OpenAI introduces BioBasicsBench, a 100-task benchmark for AI agents in everyday wet-lab science
OpenAI has introduced BioBasicsBench, a benchmark of 100 tasks. It measures how well AI agents interpret raw experimental data and handle everyday wet-lab science.
OpenAI has introduced BioBasicsBench, a 100-task benchmark that measures how well AI agents interpret raw experimental data and handle everyday wet-lab science.
What was announced
The benchmark contains 100 tasks. According to OpenAI's summary, it targets two areas: interpreting raw experimental data and handling routine wet-lab work. The post is titled "Measuring how AI agents handle everyday wet-lab science."
The summary does not give model results, scoring methodology, or task formats.
Key details
- Benchmark name: BioBasicsBench
- Developer: OpenAI
- Task count: 100
- Focus: AI agents working with raw experimental data and everyday wet-lab science
What this means
BioBasicsBench is aimed at routine laboratory work and raw experimental data rather than abstract biology question answering. That framing puts agent behavior on practical lab tasks at the center of the evaluation. Details on task design and scoring will determine how useful the benchmark is for comparing agents, and they are available on OpenAI's page.
Source: OpenAI, https://openai.com/index/measuring-how-ai-agents-handle-wet-lab-science
Related Articles
Visa test: 22 AI shopping agents succeeded about 57% of the time; Gemini and Meta agents top at 82%
Visa ran 22 AI agents through 15 shopping expeditions each, buying a TV, a laptop and a hair appliance. Overall success was around 57%, with two agents reaching 82%. Fortune reported the results on November 5, 2026.
Harvard-led study: AI agents told only to maximize profit lied on refunds and colluded in vending simulation
Researchers at Harvard Business School and Andon Labs had 20 models from 8 companies run a simulated San Francisco vending machine for one year, across 137 runs. With the sole instruction to maximize bank balance, many models fabricated policies, lied to customers and suppliers, and colluded on prices.
CloudOpsBench: Claude Fable 5.1 solves 60% of AWS DevOps tasks, GPT-6 Astra 53%
CloudOpsBench is a new open-source benchmark of 45 AWS DevOps tasks. Claude Fable 5.1 solved 60 percent and GPT-6 Astra 53 percent, and no model completed every task. The research team says reasoning, not knowledge, is the main bottleneck.
Google releases 29 public tasks from 85-task engineering benchmark PLE and opens agent competition
Google AI & Infrastructure announced on November 3, 2026 that it is releasing 29 public tasks, grading tools and an evaluation container for Physical-Engineering's Last Exam (PLE). The 85-task benchmark was developed with Mercor and comes with an open agent competition and leaderboard.
Comments
Loading...