Search Write for us Sign in
OpenAI Daily News

Independent news about OpenAI and ChatGPT. Not an OpenAI publication.

Monday, November 9, 2026Sources checked

Models & Research

Measuring how AI agents handle everyday wet-lab science

Primary sourceOpenAI

OpenAI introduces BioBasicsBench, a 100-task benchmark measuring how well AI agents interpret raw experimental data and handle everyday wet-lab science.

This notice was published by OpenAI. What you see here is a brief excerpt. The full text is theirs.

Continue reading at OpenAI

Pass it on X Facebook WhatsApp

Latest in Models & Research

  1. GPT-Image-2.6: Faster image generation with Flare and Sunburst

Everything in Models & Research

API & Codex

Business