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.

92.7% 215/232 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.

84.3 / 100
Cost $13.34
Tokens 624k / 3.4M input / output, all attempts
Duration 58m 10s
Filter:
Per-task results for run 9d1ac7e7-d750-4fb4-b899-825cb8bef267
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK18.8s263 / 834
CG-AL-E006easy1100.0 / 1007/7OK33.7s309 / 2.1k
CG-AL-E010easy262.5 / 1000/1OK33.4s759 / 3.9k
CG-AL-E050easy2100.0 / 10013/13OK17.6s2.2k / 15k
CG-AL-E052easy1100.0 / 10016/16OK10.9s360 / 703
CG-AL-E054easy2100.0 / 1009/9OK17.3s1.1k / 5.0k
CG-AL-E056easy2100.0 / 10015/15OK11.1s1.9k / 2.8k
CG-AL-H007hard1100.0 / 10011/11OK11.1s556 / 25k
CG-AL-H011hard2100.0 / 1006/6OK11.8s980 / 4.9k
CG-AL-H014hard20.0 / 1000/0FAIL4.1s1.5k / 5.0k
CG-AL-H017hard2100.0 / 1005/5OK13.0s1.0k / 21k
CG-AL-H020hard1100.0 / 10010/10OK10.9s477 / 2.1k
CG-AL-H021hard1100.0 / 10020/20OK11.5s610 / 3.0k
CG-AL-H023hard2100.0 / 10025/25OK11.8s6.8k / 26k
CG-AL-H027hard1100.0 / 1004/4OK11.8s783 / 6.5k
CG-AL-H029hard2100.0 / 10018/18OK11.4s3.1k / 30k
CG-AL-H030hard1100.0 / 10010/10OK11.6s696 / 10k
CG-AL-H031hard1100.0 / 10022/22OK11.4s993 / 4.9k
CG-AL-H034hard2100.0 / 1003/3OK11.5s1.4k / 6.5k
CG-AL-H036hard2100.0 / 1005/5OK11.4s978 / 3.5k
CG-AL-H037hard1100.0 / 1003/3OK11.3s512 / 2.9k
CG-AL-H041hard2100.0 / 1003/3OK11.7s2.6k / 23k
CG-AL-H050hard1100.0 / 1003/3OK11.2s528 / 6.0k
CG-AL-H054hard2100.0 / 1005/5OK10.8s2.0k / 6.2k
CG-AL-H056hard2100.0 / 1004/4OK11.1s1.6k / 8.3k
CG-AL-M001medium20.0 / 1000/0FAIL4.2s1.5k / 5.7k
CG-AL-M003medium262.5 / 1000/1OK27.8s1.7k / 13k
CG-AL-M004medium1100.0 / 10012/12OK28.2s454 / 2.3k
CG-AL-M006medium2100.0 / 10018/18OK11.9s3.1k / 24k
CG-AL-M007medium2100.0 / 10015/15OK15.0s3.1k / 24k
CG-AL-M008medium262.5 / 1004/12OK12.0s4.9k / 18k
CG-AL-M009medium1100.0 / 10011/11OK10.7s437 / 3.0k
CG-AL-M010medium1100.0 / 10021/21OK24.5s644 / 5.3k
CG-AL-M020medium1100.0 / 10017/17OK11.1s579 / 1.9k
CG-AL-M023medium1100.0 / 10011/11OK11.7s498 / 6.5k
CG-AL-M025medium1100.0 / 1008/8OK11.1s419 / 2.6k
CG-AL-M026medium1100.0 / 1008/8OK10.7s381 / 7.6k
CG-AL-M027medium262.5 / 10016/18OK12.3s4.7k / 11k
CG-AL-M028medium2100.0 / 1003/3OK24.0s1.1k / 2.3k
CG-AL-M031medium1100.0 / 1002/2OK10.9s737 / 9.8k
CG-AL-M034medium1100.0 / 1002/2OK10.8s437 / 2.9k
