opencompass

GitHub

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

7,267 stars Python 1 file · ~15,039 tokens #benchmark#chatgpt#evaluation#large-language-model#llama2#llama3#llm#openai

opencompass MCP Server

MCP server for open-compass/opencompass

Ready-to-Use Client Configurations 
{
  "mcpServers": {
    "opencompass": {
      "command": "npx",
      "args": [
        "-y",
        "@open-compass/opencompass"
      ]
    }
  }
}