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.

72.8% 169/232 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.

54.2 / 100
Cost $27.93
Tokens 1.2M / 2.5M input / output, all attempts
Duration 52m 11s
Filter:
Per-task results for run c7a94f8b-2bc5-4800-9f27-5905185a12cf
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK15.2s413 / 320
CG-AL-E006easy1100.0 / 1007/7OK30.8s494 / 708
CG-AL-E010easy20.0 / 1000/0FAIL8.9s1.2k / 1.1k
CG-AL-E050easy20.0 / 1000/0FAIL8.6s3.0k / 1.3k
CG-AL-E052easy1100.0 / 10016/16OK15.8s610 / 386
CG-AL-E054easy2100.0 / 1009/9OK16.2s1.7k / 1.3k
CG-AL-E056easy262.5 / 10013/15OK15.9s2.8k / 1.3k
CG-AL-H007hard1100.0 / 10011/11OK10.5s947 / 3.3k
CG-AL-H011hard20.0 / 1000/0FAIL8.7s1.7k / 5.9k
CG-AL-H014hard2100.0 / 1007/7OK10.8s4.1k / 4.9k
CG-AL-H017hard20.0 / 1000/0FAIL4.1s1.7k / 12k
CG-AL-H020hard2100.0 / 10010/10OK11.0s3.5k / 2.5k
CG-AL-H021hard2100.0 / 10020/20OK11.1s30k / 2.9k
CG-AL-H023hard2100.0 / 10025/25OK11.2s12k / 31k
CG-AL-H027hard2100.0 / 1004/4OK11.1s3.4k / 6.7k
CG-AL-H029hard20.0 / 1000/0FAIL6.5s4.6k / 9.6k
CG-AL-H030hard2100.0 / 10010/10OK11.6s3.4k / 3.2k
CG-AL-H031hard2100.0 / 10022/22OK12.5s4.9k / 5.4k
CG-AL-H034hard1100.0 / 1003/3OK10.3s720 / 5.6k
CG-AL-H036hard20.0 / 1000/0FAIL3.9s1.6k / 1.1k
CG-AL-H037hard2100.0 / 1003/3OK10.7s1.9k / 4.8k
CG-AL-H041hard262.5 / 1001/3OK15.3s2.4k / 2.7k
CG-AL-H050hard262.5 / 1001/3OK10.9s2.4k / 27k
CG-AL-H054hard20.0 / 1000/0FAIL3.9s3.1k / 1.7k
CG-AL-H056hard20.0 / 1000/0FAIL3.9s2.4k / 477
CG-AL-M001medium2100.0 / 10010/10OK23.2s2.2k / 2.0k
CG-AL-M003medium20.0 / 1000/0FAIL3.8s2.8k / 2.8k
CG-AL-M004medium1100.0 / 10012/12OK28.6s773 / 1.3k
CG-AL-M006medium262.5 / 10017/18OK12.1s5.0k / 7.5k
CG-AL-M007medium20.0 / 1000/0FAIL4.4s4.9k / 22k
CG-AL-M008medium262.5 / 1002/12OK12.0s8.4k / 34k
CG-AL-M009medium1100.0 / 10011/11OK10.2s746 / 11k
CG-AL-M010medium1100.0 / 10021/21OK23.3s958 / 4.7k
CG-AL-M020medium2100.0 / 10017/17OK10.8s3.0k / 3.6k
CG-AL-M023medium1100.0 / 10011/11OK10.5s803 / 810
CG-AL-M025medium2100.0 / 1008/8OK10.9s4.7k / 2.8k
CG-AL-M026medium2100.0 / 1008/8OK10.5s2.8k / 1.7k
CG-AL-M027medium20.0 / 1000/0FAIL4.1s6.8k / 5.6k
CG-AL-M028medium211.1 / 1000/0FAIL5.4s1.5k / 4.4k
CG-AL-M031medium2100.0 / 1002/2OK11.6s3.4k / 4.9k
CG-AL-M034medium2100.0 / 1002/2OK11.1s2.6k / 2.3k
