New benchmark confirms AI models still perform poorly at visual perception

The DecoderAugust 15, 2026en

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 .

This is a short summary published by AI Global Wire. The full article is owned and hosted by The Decoder — open it there to read it in full.

• OpenAI
• Verktyg
• Bild