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.

66.3% 138/208 of 208 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.

41.9 / 100
Cost $29.17
Tokens 1.2M / 2.7M input / output, all attempts
Duration 40m 29s
Filter:
Per-task results for run 145a7708-c39e-4e5b-8940-f768b9aec3d8
TaskDifficultyAttemptScoreTestsCompileDurationTokens
CG-AL-E001easy1100.0 / 1007/7OK16.6s413 / 314
CG-AL-E006easy1100.0 / 1007/7OK31.2s494 / 1.0k
CG-AL-E010easy1100.0 / 1005/5OK16.8s466 / 224
CG-AL-E050easy20.0 / 1000/0FAIL8.7s3.0k / 6.1k
CG-AL-E052easy1100.0 / 10016/16OK16.4s610 / 376
CG-AL-E054easy2100.0 / 1009/9OK17.4s1.7k / 932
CG-AL-E056easy20.0 / 1000/0FAIL8.7s2.8k / 1.4k
CG-AL-H007hard1100.0 / 10011/11OK11.4s947 / 1.2k
CG-AL-H011hard20.0 / 1000/0FAIL8.7s1.8k / 2.4k
CG-AL-H014hard2100.0 / 1007/7OK16.9s4.2k / 5.0k
CG-AL-H017hard20.0 / 1000/0FAIL3.8s1.8k / 1.9k
CG-AL-H020hard2100.0 / 10010/10OK12.3s3.5k / 2.5k
CG-AL-H021hard2100.0 / 10020/20OK12.4s30k / 3.3k
CG-AL-H023hard2100.0 / 10025/25OK10.9s11k / 37k
CG-AL-H027hard2100.0 / 1004/4OK10.8s3.4k / 8.3k
CG-AL-H029hard20.0 / 1000/0FAIL4.0s4.5k / 22k
CG-AL-H030hard1100.0 / 10010/10OK11.0s1.1k / 3.4k
CG-AL-H031hard1100.0 / 10022/22OK11.3s1.6k / 3.0k
CG-AL-H034hard2100.0 / 1003/3OK10.4s2.1k / 3.0k
CG-AL-H036hard20.0 / 1000/0FAIL3.9s1.5k / 1.3k
CG-AL-H037hard2100.0 / 1003/3OK10.3s2.2k / 1.3k
CG-AL-H041hard20.0 / 1000/0FAIL4.2s2.6k / 3.3k
CG-AL-H050hard262.5 / 1002/3OK10.3s2.8k / 16k
CG-AL-H054hard20.0 / 1000/0FAIL3.8s3.0k / 1.0k
CG-AL-H056hard20.0 / 1000/0FAIL3.8s2.4k / 498
CG-AL-M001medium2100.0 / 10010/10OK22.6s2.3k / 2.1k
CG-AL-M003medium2100.0 / 1009/9OK13.2s2.8k / 3.1k
CG-AL-M004medium1100.0 / 10012/12OK31.2s773 / 1.6k
CG-AL-M006medium2100.0 / 10018/18OK11.2s3.8k / 6.3k
CG-AL-M007medium20.0 / 1000/0FAIL4.0s5.5k / 20k
CG-AL-M008medium262.5 / 1001/12OK11.7s9.4k / 32k
CG-AL-M009medium1100.0 / 10011/11OK11.3s746 / 7.7k
CG-AL-M010medium1100.0 / 10021/21OK25.6s958 / 3.0k
CG-AL-M020medium2100.0 / 10017/17OK10.4s3.1k / 2.3k
CG-AL-M023medium1100.0 / 10011/11OK13.9s803 / 861
CG-AL-M025medium2100.0 / 1008/8OK10.7s4.7k / 2.3k
CG-AL-M026medium1100.0 / 1008/8OK10.7s624 / 543
CG-AL-M027medium2100.0 / 10018/18OK10.6s6.6k / 5.1k
CG-AL-M028medium211.1 / 1000/0FAIL3.8s1.7k / 1.3k
CG-AL-M031medium2100.0 / 1002/2OK10.6s3.3k / 3.4k
CG-AL-M034medium1100.0 / 1002/2OK11.8s695 / 1.1k
CG-AL-M036medium211.1 / 1000/0FAIL3.9s2.6k / 1.2k
CG-AL-M040medium20.0 / 1000/0FAIL3.7s1.3k / 1.0k
CG-AL-M042medium1100.0 / 1008/8OK11.9s753 / 523
CG-AL-X001hard1100.0 / 1002/2OK10.7s499 / 202
CG-AL-X002hard2100.0 / 1004/4OK10.2s4.0k / 6.2k