CG-AL-M036medium211.1 / 1000/0FAIL3.7s2.6k / 2.7k
CG-AL-M040medium20.0 / 1000/0FAIL3.9s1.3k / 5.6k
CG-AL-M042medium1100.0 / 1008/8OK10.3s753 / 478
CG-AL-X001hard1100.0 / 1002/2OK10.5s499 / 203
CG-AL-X002hard2100.0 / 1004/4OK11.0s4.1k / 9.8k
CG-AL-X003hard20.0 / 1000/0FAIL3.9s1.2k / 2.7k
CG-AL-X004medium1100.0 / 1003/3OK10.2s551 / 405
CG-AL-X005hard1100.0 / 1002/2OK10.3s515 / 262
CG-AL-X006hard1100.0 / 1003/3OK10.2s603 / 411
CG-AL-X007hard1100.0 / 1002/2OK1m 18s575 / 290
CG-AL-X008hard2100.0 / 1001/1OK11.3s2.3k / 4.4k
CG-AL-X009medium1100.0 / 1002/2OK9.9s493 / 207
CG-AL-X010medium1100.0 / 1003/3OK10.0s449 / 238
CG-AL-X011medium1100.0 / 1002/2OK10.1s557 / 226
CG-AL-X012hard1100.0 / 1001/1OK10.5s589 / 1.0k
CG-AL-X013hard1100.0 / 1002/2OK10.7s423 / 144
CG-AL-X014medium1100.0 / 1004/4OK10.3s458 / 149
CG-AL-X017medium2100.0 / 1003/3OK10.6s2.4k / 409
CG-AL-X018medium1100.0 / 1003/3OK10.8s606 / 303
CG-AL-X019medium2100.0 / 1003/3OK11.0s2.8k / 2.3k
CG-AL-X022medium2100.0 / 1003/3OK11.5s2.1k / 4.9k
CG-AL-X024medium1100.0 / 1003/3OK10.1s541 / 518
CG-AL-X025medium1100.0 / 1001/1OK10.2s601 / 526
CG-AL-X026medium1100.0 / 1003/3OK10.4s524 / 216
CG-AL-X027medium2100.0 / 1004/4OK12.0s1.3k / 753
CG-AL-X029medium1100.0 / 1002/2OK10.2s435 / 321
CG-AL-X030medium1100.0 / 1002/2OK10.0s408 / 139
CG-AL-X031medium1100.0 / 1003/3OK10.5s465 / 222
CG-AL-X033hard1100.0 / 1002/2OK10.1s558 / 218
CG-AL-X034hard2100.0 / 1003/3OK10.8s2.5k / 773
CG-AL-X035hard262.5 / 1001/3OK11.0s2.5k / 5.7k
CG-AL-X037hard262.5 / 1000/4OK10.6s1.8k / 5.1k
CG-AL-X040hard20.0 / 1000/0FAIL4.3s2.2k / 3.3k
CG-AL-X041hard20.0 / 1000/0FAIL4.3s1.9k / 23k
CG-AL-X043hard20.0 / 1000/0FAIL4.4s2.5k / 8.2k
CG-AL-X044hard262.5 / 1001/3OK11.3s1.7k / 7.5k
CG-AL-X045hard1100.0 / 1003/3OK10.2s602 / 256
CG-AL-X046hard262.5 / 1000/2OK10.3s2.5k / 10k
CG-AL-X047hard1100.0 / 1002/2OK10.4s650 / 2.8k
CG-AL-X050hard1100.0 / 1002/2OK10.5s658 / 516
CG-AL-X051hard262.5 / 1000/2OK10.8s2.0k / 733
CG-AL-X052hard1100.0 / 1003/3OK10.3s582 / 2.1k
CG-AL-X055hard1100.0 / 1005/5OK10.3s546 / 385
CG-AL-X056hard1100.0 / 1005/5OK10.0s447 / 545
CG-AL-X057hard1100.0 / 1005/5OK9.9s411 / 157
CG-AL-X058hard1100.0 / 1005/5OK10.3s500 / 444
CG-AL-X059hard1100.0 / 1003/3OK10.3s511 / 121
CG-AL-X060hard1100.0 / 1003/3OK10.2s487 / 146
