lighteval
by huggingfaceIn its repository's words: “Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends”
Facts from GitHub
- Licence
- MIT (MIT License), permissive, our reading
- Activity
- Last push 18 Nov 2026: pushed to in the last 90 days
- Latest release
- not fetched yet
- Stars
- 2.6k
- Main language
- Python
- On GitHub since
- 26 Jan 2024
- Topics
- evaluation, evaluation-framework, evaluation-metrics, huggingface
Other tools in Evaluate
- promptfoo promptfoo, 27k stars
- deepeval confident-ai, 20k stars
- lm-evaluation-harness EleutherAI, 15k stars
- garak NVIDIA, 10k stars
- opencompass open-compass, 7.6k stars
- SWE-bench SWE-bench, 6.2k stars
Tool data from the GitHub API, fetched 19 Nov 2026, 15:35 UTC. Listing is not endorsement and nobody can pay to be listed. Something wrong here? Write to hello@weightsnotwalls.com.