HealthBench is a new evaluation benchmark for AI in healthcare which evaluates models in realistic scenarios. Built with input from 250+ physicians, it aims to provide a shared standard for model performance and safety in health.

Recommended

Introducing new capabilities to GPT-RosalindOpenai Introducing ChatGPT Futures: Class of 2026Openai Introducing LifeSciBenchOpenai Introducing ChatGPT EnterpriseOpenai Introducing workspace agents in ChatGPTOpenai Operation "Doppelganger": Russian influence activity targeting UkraineOpenai Introducing CORPS: The 5 Pillars for a Robust Cloud Architecture FrameworkIntroducing CORPS: The 5 Pillars for a Robust Cloud Architecture FrameworkThenewstack Introducing New Slimmer Docker ImagesIntroducing New Slimmer Docker ImagesPulumi Introducing: H100s on ModalIntroducing: H100s on ModalModal pg_duckdb: Splicing Duck and Elephant DNApg_duckdb: Splicing Duck and Elephant DNAMotherduck The Serverless Backend for Analytics: Introducing MotherDuck’s Native Integration on VercelThe Serverless Backend for Analytics: Introducing MotherDuck’s Native Integration on VercelMotherduck Introducing DocChat: GPT-4 Level Conversational QA Trained In a Few Hours - CerebrasIntroducing DocChat: GPT-4 Level Conversational QA Trained In a Few Hours - CerebrasCerebras Introducing the Docker Desktop WSL 2 BackendIntroducing the Docker Desktop WSL 2 BackendDocker Bringing More Power To Edge Rules! Introducing Variable ExpansionBringing More Power To Edge Rules! Introducing Variable ExpansionBunny Introducing AI AssistantIntroducing AI AssistantMintlify Introducing Dependency Divergence GitHub ActionIntroducing Dependency Divergence GitHub ActionSocket Enhancing Pulumi Copilot: Introducing System Prompts for Your OrganizationEnhancing Pulumi Copilot: Introducing System Prompts for Your OrganizationPulumi Introducing the Go Playground - The Go Programming LanguageIntroducing the Go Playground - The Go Programming LanguageGo Role-Based Access Control for humans and agentsRole-Based Access Control for humans and agentsModal Introducing Embedded DivesIntroducing Embedded DivesMotherduck