CG-AL-M036medium211.1 / 1000/0FAIL4.0s1.6k / 3.2k
CG-AL-M040medium20.0 / 1000/0FAIL3.9s856 / 12k
CG-AL-M042medium1100.0 / 1008/8OK11.0s518 / 1.9k
CG-AL-X001hard1100.0 / 1002/2OK10.8s328 / 823
CG-AL-X002hard1100.0 / 1004/4OK11.0s532 / 4.3k
CG-AL-X003hard2100.0 / 1003/3OK16.5s1.1k / 15k
CG-AL-X004medium1100.0 / 1003/3OK11.1s376 / 1.6k
CG-AL-X005hard1100.0 / 1002/2OK10.9s339 / 4.8k
CG-AL-X006hard1100.0 / 1003/3OK11.0s410 / 1.5k
CG-AL-X007hard1100.0 / 1002/2OK1m 31s387 / 1.3k
CG-AL-X008hard1100.0 / 1001/1OK11.0s439 / 1.8k
CG-AL-X009medium1100.0 / 1002/2OK11.0s325 / 1.4k
CG-AL-X010medium1100.0 / 1003/3OK11.0s294 / 1.7k
CG-AL-X011medium1100.0 / 1002/2OK10.8s384 / 874
CG-AL-X012hard1100.0 / 1001/1OK10.7s405 / 1.5k
CG-AL-X013hard1100.0 / 1002/2OK10.5s266 / 914
CG-AL-X014medium1100.0 / 1004/4OK11.2s305 / 2.6k
CG-AL-X017medium2100.0 / 1003/3OK11.2s1.7k / 1.1k
CG-AL-X018medium1100.0 / 1003/3OK10.9s412 / 3.5k
CG-AL-X019medium2100.0 / 1003/3OK11.7s2.0k / 5.4k
CG-AL-X022medium2100.0 / 1003/3OK11.4s1.5k / 4.5k
CG-AL-X024medium1100.0 / 1003/3OK10.9s346 / 1.4k
CG-AL-X025medium1100.0 / 1001/1OK10.7s399 / 1.2k
CG-AL-X026medium1100.0 / 1003/3OK10.6s340 / 4.4k
CG-AL-X027medium1100.0 / 1004/4OK10.4s266 / 1.1k
CG-AL-X029medium1100.0 / 1002/2OK11.7s281 / 7.0k
CG-AL-X030medium1100.0 / 1002/2OK10.6s243 / 985
CG-AL-X031medium1100.0 / 1003/3OK10.8s309 / 705
CG-AL-X033hard1100.0 / 1002/2OK11.0s369 / 1.0k
CG-AL-X034hard1100.0 / 1003/3OK11.0s317 / 16k
CG-AL-X035hard1100.0 / 1003/3OK10.8s346 / 2.4k
CG-AL-X037hard1100.0 / 1004/4OK11.6s427 / 8.4k
CG-AL-X040hard1100.0 / 1004/4OK11.1s579 / 18k
CG-AL-X041hard1100.0 / 1005/5OK11.0s464 / 12k
CG-AL-X043hard20.0 / 1000/0FAIL4.7s1.6k / 25k
CG-AL-X044hard262.5 / 1001/3OK11.7s1.9k / 60k
CG-AL-X045hard1100.0 / 1003/3OK11.0s385 / 1.1k
CG-AL-X046hard1100.0 / 1002/2OK11.0s402 / 3.4k
CG-AL-X047hard1100.0 / 1002/2OK11.1s414 / 5.9k
CG-AL-X050hard1100.0 / 1002/2OK10.7s436 / 2.2k
CG-AL-X051hard1100.0 / 1002/2OK10.8s550 / 2.4k
CG-AL-X052hard1100.0 / 1003/3OK10.8s377 / 4.2k
CG-AL-X055hard1100.0 / 1005/5OK10.6s355 / 854
CG-AL-X056hard1100.0 / 1005/5OK10.8s285 / 862
CG-AL-X057hard1100.0 / 1005/5OK10.7s259 / 834
CG-AL-X058hard1100.0 / 1005/5OK11.0s325 / 1.4k
CG-AL-X059hard1100.0 / 1003/3OK10.7s352 / 740
CG-AL-X060hard1100.0 / 1003/3OK11.2s322 / 759
