1.confident-ai / deepevalThe LLM Evaluation Frameworkevaluation-metricsevaluation-frameworkllm-evaluationllm-evaluation-frameworkllm-evaluation-metricspythonPythonAPACHE-2.019K total2.2K forks+4,160 starsfrom 15,071 · score 8.33
2.EleutherAI / lm-evaluation-harnessA framework for few-shot evaluation of language models.evaluation-frameworklanguage-modeltransformerPythonMIT14K total3.8K forks+1,983 starsfrom 12,379 · score 7.59
3.future-agi / future-agiOpen-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.ai-gatewayobservabilitysimulationai-agentsai-evalsevaluation-framework+14 morePythonAPACHE-2.02.2K total705 forks+1,412 starsfrom 825 · score 7.25