# New benchmark confirms AI models still perform poorly at visual perception

> Source: <https://the-decoder.com/new-benchmark-confirms-ai-models-still-perform-poorly-at-visual-perception/>
> Published: 2026-08-15 05:30:18+00:00

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](https://the-decoder.com/new-benchmark-confirms-ai-models-still-perform-poorly-at-visual-perception/) appeared first on [The Decoder](https://the-decoder.com).