CG-AL-X061hard1100.0 / 1004/4OK10.7s389 / 646
CG-AL-X062hard1100.0 / 1004/4OK11.0s373 / 1.3k
CG-AL-X063hard1100.0 / 1003/3OK11.0s379 / 1.5k
CG-AL-X064hard1100.0 / 1007/7OK10.7s283 / 1.3k
CG-AL-X065hard1100.0 / 1006/6OK10.8s818 / 4.3k
CG-AL-X066hard2100.0 / 10014/14OK11.0s4.2k / 51k
CG-AL-X067hard1100.0 / 1007/7OK10.8s661 / 2.9k
CG-AL-X068hard1100.0 / 10012/12OK10.9s1.4k / 4.5k
CG-AL-X069hard1100.0 / 1008/8OK11.0s1.3k / 25k
CG-AL-X070hard1100.0 / 10012/12OK12.5s1.3k / 4.6k
CG-AL-X071hard1100.0 / 1008/8OK11.1s1.6k / 2.8k
CG-AL-X072hard1100.0 / 1007/7OK10.8s1.3k / 5.4k
CG-AL-X073hard1100.0 / 1008/8OK11.2s1.7k / 9.2k
CG-AL-X074hard2100.0 / 1007/7OK11.1s4.0k / 32k
CG-AL-X075hard1100.0 / 1007/7OK10.8s931 / 14k
CG-AL-X076hard1100.0 / 10014/14OK11.2s1.1k / 6.5k
CG-AL-X077hard1100.0 / 10022/22OK11.0s1.6k / 4.9k
CG-AL-X078hard1100.0 / 10017/17OK11.0s1.4k / 1.9k
CG-AL-X079hard1100.0 / 10011/11OK11.3s1.4k / 7.1k
CG-AL-X080hard2100.0 / 1007/7OK11.1s2.9k / 13k
CG-AL-X081hard1100.0 / 1008/8OK12.0s1.1k / 1.5k
CG-AL-X082hard1100.0 / 10015/15OK11.2s1.4k / 6.1k
CG-AL-X083hard1100.0 / 1009/9OK10.9s1.7k / 5.8k
CG-AL-X084hard2100.0 / 10010/10OK12.2s3.7k / 12k
CG-AL-X085hard1100.0 / 1007/7OK11.0s1.1k / 6.5k
CG-AL-X086hard1100.0 / 1006/6OK11.1s1.6k / 8.4k
CG-AL-X087hard1100.0 / 1003/3OK11.2s1.2k / 6.7k
CG-AL-X088hard1100.0 / 1006/6OK11.1s1.1k / 8.9k
CG-AL-X089hard1100.0 / 10011/11OK11.2s1.2k / 5.2k
CG-AL-X090hard2100.0 / 10010/10OK11.3s3.3k / 54k
CG-AL-X091hard1100.0 / 1006/6OK10.9s640 / 694
CG-AL-X092hard1100.0 / 10015/15OK10.8s469 / 804
CG-AL-X093hard1100.0 / 10010/10OK10.9s1.1k / 17k
CG-AL-X094hard1100.0 / 1007/7OK10.8s854 / 2.0k
CG-AL-X095hard2100.0 / 1005/5OK10.7s3.4k / 20k
CG-AL-X096hard1100.0 / 10049/49OK11.3s3.9k / 12k
CG-AL-X097hard1100.0 / 10046/46OK11.7s3.9k / 8.1k
CG-AL-X098hard1100.0 / 10029/29OK11.4s3.1k / 6.1k
CG-AL-X099hard1100.0 / 10039/39OK13.1s4.3k / 26k
CG-AL-X100hard2100.0 / 10035/35OK12.0s8.6k / 29k
CG-AL-X101hard1100.0 / 10010/10OK11.0s1.3k / 5.7k
CG-AL-X102hard1100.0 / 1008/8OK11.4s586 / 8.9k
CG-AL-X103hard1100.0 / 1007/7OK10.7s820 / 1.3k
CG-AL-X104hard1100.0 / 1006/6OK11.0s1.2k / 2.6k
CG-AL-X105hard1100.0 / 1006/6OK11.2s877 / 1.3k
CG-AL-X106hard1100.0 / 1005/5OK10.7s1.0k / 4.7k
CG-AL-X107hard1100.0 / 1004/4OK10.8s934 / 2.0k
CG-AL-X108hard1100.0 / 1006/6OK11.5s812 / 1.4k
