Skip to content

OpenCompass 2.0 Large Language Model Leaderboard

A live leaderboard for large language model evaluation

Visit official site

What opencompass-2-0-large-language-model-leaderboard is

The platform evaluates large language models on closed datasets and publishes a real time ranking with overall and skill scores.

What you can do with it

  • Compare how different models perform on a given task
  • Pick a language model for a chatbot project
  • Use ranking data when choosing a model for a product

Getting started

  • Visit the official leaderboard site
  • Read the live updated rankings
  • Open a model score and follow the GitHub config link

Pros & cons

✓ What we like

  • Rankings update to reflect newer model results
  • Scores link to GitHub config files for technical detail

! What to watch out for

  • Evaluation relies on closed source datasets
  • Config details are viewed through a GitHub link

FAQ

Which skills are scored?

Language, knowledge, reasoning, math and coding.

Can I see the configs?

Yes, scores link to GitHub configuration files.

Last reviewed: 2026-11-15

More AI coding tools tools

View all →

How we review