{"avoid_when":"只评业务 RAG 流水线（看 ragas）","content_hash":"4b8411055c1856423950064922e89196f4d23d032a625b42c04e4880fe6208e9","domain":"ai-agents","evidence_urls":["https://github.com/EleutherAI/lm-evaluation-harness"],"id":"lm-evaluation-harness","language":"Python","license":"","name":"LM Evaluation Harness","niche":"foundation model eval","repo":"https://github.com/EleutherAI/lm-evaluation-harness","source_updated_at":null,"status":"active","summary":"开源模型评测基准框架。","tags":["eval"],"use_when":"要标准化评测基座模型能力","verification_status":"unverified","verified_at":null}