CG-AL-X109hard1100.0 / 1005/5OK11.0s602 / 1.8k
CG-AL-X110hard1100.0 / 10017/17OK10.7s1.4k / 3.1k
CG-AL-X111hard1100.0 / 1008/8OK11.0s1.3k / 12k
CG-AL-X112hard1100.0 / 10012/12OK11.2s1.0k / 17k
CG-AL-X113hard1100.0 / 10013/13OK11.3s796 / 7.6k
CG-AL-X114hard1100.0 / 1007/7OK10.7s794 / 5.0k
CG-AL-X115hard1100.0 / 10013/13OK10.9s493 / 2.7k
CG-AL-X116hard1100.0 / 10017/17OK10.8s987 / 13k
CG-AL-X117hard1100.0 / 1008/8OK11.0s1.2k / 1.6k
CG-AL-X118hard1100.0 / 10017/17OK11.0s1.6k / 12k
CG-AL-X119hard1100.0 / 10015/15OK11.1s2.0k / 3.8k
CG-AL-X120hard1100.0 / 10012/12OK11.0s1.4k / 2.4k
CG-AL-X121hard1100.0 / 1006/6OK10.9s1.1k / 1.8k
CG-AL-X122hard2100.0 / 10010/10OK11.7s3.8k / 46k
CG-AL-X123hard1100.0 / 1005/5OK11.1s671 / 11k
CG-AL-X124hard1100.0 / 10010/10OK11.1s1.1k / 3.4k
CG-AL-X125hard1100.0 / 1008/8OK11.1s1.6k / 17k
CG-AL-X126hard1100.0 / 10014/14OK10.7s786 / 3.4k
CG-AL-X127hard1100.0 / 1005/5OK11.1s764 / 1.8k
CG-AL-X128hard1100.0 / 1008/8OK10.8s1.3k / 1.7k
CG-AL-X129hard1100.0 / 10014/14OK10.8s1.3k / 3.8k
CG-AL-X130hard1100.0 / 1005/5OK10.8s578 / 4.3k
CG-AL-X131hard1100.0 / 10013/13OK10.8s1.0k / 3.7k
CG-AL-X132hard1100.0 / 10010/10OK10.8s788 / 776
CG-AL-X133hard2100.0 / 1008/8OK11.5s4.5k / 88k
CG-AL-X134hard1100.0 / 1006/6OK11.3s1.4k / 14k
CG-AL-X135hard1100.0 / 1004/4OK10.9s991 / 1.2k
CG-AL-X136hard1100.0 / 1007/7OK10.8s831 / 4.6k
CG-AL-X137hard1100.0 / 1004/4OK10.7s1.0k / 3.0k
CG-AL-X138hard1100.0 / 1009/9OK19.1s1.6k / 6.5k
CG-AL-X139hard1100.0 / 10011/11OK11.2s1.9k / 3.4k
CG-AL-X140hard1100.0 / 1007/7OK11.0s1.7k / 53k
CG-AL-X141hard1100.0 / 10039/39OK11.7s4.1k / 9.8k
CG-AL-X142hard2100.0 / 10048/48OK13.6s11k / 57k
CG-AL-X143hard1100.0 / 10035/35OK15.8s4.8k / 20k
CG-AL-X144hard1100.0 / 10043/43OK11.5s4.2k / 16k
CG-AL-X145hard1100.0 / 10032/32OK11.6s4.9k / 7.5k
CG-AL-X146hard2100.0 / 1009/9OK11.5s4.3k / 53k
CG-AL-X147hard1100.0 / 1008/8OK11.5s1.4k / 4.0k
CG-AL-X148hard1100.0 / 1006/6OK11.0s1.3k / 1.4k
CG-AL-X149hard1100.0 / 1007/7OK11.0s1.3k / 2.4k
CG-AL-X150hard1100.0 / 1009/9OK11.4s2.2k / 29k
CG-AL-X151hard1100.0 / 1006/6OK11.0s918 / 1.2k
CG-AL-X152hard1100.0 / 1008/8OK11.0s1.2k / 4.0k
CG-AL-X153hard1100.0 / 1009/9OK14.9s999 / 4.3k
CG-AL-X154hard1100.0 / 1009/9OK10.8s1.4k / 4.1k
CG-AL-X155hard1100.0 / 10011/11OK11.1s1.0k / 2.0k
