8s7.6k / 41k
CG-AL-X289hard2100.0 / 10057/57OK13.8s12k / 76k
CG-AL-X290hard1100.0 / 10047/47OK12.6s5.9k / 41k
CG-AL-X292hard20.0 / 1000/0FAIL4.2s13k / 64k
CG-AL-X293hard1100.0 / 10049/49OK12.3s5.0k / 36k
CG-AL-X296hard2100.0 / 10047/47OK12.3s16k / 58k
CG-AL-X298hard1100.0 / 10055/55OK12.1s5.2k / 26k