精选理由
Moonshot AI 出了个新测试 PerceptionBench，专门查 AI 的“眼神”。结果最强模型 GPT-5.6 Sol 准确率也不到 60%，而且很多错是从看图时就错了。
Moonshot AI 发布 PerceptionBench 基准，专门测试多模态 AI 模型的视觉感知能力，并将该能力与逻辑推理分离评估。目前没有任何前沿模型在该基准上达到 60% 的准确率，GPT-5.6 Sol 以微弱优势领先。测试还发现，许多原本被认为是推理过程的错误，实际上在图像读取阶段就已经发生。
原文 · Decoder
New benchmark confirms AI models still perform poorly at visual perception
Moonshot AI's PerceptionBench tests how well multimodal AI models can actually "see," separate from logical reasoning. No frontier model reaches 60 percent accuracy, and GPT-5.6 Sol leads by a narrow margin. Many supposed reasoning errors actually happen as early as the image-reading stage. The article New benchmark confirms AI models still perform poorly at visual perception appeared first on The Decoder .