internlm/internlm2_5-1_8b
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| CMMLU | knowledge | 65.44 | CMMLU | medium | | CMMLU | 65.44 | 45.27 | 70.58 | |
| MMLU | knowledge | 53.52 | MMLU | medium | | MMLU | 53.52 | 45.99 | 57.45 | |
| BBH | reasoning | 41.16 | BBH | medium | | BBH | 41.16 | 36.03 | 35.75 | |
| HumanEval | coding | 35.98 | HUMANEVAL | medium | | HUMANEVAL | 35.98 | 30.49 | 34.15 | |
| MATH | math | 27.28 | MATH | medium | | MATH | 27.28 | 9.42 | 24.38 | |
| GPQA | reasoning | 24.24 | GPQA | medium | | GPQA | 24.24 | 24.24 | 31.82 | |
none scraped.