internlm/internlm2_5-20b
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| CMMLU | knowledge | 82.22 | CMMLU | medium | | CMMLU | 82.22 | 68.29 | |
| BBH | reasoning | 77.82 | BBH | medium | | BBH | 77.82 | 71.36 | |
| MMLU | knowledge | 74.25 | MMLU | medium | | MMLU | 74.25 | 67.58 | |
| HumanEval | coding | 71.95 | HUMANEVAL | medium | | HUMANEVAL | 71.95 | 51.22 | |
| MATH | math | 48.0 | MATH | medium | | MATH | 48 | 32.66 | |
| GPQA | reasoning | 37.88 | GPQA | medium | | GPQA | 37.88 | 31.31 | |
none scraped.