GPT-6 Astra Hits 66.7% on OpenAI's New Wet-Lab Benchmark
OpenAI's GPT-6 Astra scored 66.7% on BioBasicsBench, a 100-task wet-lab benchmark built with Ligo, beating GPT-5.6 Sol's 43.8% — but still failing key experimental judgment tests.
Topic
Topic
OpenAI's GPT-6 Astra scored 66.7% on BioBasicsBench, a 100-task wet-lab benchmark built with Ligo, beating GPT-5.6 Sol's 43.8% — but still failing key experimental judgment tests.