OpenAI and Ligo launch BioBasicsBench, a wet-lab benchmark with 100 routine tasks
What happened
On November 6, 2026, OpenAI News reported that OpenAI and biotech company Ligo released BioBasicsBench, a benchmark for measuring how well AI agents handle everyday wet-lab science tasks. It contains 100 routine wet-lab tasks, covering interpretation of raw experimental data, spotting errors, and judging whether the evidence an experiment produced is enough to support a conclusion. The report covers the launch, the task count and the scope of evaluation; it gives no specific agent scores.
Written by AI from the coverage · updated 51 minutes ago
Coverage
Follow the reports to see the story from different sides.
- OpenAI NewsMeasuring how AI agents handle everyday wet-lab science
OpenAI 与生物技术公司 Ligo 联合推出 BioBasicsBench，用 100 项常规湿实验室任务衡量 AI 智能体解读原始实验数据、识别错误并判断证据是否足以支撑结论的能力。
Heat over time
Not enough continuous observations to draw a trend yet.