DeepSeek Vision Impresses in Tests but Still Struggles with Spatial Reasoning
teortaxesTex · x · 2026-08-09
User tests reveal that DeepSeek's vision capabilities are highly competitive, even surpassing Claude and GPT-4o in identifying fine details in complex images. However, when it comes to 3D spatial reasoning—such as determining the correct orientation for a radial cross-hole—DeepSeek makes mistakes similar to other mainstream LLMs, highlighting a persistent weakness in spatial awareness.
More from Models
- willcb: Opus 5.5 doesn't smell bigger, it smells like they fixed the data — willcb · 2026-10-16
- Unverified claim: Apple and Meta's 816B-parameter Muse Spark Open runs on two Mac Studios — TansuYegen · 2026-10-16
- Gemini 4 model card: model eliminated months of trial-and-error on bioweapons research — Puzzleheaded-King584 · 2026-10-16
- Every AI picks 7: Anthropic engineer's rule for escaping model taste convergence — rubenhassid · 2026-10-16
- Brain teaser: strip all attention, MLP and embedding matrices from a Llama 3 — how many trainable params remain? — Sauers_ · 2026-10-16
- Lean v4.35.0 ships verified kernels — one written and proven consistent by Claude — geoffreyirving · 2026-10-16