Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
BetaRare

xinxuxin/keystone-bench

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.

Owner
xinxuxin (personal account)
Stars
Stars: 1,107
Forks
Forks: 3
Language
Python
License
None
Created
2026
Topics
ai-safetybenchmarkclinical-decision-supportdatasetevaluationhealthhealthbenchlarge-language-modelsllm-evaluationmedical-ai
Tier
Beta (700 to 1,999 ★) What this tier means
View on GitHub

Nearby in Python

All Python repos