CG-AL-X061hard1100.0 / 1004/4OK10.1s572 / 196
CG-AL-X062hard2100.0 / 1004/4OK10.6s2.1k / 1.1k
CG-AL-X063hard1100.0 / 1003/3OK10.3s559 / 360
CG-AL-X064hard1100.0 / 1007/7OK10.1s457 / 388
CG-AL-X065hard1100.0 / 1006/6OK10.1s1.2k / 1.6k
CG-AL-X066hard1100.0 / 10014/14OK10.2s2.2k / 2.1k
CG-AL-X067hard2100.0 / 1007/7OK10.2s2.7k / 26k
CG-AL-X068hard2100.0 / 10012/12OK10.7s9.2k / 16k
CG-AL-X069hard1100.0 / 1008/8OK10.4s1.9k / 2.7k
CG-AL-X070hard1100.0 / 10012/12OK10.5s1.9k / 1.6k
CG-AL-X071hard1100.0 / 1008/8OK10.6s2.2k / 1.9k
CG-AL-X072hard1100.0 / 1007/7OK10.5s2.1k / 1.7k
CG-AL-X073hard1100.0 / 1008/8OK11.0s2.5k / 2.3k
CG-AL-X074hard2100.0 / 1007/7OK10.6s6.0k / 17k
CG-AL-X075hard1100.0 / 1007/7OK10.1s1.4k / 3.5k
CG-AL-X076hard1100.0 / 10014/14OK10.4s1.6k / 55k
CG-AL-X077hard1100.0 / 10022/22OK10.2s2.6k / 2.4k
CG-AL-X078hard1100.0 / 10017/17OK10.1s2.0k / 1.6k
CG-AL-X079hard1100.0 / 10011/11OK10.5s2.0k / 2.5k
CG-AL-X080hard262.5 / 1006/7OK11.0s4.3k / 6.0k
CG-AL-X081hard1100.0 / 1008/8OK10.0s1.5k / 1.1k
CG-AL-X082hard1100.0 / 10015/15OK10.3s2.1k / 1.8k
CG-AL-X083hard1100.0 / 1009/9OK10.1s2.8k / 2.5k
CG-AL-X084hard1100.0 / 10010/10OK10.5s2.5k / 2.7k
CG-AL-X085hard1100.0 / 1007/7OK10.1s1.6k / 1.2k
CG-AL-X086hard1100.0 / 1006/6OK10.5s2.4k / 12k
CG-AL-X087hard1100.0 / 1003/3OK10.2s1.8k / 2.1k
CG-AL-X088hard1100.0 / 1006/6OK10.3s1.7k / 2.5k
CG-AL-X089hard1100.0 / 10011/11OK10.7s1.8k / 13k
CG-AL-X090hard20.0 / 1000/0FAIL3.7s4.7k / 12k
CG-AL-X091hard1100.0 / 1006/6OK10.1s941 / 647
CG-AL-X092hard1100.0 / 10015/15OK10.0s716 / 395
CG-AL-X093hard1100.0 / 10010/10OK10.0s1.7k / 1.5k
CG-AL-X094hard1100.0 / 1007/7OK10.1s1.3k / 1.2k
CG-AL-X095hard1100.0 / 1005/5OK10.2s1.3k / 1.1k
CG-AL-X096hard1100.0 / 10049/49OK10.7s6.0k / 5.8k
CG-AL-X097hard1100.0 / 10046/46OK10.9s6.0k / 6.0k
CG-AL-X098hard1100.0 / 10029/29OK10.4s4.8k / 4.6k
CG-AL-X099hard1100.0 / 10039/39OK12.3s6.4k / 17k
CG-AL-X100hard20.0 / 1000/0FAIL4.1s12k / 37k
CG-AL-X101hard262.5 / 1005/10OK10.9s4.2k / 7.6k
CG-AL-X102hard2100.0 / 1008/8OK10.7s1.8k / 9.2k
CG-AL-X103hard262.5 / 1003/7OK10.8s2.5k / 11k
CG-AL-X104hard2100.0 / 1006/6OK10.8s3.6k / 3.7k
CG-AL-X105hard2100.0 / 1006/6OK10.7s2.8k / 6.2k
CG-AL-X106hard2100.0 / 1005/5OK10.8s3.2k / 18k
CG-AL-X107hard2100.0 / 1004/4OK10.5s2.9k / 4.9k
