# OpenAI introduces BioBasicsBench to test AI agents on wet-lab analysis

> Original title: A new way to measure how AI agents handle the routine analyses of wet-lab science—BioBasicsBench.

- Source: OpenAI
- Published: 2026-11-06T19:08:57.000Z
- Bad Influence: https://badinfluence.news/items/rqym00w89i78x2xzyweignjxw
- Original: https://x.com/OpenAI/status/2118782708767965238

## Summary

OpenAI introduces BioBasicsBench, a benchmark for measuring how AI agents handle routine wet-lab science analyses. Developed with biotech company Ligo, it draws on 100 tasks from real experiments to test whether agents can interpret raw lab data, identify errors, and recognize when evidence does not support a conclusion.

## Post

A new way to measure how AI agents handle the routine analyses of wet-lab science—BioBasicsBench.

Developed with Ligo, a biotech company focused on enzyme design, the benchmark draws on 100 tasks from real experiments to test whether agents can interpret raw lab data, identify errors, and recognize when the evidence doesn’t support a conclusion.

Accelerating biological research starts with getting the everyday work right. BioBasicsBench shows where models need to improve, and helps us track what those gains mean for scientific progress, biosafety, and biosecurity.

https://openai.com/index/measuring-how-ai-agents-handle-wet-lab-science/

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWdtpRua4AAuNL-.jpg&mode=thumb&exp=1794182400&sig=54cda6e9eceb35c0)