CG-AL-X003hard20.0 / 1000/0FAIL3.9s1.5k / 3.4k
CG-AL-X004medium1100.0 / 1003/3OK10.9s551 / 429
CG-AL-X005hard1100.0 / 1002/2OK10.4s515 / 226
CG-AL-X006hard1100.0 / 1003/3OK10.9s603 / 408
CG-AL-X007hard1100.0 / 1002/2OK1m 49s575 / 726
CG-AL-X008hard1100.0 / 1001/1OK10.8s641 / 2.5k
CG-AL-X009medium1100.0 / 1002/2OK10.5s493 / 225
CG-AL-X010medium1100.0 / 1003/3OK10.6s449 / 247
CG-AL-X011medium1100.0 / 1002/2OK10.6s557 / 222
CG-AL-X012hard2100.0 / 1001/1OK10.1s1.7k / 1.9k
CG-AL-X013hard2100.0 / 1002/2OK9.9s1.1k / 280
CG-AL-X017medium262.5 / 1000/3OK10.1s1.1k / 292
CG-AL-X022medium262.5 / 1001/3OK10.0s1.1k / 2.8k
CG-AL-X024medium2100.0 / 1003/3OK10.2s1.6k / 3.5k
CG-AL-X025medium2100.0 / 1001/1OK10.2s1.6k / 1.2k
CG-AL-X027medium2100.0 / 1004/4OK10.0s1.2k / 775
CG-AL-X029medium2100.0 / 1002/2OK10.0s1.3k / 3.9k
CG-AL-X030medium2100.0 / 1002/2OK10.0s903 / 556
CG-AL-X043hard20.0 / 1000/0FAIL4.1s1.9k / 20k
CG-AL-X055hard2100.0 / 1005/5OK10.2s1.4k / 781
CG-AL-X056hard2100.0 / 1005/5OK10.1s1.1k / 1.0k
CG-AL-X057hard2100.0 / 1005/5OK9.9s879 / 670
CG-AL-X064hard2100.0 / 1007/7OK10.2s1.2k / 2.1k
CG-AL-X065hard2100.0 / 1006/6OK10.1s2.4k / 6.0k
CG-AL-X066hard2100.0 / 10014/14OK10.4s4.5k / 13k
CG-AL-X067hard20.0 / 1000/0FAIL3.8s2.3k / 4.1k
CG-AL-X068hard2100.0 / 10012/12OK10.2s4.1k / 12k
CG-AL-X069hard2100.0 / 1008/8OK10.5s3.7k / 21k
CG-AL-X070hard2100.0 / 10012/12OK10.5s3.9k / 10k
CG-AL-X071hard2100.0 / 1008/8OK10.3s4.6k / 4.1k
CG-AL-X072hard2100.0 / 1007/7OK10.5s4.2k / 9.5k
CG-AL-X073hard2100.0 / 1008/8OK10.4s5.2k / 19k
CG-AL-X074hard2100.0 / 1007/7OK10.7s5.5k / 31k
CG-AL-X075hard2100.0 / 1007/7OK10.2s2.8k / 18k
CG-AL-X076hard20.0 / 1000/0FAIL3.7s2.2k / 68k
CG-AL-X077hard2100.0 / 10022/22OK10.1s5.3k / 12k
CG-AL-X078hard2100.0 / 10017/17OK10.5s4.1k / 5.7k
CG-AL-X079hard2100.0 / 10011/11OK10.5s4.3k / 6.3k
CG-AL-X080hard262.5 / 1005/7OK10.5s3.8k / 3.9k
CG-AL-X081hard2100.0 / 1008/8OK10.5s3.0k / 4.3k
CG-AL-X082hard2100.0 / 10015/15OK10.2s4.3k / 5.9k
CG-AL-X083hard262.5 / 1007/9OK10.6s5.6k / 7.2k
CG-AL-X084hard2100.0 / 10010/10OK10.8s5.1k / 7.2k
CG-AL-X085hard2100.0 / 1007/7OK10.4s3.3k / 5.5k
CG-AL-X086hard262.5 / 1004/6OK10.2s5.2k / 23k
CG-AL-X087hard2100.0 / 1003/3OK10.1s3.6k / 19k
CG-AL-X088hard2100.0 / 1006/6OK10.2s3.6k / 14k
CG-AL-X089hard20.0 / 1000/0FAIL4.2s4.2k / 32k
CG-AL-X090hard262.5 / 1007/10OK10.3s3.3k / 14k
CG-AL-X091hard2100.0 / 1006/6OK10.0s1.9k / 7.9k
CG-AL-X092hard2100.0 / 10015/15OK10.0s1.5k / 18k
CG-AL-X093hard2100.0 / 10010/10OK10.5s3.4k / 13k
CG-AL-X094hard2100.0 / 1007/7OK10.2s2.7k / 2.2k
CG-AL-X095hard2100.0 / 1005/5OK10.2s2.7k / 9.7k