CG-AL-X108hard2100.0 / 1006/6OK11.4s2.4k / 5.4k
CG-AL-X109hard2100.0 / 1005/5OK12.7s1.8k / 1.8k
CG-AL-X110hard20.0 / 1000/0FAIL4.0s4.3k / 10.0k
CG-AL-X111hard2100.0 / 1008/8OK10.7s4.2k / 21k
CG-AL-X112hard2100.0 / 10012/12OK10.4s3.1k / 11k
CG-AL-X113hard2100.0 / 10013/13OK11.7s2.7k / 4.6k
CG-AL-X114hard2100.0 / 1007/7OK10.6s2.5k / 3.5k
CG-AL-X115hard20.0 / 1000/0FAIL3.7s1.8k / 2.6k
CG-AL-X116hard2100.0 / 10017/17OK10.5s3.1k / 5.6k
CG-AL-X117hard2100.0 / 1008/8OK10.6s3.5k / 7.9k
CG-AL-X118hard262.5 / 10016/17OK11.0s5.0k / 21k
CG-AL-X119hard20.0 / 1000/0FAIL4.0s5.8k / 7.9k
CG-AL-X120hard2100.0 / 10012/12OK10.5s4.6k / 9.7k
CG-AL-X121hard262.5 / 1005/6OK10.4s3.4k / 12k
CG-AL-X122hard2100.0 / 10010/10OK10.6s5.4k / 8.7k
CG-AL-X123hard2100.0 / 1005/5OK11.4s2.0k / 1.2k
CG-AL-X124hard2100.0 / 10010/10OK12.0s3.4k / 8.8k
CG-AL-X125hard2100.0 / 1008/8OK12.1s4.7k / 8.7k
CG-AL-X126hard2100.0 / 10014/14OK10.9s2.5k / 6.5k
CG-AL-X127hard262.5 / 1004/5OK10.7s2.1k / 2.3k
CG-AL-X128hard2100.0 / 1008/8OK10.7s4.0k / 17k
CG-AL-X129hard20.0 / 1000/0FAIL3.7s4.3k / 6.1k
CG-AL-X130hard20.0 / 1000/0FAIL4.0s1.8k / 5.9k
CG-AL-X131hard2100.0 / 10013/13OK10.4s3.2k / 4.0k
CG-AL-X132hard2100.0 / 10010/10OK11.0s2.5k / 2.8k
CG-AL-X133hard20.0 / 1000/0FAIL4.0s5.5k / 13k
CG-AL-X134hard2100.0 / 1006/6OK11.7s4.1k / 7.4k
CG-AL-X135hard2100.0 / 1004/4OK12.7s2.9k / 11k
CG-AL-X136hard2100.0 / 1007/7OK13.6s2.5k / 19k
CG-AL-X137hard2100.0 / 1004/4OK11.7s3.1k / 9.9k
CG-AL-X138hard2100.0 / 1009/9OK11.8s5.1k / 5.5k
CG-AL-X139hard2100.0 / 10011/11OK10.9s5.9k / 8.9k
CG-AL-X140hard2100.0 / 1007/7OK11.0s6.2k / 39k
CG-AL-X141hard2100.0 / 10039/39OK11.8s12k / 15k
CG-AL-X142hard2100.0 / 10048/48OK11.8s14k / 45k
CG-AL-X143hard2100.0 / 10035/35OK15.9s15k / 21k
CG-AL-X144hard2100.0 / 10043/43OK11.0s13k / 12k
CG-AL-X145hard2100.0 / 10032/32OK11.7s15k / 33k
CG-AL-X146hard2100.0 / 1009/9OK11.0s6.5k / 25k
CG-AL-X147hard2100.0 / 1008/8OK10.8s4.6k / 8.9k
CG-AL-X148hard2100.0 / 1006/6OK10.7s3.8k / 19k
CG-AL-X149hard2100.0 / 1007/7OK11.0s3.8k / 3.9k
CG-AL-X150hard2100.0 / 1009/9OK10.9s8.1k / 16k
CG-AL-X151hard2100.0 / 1006/6OK10.2s3.0k / 5.7k
CG-AL-X152hard2100.0 / 1008/8OK10.4s3.8k / 5.9k
CG-AL-X153hard2100.0 / 1009/9OK14.6s2.9k / 4.0k
CG-AL-X154hard2100.0 / 1009/9OK10.4s4.4k / 11k
CG-AL-X155hard2100.0 / 10011/11OK10.5s3.4k / 8.5k
