OpenAI revealed for the first time that GPT-5 has demonstrated the ability to assist in scientific research in a real laboratory environment. OpenAI collaborated with biosafety startup Red Queen Bio to build a testing framework to evaluate the performance of AI models in laboratories involving operations involving liquids, chemicals, and biological samples. In the experiment, GPT-5 proposed improvements to the molecular cloning experimental process. After execution, human scientists fed back the results to GPT-5. GPT-5 was based on an iterative feedback optimization plan. Experimental results showed that GPT-5 increased the efficiency of a standard molecular cloning process by 79 times.

OpenAI revealed for the first time that GPT-5 has demonstrated the ability to assist in scientific research in a real laboratory environment. OpenAI collaborated with biosafety startup Red Queen Bio to build a testing framework to evaluate the performance of AI models in laboratories involving operations involving liquids, chemicals, and biological samples. In the experiment, GPT-5 proposed improvements to the molecular cloning experimental process. After execution, human scientists fed back the results to GPT-5. GPT-5 was based on an iterative feedback optimization plan. Experimental results showed that GPT-5 increased the efficiency of a standard molecular cloning process by 79 times.