onejune2018/Awesome-LLM-Eval

Evaluation & Testing

Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs. 一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表，主要面向基础大模型评测，旨在探求生成式AI的技术边界.

GitHub →Website →

4.3

GitHub Metrics

Stars

659

Forks

109

Open Issues

Watchers

Contributors

Weekly Commits

Language

—

License

MIT

Last Commit

Nov 24, 2025

Created

Apr 26, 2023

Latest Release

—

Release Date

—

Synced: Oct 18, 2026

Quality Scores

Documentation Qualityw: 20%

5.7

Has docs site (https://arxiv.org/abs/2508.18646). Description: 198 chars. Stars signal: 659. Contributors: 5. Score: 5.7/10

Community Healthw: 20%

3.4

Stars: 659. Contributors: 5. Watchers: 7. Forks: 107. Issue ratio: 10.0%. Score: 3.4/10

Maintenance Velocityw: 15%

1.5

Last commit: 328d ago. Weekly commits: 0. No releases published. Maturity bonus: 3.5y old. Score: 1.5/10

API Design & DXw: 20%

5.9

Stars/issues ratio: 10. Has documentation site. Permissive license: MIT. Popularity signal: 659 stars. Score: 5.9/10

Production Readinessw: 15%

3.5

Battle-tested: 659 stars. Peer review: 5 contributors. No versioned releases. Licensed: MIT. Age: 3.5 years. Maintenance: last commit 328d ago. Score: 3.5/10

Ecosystem Integrationw: 10%

5.9

Fork interest: 107. Integration-friendly: MIT. Adoption: 659 stars. Has web presence. Score: 5.9/10