CG-AL-X096hard2100.0 / 10049/49OK11.0s12k / 17k
CG-AL-X097hard2100.0 / 10046/46OK11.1s12k / 22k
CG-AL-X098hard2100.0 / 10029/29OK10.6s9.6k / 23k
CG-AL-X099hard2100.0 / 10039/39OK12.1s13k / 29k
CG-AL-X100hard2100.0 / 10035/35OK10.7s12k / 24k
CG-AL-X101hard2100.0 / 10010/10OK10.2s4.2k / 19k
CG-AL-X102hard2100.0 / 1008/8OK10.1s1.8k / 8.8k
CG-AL-X103hard2100.0 / 1007/7OK10.1s2.5k / 9.1k
CG-AL-X104hard2100.0 / 1006/6OK10.4s3.6k / 3.5k
CG-AL-X105hard2100.0 / 1006/6OK10.3s2.8k / 6.5k
CG-AL-X106hard2100.0 / 1005/5OK10.2s3.3k / 6.5k
CG-AL-X107hard2100.0 / 1004/4OK10.0s2.9k / 3.9k
CG-AL-X108hard2100.0 / 1006/6OK10.6s2.4k / 2.6k
CG-AL-X109hard262.5 / 1001/5OK10.6s1.8k / 3.9k
CG-AL-X110hard2100.0 / 10017/17OK10.4s4.2k / 12k
CG-AL-X111hard20.0 / 1000/0FAIL3.8s4.2k / 15k
CG-AL-X112hard2100.0 / 10012/12OK10.2s3.4k / 22k
CG-AL-X113hard2100.0 / 10013/13OK10.9s2.6k / 15k
CG-AL-X114hard2100.0 / 1007/7OK10.1s2.5k / 3.7k
CG-AL-X115hard2100.0 / 10013/13OK10.0s1.8k / 2.0k
CG-AL-X116hard2100.0 / 10017/17OK10.2s3.1k / 6.1k
CG-AL-X117hard2100.0 / 1008/8OK10.4s3.5k / 6.4k
CG-AL-X118hard2100.0 / 10017/17OK10.6s4.9k / 22k
CG-AL-X119hard2100.0 / 10015/15OK10.5s5.8k / 14k
CG-AL-X120hard2100.0 / 10012/12OK10.4s4.6k / 11k
CG-AL-X121hard262.5 / 1002/6OK10.3s3.4k / 5.4k
CG-AL-X122hard20.0 / 1000/0FAIL3.9s5.6k / 15k
CG-AL-X123hard2100.0 / 1005/5OK10.3s2.0k / 1.3k
CG-AL-X124hard2100.0 / 10010/10OK10.4s3.4k / 8.0k
CG-AL-X125hard2100.0 / 1008/8OK10.4s4.7k / 9.4k
CG-AL-X126hard2100.0 / 10014/14OK10.6s2.5k / 4.8k
CG-AL-X127hard262.5 / 1002/5OK10.4s2.1k / 3.3k
CG-AL-X128hard2100.0 / 1008/8OK10.4s4.0k / 12k
CG-AL-X129hard2100.0 / 10014/14OK10.7s4.3k / 8.5k
CG-AL-X130hard20.0 / 1000/0FAIL3.7s1.8k / 3.6k
CG-AL-X131hard20.0 / 1000/0FAIL3.8s3.2k / 4.0k
CG-AL-X132hard2100.0 / 10010/10OK10.4s2.5k / 2.8k
CG-AL-X133hard20.0 / 1000/0FAIL3.9s5.8k / 15k
CG-AL-X134hard2100.0 / 1006/6OK10.7s4.1k / 5.7k
CG-AL-X135hard2100.0 / 1004/4OK10.1s2.9k / 8.9k
CG-AL-X136hard2100.0 / 1007/7OK10.1s2.5k / 8.6k
CG-AL-X137hard2100.0 / 1004/4OK10.2s3.1k / 15k
CG-AL-X138hard2100.0 / 1009/9OK10.7s5.0k / 12k
CG-AL-X139hard2100.0 / 10011/11OK10.5s5.9k / 14k
CG-AL-X140hard2100.0 / 1007/7OK10.4s5.8k / 22k
CG-AL-X141hard2100.0 / 10039/39OK11.0s13k / 19k
CG-AL-X142hard2100.0 / 10048/48OK11.3s15k / 52k
CG-AL-X143hard2100.0 / 10035/35OK15.6s15k / 33k
CG-AL-X144hard2100.0 / 10043/43OK10.8s13k / 12k
CG-AL-X145hard2100.0 / 10032/32OK11.0s15k / 20k
CG-AL-X146hard2100.0 / 1009/9OK10.7s6.5k / 19k
CG-AL-X147hard2100.0 / 1008/8OK10.0s4.6k / 8.3k
CG-AL-X148hard2100.0 / 1006/6OK10.4s3.8k / 13k
