Measuring how AI agents handle everyday wet-lab science
中文摘要
OpenAI推出BioBasicsBench,通过100项任务评估AI智能体解读原始实验数据及处理日常湿实验室科学的能力。
English Summary
OpenAI introduced BioBasicsBench, a 100-task benchmark measuring how AI agents interpret raw experimental data and handle everyday wet-lab science.
原文节选
OpenAI introduces BioBasicsBench, a 100-task benchmark measuring how well AI agents interpret raw experimental data and handle everyday wet-lab science.