VisReason (Vision-Centric) - 3D-Spatial Reasoning: leaderboard
VisReason 3D-Spatial Reasoning is a structural-reasoning category of VisReason (2026): the model must reason about implicit 3D geometric relationships to infer the correct answer. The score is accuracy in percent, higher is better.
Metric: Accuracy (%) on the 3D-Spatial Reasoning category (structural reasoning: reason about implicit 3D geometric relationships to infer the correct answer) of VisReason, answers scored by format (regular-expression match, GPT-5-mini judge for open-ended answers, IoU above 0.5 for boxes), zero-shot with chain-of-thought prompt templates, one per answer format; rows not shaded gray in the paper use explicit reasoning (GPT-5 and Gemini 3 Pro at low reasoning effort); higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 20 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | Low | 43.9 | #119 |
| 2 | Qwen 3 VL 235B A22B (Thinking) | 36.2 | #459 | |
| 3 | Qwen 3 VL 8B (Thinking) | 33.1 | #910 | |
| 4 | Gemini 2.5 Flash | 31.5 | #463 | |
| 5 | InternVL3-8B | 31.5 | #1782 | |
| 6 | Qwen 3 VL 30B A3B (Thinking) | 30.8 | #719 | |
| 7 | Qwen 3 VL 32B (Thinking) | 30.8 | #573 | |
| 8 | GPT-5.2 | Thinking | 30.8 | #185 |
| 9 | GPT-5 Mini | Low | 30.8 | #364 |
| 10 | O4 Mini | 27.7 | #368 | |
| 11 | Qwen 2.5 VL 32B Instruct | 27.7 | #1062 | |
| 12 | GPT-5 | Low | 26.2 | #178 |
| 13 | GPT-4o | 25.4 | #751 | |
| 14 | MiMo-VL-7B-RL | 25.4 | #1155 | |
| 15 | GPT-5 Nano | 23.9 | #906 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=visreason-vision-centric-3d-spatial-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.