MAXNORM8650/MedAgentSim

Agent benchmark for medical diagnosis

A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.

[ICML 2025] MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding

An evaluation harness for medical/health AI agents — reproduce and cover multiple benchmarks under one scoring discipline

Meditron is a suite of open-source medical Large Language Models (LLMs).

A framework for comprehensive diagnosis and optimization of agents using simulated, realistic synthetic interactions

τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。