Pinned Loading

1. open-compass/opencompass open-compass/opencompass Public

   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.

   Python 6.5k 716

2. open-compass/MathBench open-compass/MathBench Public

   [ACL 2024 Findings] MathBench: A Comprehensive Multi-Level Difficulty Mathematics Evaluation Dataset

   108 1

3. open-compass/GPassK open-compass/GPassK Public

   [ACL 2025] Are Your LLMs Capable of Stable Reasoning?

   Python 32 2

4. open-compass/CompassVerifier open-compass/CompassVerifier Public

   [EMNLP 2025] CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

   Jupyter Notebook 61 2