OpenAI 推出湿实验基准 BioBasicsBench，GPT-6 Astra 得分 66.7%
OpenAI 拿凝胶照片和显微镜视频考 AI，GPT-6 Astra 拿了 66.7 分，比上一代高出 20 多分，还省了一半 token。
OpenAI 与酶设计公司 Ligo 合作构建了 BioBasicsBench，用凝胶照片、显微镜视频、测序读数等真实实验数据测试 AI 的解读能力。基准包含 100 个任务，采用部分给分规则，能识别错误或判断证据不足也可得分。GPT-6 Astra 在该基准上获得 66.7% 的可用分数，GPT-5.6 Sol 为 43.8%。在 xhigh 设置下，Astra 每个任务使用 4704 个输出 token，约为旧模型的一半，说明成绩提升并非依赖更长推理。
OpenAI built BioBasicsBench, a test that gives AI agents the messy raw data of real lab work, like gel photos and microscope videos, and grades whether they read it correctly.
GPT-6 Astra earned 66.7% of available credit on a new wet-lab benchmark, versus 43.8% for GPT-5.6 Sol.
BioBasicsBench, built with enzyme-design company Ligo, draws 100 tasks from scientists’ raw gels, colony plates, microscopy, sequencing reads and bench videos.
Its rubrics give partial credit, including for spotting errors or saying evidence can’t support conclusions.
At the xhigh setting, Astra used 4,704 output tokens per task, about half the older model’s, so longer reasoning didn’t drive the gain.