CG-AL-X156hard2100.0 / 1007/7OK10.3s3.0k / 5.1k
CG-AL-X157hard2100.0 / 10010/10OK10.4s4.4k / 7.7k
CG-AL-X158hard2100.0 / 1007/7OK10.5s2.7k / 10k
CG-AL-X159hard2100.0 / 1007/7OK10.9s2.8k / 15k
CG-AL-X160hard2100.0 / 10013/13OK10.7s4.5k / 9.6k
CG-AL-X161hard20.0 / 1000/0FAIL3.9s5.3k / 5.3k
CG-AL-X162hard2100.0 / 1007/7OK10.9s3.3k / 14k
CG-AL-X163hard2100.0 / 1007/7OK10.4s3.5k / 13k
CG-AL-X164hard2100.0 / 1007/7OK10.5s3.1k / 5.3k
CG-AL-X165hard20.0 / 1000/0FAIL3.9s9.4k / 21k
CG-AL-X166hard20.0 / 1000/0FAIL4.0s5.2k / 4.9k
CG-AL-X167hard20.0 / 1000/0FAIL3.9s5.5k / 31k
CG-AL-X168hard2100.0 / 1009/9OK10.7s4.7k / 22k
CG-AL-X169hard2100.0 / 10011/11OK11.3s6.0k / 30k
CG-AL-X170hard2100.0 / 10011/11OK11.3s11k / 16k
CG-AL-X171hard2100.0 / 1009/9OK13.2s5.7k / 22k
CG-AL-X172hard2100.0 / 10011/11OK10.7s9.4k / 38k
CG-AL-X173hard20.0 / 1000/0FAIL4.0s12k / 64k
CG-AL-X174hard2100.0 / 10016/16OK10.9s14k / 28k
CG-AL-X185hard262.5 / 10034/43OK11.2s8.3k / 34k
CG-AL-X187hard262.5 / 10029/33OK11.2s11k / 22k
CG-AL-X194hard262.5 / 10048/50OK11.2s17k / 30k
CG-AL-X211hard262.5 / 10036/43OK11.7s13k / 59k
CG-AL-X214hard262.5 / 10031/34OK11.2s12k / 28k
CG-AL-X218hard262.5 / 10024/27OK11.3s12k / 34k
CG-AL-X234hard20.0 / 1000/0FAIL4.1s13k / 47k
CG-AL-X239hard262.5 / 10034/37OK11.6s17k / 14k
CG-AL-X244hard262.5 / 10035/38OK11.6s19k / 41k
CG-AL-X245hard262.5 / 10059/63OK11.7s14k / 33k
CG-AL-X248hard262.5 / 10062/66OK11.7s14k / 17k
CG-AL-X249hard2100.0 / 10037/37OK11.3s16k / 35k
CG-AL-X254hard2100.0 / 10070/70OK12.3s23k / 24k
CG-AL-X257hard262.5 / 10051/53OK11.6s18k / 75k
CG-AL-X263hard2100.0 / 10061/61OK11.9s21k / 24k
CG-AL-X264hard262.5 / 10063/65OK11.9s23k / 66k
CG-AL-X270hard2100.0 / 10063/63OK12.2s32k / 34k
CG-AL-X271hard262.5 / 10063/70OK12.0s28k / 23k
CG-AL-X272hard2100.0 / 10079/79OK12.2s23k / 22k
CG-AL-X274hard2100.0 / 10064/64OK11.9s23k / 24k
CG-AL-X276hard2100.0 / 10078/78OK12.4s23k / 29k
CG-AL-X278hard2100.0 / 10071/71OK12.3s26k / 34k
CG-AL-X283hard2100.0 / 10076/76OK11.9s25k / 40k
CG-AL-X289hard2100.0 / 10057/57OK11.7s20k / 31k
CG-AL-X290hard2100.0 / 10047/47OK11.6s20k / 26k
CG-AL-X292hard2100.0 / 10057/57OK11.8s21k / 32k
CG-AL-X293hard2100.0 / 10049/49OK11.6s19k / 25k
CG-AL-X296hard262.5 / 10046/47OK14.9s29k / 23k
CG-AL-X298hard262.5 / 10054/55OK15.1s15k / 24k