VisReason (Vision-Centric) - Bounding-Box: leaderboard
VisReason Bounding-Box scores multimodal LLMs on the 140 bounding-box questions of VisReason (2026), a benchmark of vision-centric reasoning in everyday images, drawn from its Localized Reasoning and Spot the Difference categories. The score is accuracy in percent, higher is better.
Metric: Accuracy (%) on the 140 bounding-box questions (boxes Hungarian-matched to the ground truth at IoU above 0.5, partial credit per question) of VisReason, drawn from the Localized Reasoning and Spot the Difference categories, 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 March 2027. 18 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | Low | 24.5 | #123 |
| 2 | GPT-5.2 | Thinking | 14.7 | #190 |
| 3 | GPT-5 | Low | 8.9 | #185 |
| 4 | GPT-5 Mini | Low | 7.4 | #373 |
| 5 | Qwen 3 VL 8B (Thinking) | 5.2 | #924 | |
| 6 | Qwen 3 VL 235B A22B (Thinking) | 4.4 | #462 | |
| 7 | GPT-4o | 3.6 | #754 | |
| 8 | O4 Mini | 3.3 | #372 | |
| 9 | Qwen 2.5 VL 32B Instruct | 2.4 | #1065 | |
| 10 | GPT-5 Nano | 2 | #912 | |
| 11 | Qwen 3 VL 2B (Thinking) | 1.4 | #2552 | |
| 12 | Qwen 3 VL 32B (Thinking) | 1.3 | #577 | |
| 13 | Qwen 3 VL 8B Instruct | 1.2 | #1043 | |
| 14 | InternVL3-14B | 0.7 | #1227 | |
| 15 | Gemini 2.5 Flash | 0.3 | #466 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=visreason-vision-centric-bounding-box · How It Works · Data refreshed daily, snapshot 2026-11-22.