Modular Design
Built with modularity in mind, allowing easy extension and customization of evaluation components.
FreeEval
A modular and extensible framework for conducting trustworthy and efficient automatic evaluations of large language models
Trustworthy Results
Incorporates meta-evaluation techniques like human evaluation and data contamination detection.
High Performance
Efficient infrastructure supporting multi-node, multi-GPU evaluations at scale.
Comprehensive Support
Works with both open-source and proprietary LLMs through a unified interface.