{"id":"lm-evaluation-harness","name":"Language Model Evaluation Harness","maker":"EleutherAI","url":"https://github.com/EleutherAI/lm-evaluation-harness","repo":"EleutherAI/lm-evaluation-harness","package":"pypi:lm-eval","summary":"A command-line framework for running language models against hundreds of standard evaluation tasks.","details":"Supports many model backends, including Hugging Face models and OpenAI-compatible APIs, and a large collection of tasks with a shared interface. The code is MIT licensed.","open_source":true,"hosted":false,"speaks":["openai-api"],"verified":"2026-11-15","category":"benchmarks","category_name":"Agent benchmarks","page":"https://modelmoot.com/tools/lm-evaluation-harness","reviewed":"2026-11-15","checked":{"at":"2026-11-15T14:03:44.997Z","address_answers":true,"repository":{"at":"2026-11-16T02:35:24.378Z","archived":false,"licence":"MIT","language":"Python","last_change":"2026-11-04T14:34:40.000Z","latest_release":{"tag":"v0.4.13","published":"2026-08-31T20:42:30.000Z"}}},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}