---
title: "New benchmark shows top AI models still struggle to 'see'"
url: https://www.parallelquant.com/posts/new-benchmark-shows-top-ai-models-still-struggle-to-see-2724a8
source_name: "The Decoder"
source_url: https://the-decoder.com/new-benchmark-confirms-ai-models-still-perform-poorly-at-visual-perception/
published: 2026-08-15T05:30:18.000Z
topics: ["research"]
publisher: "Parallel Quant"
---

# New benchmark shows top AI models still struggle to 'see'

*2026-08-15 · Source: [The Decoder](https://the-decoder.com/new-benchmark-confirms-ai-models-still-perform-poorly-at-visual-perception/)*

Moonshot AI's PerceptionBench tests multimodal AI models on visual perception, separate from logical reasoning. No frontier model scores above 60% accuracy, with GPT-5.6 Sol leading by a narrow margin, and many apparent reasoning errors actually trace back to misreading the image.

**Why it matters:** This suggests a meaningful share of AI 'reasoning' failures on visual tasks are really perception failures, pointing labs toward a different bottleneck than commonly assumed. It's a useful check against continued frontier-model benchmark claims covered elsewhere.

**Topics:** research

---
Read the original: https://the-decoder.com/new-benchmark-confirms-ai-models-still-perform-poorly-at-visual-perception/
Canonical: https://www.parallelquant.com/posts/new-benchmark-shows-top-ai-models-still-struggle-to-see-2724a8
Published by Parallel Quant — https://www.parallelquant.com