CG-AL-X156hard1100.0 / 1007/7OK11.0s986 / 1.1k
CG-AL-X157hard1100.0 / 10010/10OK11.0s1.5k / 2.4k
CG-AL-X158hard1100.0 / 1007/7OK11.1s916 / 940
CG-AL-X159hard1100.0 / 1007/7OK11.7s973 / 4.6k
CG-AL-X160hard1100.0 / 10013/13OK11.2s1.3k / 15k
CG-AL-X161hard1100.0 / 10010/10OK11.3s1.6k / 2.9k
CG-AL-X162hard1100.0 / 1007/7OK11.3s1.1k / 1.7k
CG-AL-X163hard1100.0 / 1007/7OK10.9s1.2k / 2.1k
CG-AL-X164hard1100.0 / 1007/7OK10.9s1.1k / 2.7k
CG-AL-X165hard1100.0 / 10013/13OK13.7s3.0k / 27k
CG-AL-X166hard1100.0 / 10014/14OK12.3s1.8k / 4.6k
CG-AL-X167hard1100.0 / 10013/13OK11.4s1.5k / 34k
CG-AL-X168hard1100.0 / 1009/9OK11.0s1.5k / 28k
CG-AL-X169hard1100.0 / 10011/11OK11.9s1.9k / 35k
CG-AL-X170hard1100.0 / 10011/11OK11.5s3.5k / 17k
CG-AL-X171hard2100.0 / 1009/9OK11.7s5.8k / 40k
CG-AL-X172hard262.5 / 10010/11OK17.1s6.3k / 46k
CG-AL-X173hard20.0 / 1000/0FAIL4.4s8.0k / 72k
CG-AL-X174hard1100.0 / 10016/16OK12.0s4.5k / 12k
CG-AL-X185hard262.5 / 10041/43OK12.0s6.2k / 13k
CG-AL-X187hard2100.0 / 10033/33OK13.2s8.8k / 51k
CG-AL-X194hard2100.0 / 10050/50OK12.5s11k / 44k
CG-AL-X211hard2100.0 / 10043/43OK12.9s9.9k / 39k
CG-AL-X214hard262.5 / 10031/34OK12.4s9.3k / 64k
CG-AL-X218hard2100.0 / 10027/27OK12.9s9.1k / 63k
CG-AL-X234hard1100.0 / 10035/35OK12.4s4.3k / 33k
CG-AL-X239hard262.5 / 10034/37OK16.4s13k / 70k
CG-AL-X244hard2100.0 / 10038/38OK15.0s13k / 78k
CG-AL-X245hard1100.0 / 10063/63OK12.4s5.0k / 31k
CG-AL-X248hard1100.0 / 10066/66OK12.5s4.9k / 33k
CG-AL-X249hard2100.0 / 10037/37OK13.2s11k / 48k
CG-AL-X254hard1100.0 / 10070/70OK12.4s6.5k / 31k
CG-AL-X257hard2100.0 / 10053/53OK13.4s11k / 81k
CG-AL-X263hard2100.0 / 10061/61OK14.7s11k / 40k
CG-AL-X264hard1100.0 / 10065/65OK12.5s5.7k / 44k
CG-AL-X270hard2100.0 / 10063/63OK13.6s18k / 56k
CG-AL-X271hard2100.0 / 10070/70OK14.0s20k / 59k
CG-AL-X272hard2100.0 / 10079/79OK13.7s14k / 39k
CG-AL-X274hard2100.0 / 10064/64OK14.3s14k / 52k
CG-AL-X276hard2100.0 / 10078/78OK14.1s18k / 66k
CG-AL-X278hard262.5 / 10068/71OK13.8s18k / 77k
CG-AL-X283hard1100.0 / 10076/76OK12.3s7.6k / 41k
CG-AL-X289hard1100.0 / 10057/57OK13.0s5.8k / 33k
CG-AL-X290hard262.5 / 10046/47OK12.4s12k / 58k
CG-AL-X292hard2100.0 / 10057/57OK14.1s12k / 64k
CG-AL-X293hard1100.0 / 10049/49OK11.9s5.0k / 38k
CG-AL-X296hard2100.0 / 10047/47OK14.1s16k / 49k
CG-AL-X298hard2100.0 / 10055/55OK14.1s16k / 38k