deepseek-ai/DeepSeek-V2-Lite-Chat
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| MMLU | knowledge | 48.2 | **MMLU** | medium | | **MMLU** | English | 48.2 | 45.0 | 58.3 | |
| CMMLU | knowledge | 47.2 | **CMMLU** | medium | | **CMMLU** | Chinese | 47.2 | 42.5 | 64.3 | |
| C-Eval | knowledge | 45.0 | **C-Eval** | medium | | **C-Eval** | Chinese | 45.0 | 40.6 | 60.3 | |
| BBH | reasoning | 39.5 | **BBH** | medium | | **BBH** | English | 39.5 | 38.9 | 44.1 | |
| MBPP | coding | 39.0 | **MBPP** | medium | | **MBPP** | Code | 39.0 | 39.2 | 43.2 | |
| HumanEval | coding | 26.2 | **HumanEval** | medium | | **HumanEval** | Code | 26.2 | 26.8 | 29.9 | |
| GSM8K | math | 17.4 | **GSM8K** | medium | | **GSM8K** | Math | 17.4 | 18.8 | 41.1 | |
| MATH | math | 3.3 | **Math** | medium | | **Math** | Math | 3.3 | 4.3 | 17.1 | |
none scraped.