LM Evaluation Harness
A framework for few-shot evaluation of language models.
LLM evals
Open LM Evaluation Harness in AirStackWhat LM Evaluation Harness’s own pages say
| What it says it does | A framework for few-shot evaluation of language models. github.com |
|---|---|
| Integrations | vLLM, SGLang, ONNX Runtime GenAI, Windows ML github.com |
| License | MIT license github.com |
| Models supported | TextSynth, ChatGLM, Gemma, Granite, Llama, Phi, Qwen github.com |
| Customers (their claim) | is used internally by dozens of organizations including NVIDIA, Cohere, BigScience, BigCode, Nous Research, and Mosaic ML. github.com |
Each value is a quote AirStack found on the product’s own pages, read 2026-11-04. A missing field means AirStack has not found it on its pages.