CG-AL-X149hard2100.0 / 1007/7OK10.4s3.8k / 5.7k
CG-AL-X150hard262.5 / 1007/9OK10.8s7.8k / 26k
CG-AL-X151hard2100.0 / 1006/6OK10.0s3.0k / 12k
CG-AL-X152hard2100.0 / 1008/8OK10.4s3.8k / 7.0k
CG-AL-X153hard2100.0 / 1009/9OK14.1s2.8k / 4.3k
CG-AL-X154hard2100.0 / 1009/9OK10.4s4.4k / 12k
CG-AL-X155hard2100.0 / 10011/11OK10.7s3.4k / 13k
CG-AL-X156hard2100.0 / 1007/7OK10.1s3.0k / 3.3k
CG-AL-X157hard2100.0 / 10010/10OK10.5s4.4k / 12k
CG-AL-X158hard2100.0 / 1007/7OK10.0s2.7k / 8.8k
CG-AL-X159hard2100.0 / 1007/7OK10.7s2.8k / 14k
CG-AL-X160hard2100.0 / 10013/13OK10.5s4.5k / 11k
CG-AL-X161hard2100.0 / 10010/10OK11.0s5.3k / 16k
CG-AL-X162hard2100.0 / 1007/7OK10.4s3.3k / 11k
CG-AL-X163hard2100.0 / 1007/7OK10.2s3.5k / 11k
CG-AL-X164hard2100.0 / 1007/7OK10.2s3.1k / 14k
CG-AL-X165hard20.0 / 1000/0FAIL3.8s9.2k / 15k
CG-AL-X166hard20.0 / 1000/0FAIL3.9s5.2k / 4.8k
CG-AL-X167hard20.0 / 1000/0FAIL3.8s4.8k / 5.4k
CG-AL-X168hard2100.0 / 1009/9OK10.8s5.0k / 12k
CG-AL-X169hard20.0 / 1000/0FAIL3.9s6.0k / 19k
CG-AL-X170hard2100.0 / 10011/11OK10.5s11k / 26k
CG-AL-X171hard2100.0 / 1009/9OK10.5s5.7k / 18k
CG-AL-X172hard2100.0 / 10011/11OK10.7s9.0k / 38k
CG-AL-X173hard262.5 / 10017/19OK11.9s13k / 63k
CG-AL-X174hard262.5 / 10014/16OK11.0s14k / 26k
CG-AL-X185hard262.5 / 10037/43OK11.0s8.3k / 14k
CG-AL-X187hard20.0 / 1000/0FAIL3.9s11k / 21k
CG-AL-X194hard262.5 / 10048/50OK11.1s17k / 22k
CG-AL-X211hard20.0 / 1000/0FAIL3.9s13k / 26k
CG-AL-X214hard262.5 / 10031/34OK11.2s12k / 9.4k
CG-AL-X218hard20.0 / 1000/0FAIL4.0s12k / 37k
CG-AL-X234hard262.5 / 10028/35OK11.2s13k / 57k
CG-AL-X239hard262.5 / 10034/37OK11.2s17k / 14k
CG-AL-X244hard262.5 / 10035/38OK11.3s18k / 16k
CG-AL-X245hard262.5 / 10059/63OK11.7s14k / 42k
CG-AL-X248hard262.5 / 10062/66OK11.6s14k / 30k
CG-AL-X249hard262.5 / 10034/37OK11.5s15k / 17k
CG-AL-X254hard262.5 / 10060/70OK11.6s20k / 34k
CG-AL-X257hard20.0 / 1000/0FAIL3.9s14k / 37k
CG-AL-X263hard262.5 / 10057/61OK11.3s16k / 35k
CG-AL-X264hard262.5 / 10057/65OK11.4s17k / 29k
CG-AL-X270hard20.0 / 1000/0FAIL4.5s26k / 22k
CG-AL-X271hard20.0 / 1000/0FAIL4.2s26k / 37k
CG-AL-X272hard262.5 / 10075/79OK11.6s21k / 33k
CG-AL-X274hard20.0 / 1000/0FAIL4.0s19k / 30k
CG-AL-X276hard262.5 / 10073/78OK12.6s22k / 52k
CG-AL-X278hard20.0 / 1000/0FAIL4.1s22k / 35k
CG-AL-X283hard262.5 / 10071/76OK11.6s22k / 43k
CG-AL-X289hard262.5 / 10053/57OK11.2s18k / 44k
CG-AL-X290hard262.5 / 10043/47OK11.3s18k / 38k
CG-AL-X292hard262.5 / 10049/57OK11.3s16k / 53k
CG-AL-X293hard262.5 / 10045/49OK11.6s15k / 26k
CG-AL-X296hard262.5 / 10036/47OK11.7s23k / 18k
CG-AL-X298hard262.5 / 10053/55OK11.2s15k / 35k