MedAgents-Bench

gersteinlab/MedicalAgentsBench

Active

[Patterns] MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning

MedAgents-Bench is a benchmarks AI agent developed by gersteinlab with 87 GitHub stars, written in Jupyter Notebook, currently Active.

[Patterns] MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning

GitHub metrics refresh daily — last fetched today.

Companion paper

Xiangru Tang, Daniel Shao, Jiwoong Sohn, Jiapeng Chen, Jiayi Zhang, Jinyu Xiang … Arman Cohan, Mark Gerstein

No verified run reviews yet. Be the first to run MedAgents-Bench and report.

Register or sign in with GitHub to review MedAgents-Bench. Your GitHub account creates your reviewer profile on first sign-in.

No reviews yet. Reviews from researchers who actually ran MedAgents-Bench are what this platform is for.

zhao-zy15/RareArena

Stable

A Comprehensive Rare Disease Diagnostic Dataset with nearly 50,000 patients covering more than 4000 diseases

Lancet-Digital-Health

5310

Python

Benchmarks

pushed 7mo ago

no reviews

darlednik/GENEB

TodayActive

GENEB: ICML 2026 benchmark for genomic foundation models across 100 tasks and 13 functional categories.

46PythonBenchmarkspushed 1mo agono reviews

sierra-research/tau2-bench

TodayActive

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

2.2k546PythonBenchmarkspushed 4d agono reviews