VisReason (Vision-Centric) - Multiple-Choice: leaderboard
VisReason Multiple-Choice scores multimodal LLMs on the 615 multiple-choice questions of VisReason (2026), a benchmark of vision-centric reasoning in everyday images, pooled over its 10 reasoning categories. The score is accuracy in percent, higher is better.
Metric: Accuracy (%) on the 615 multiple-choice questions (option index extracted by regular expression) of VisReason, pooled over the 10 reasoning 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 January 2028. 18 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | Low | 47.8 | #119 |
| 2 | Qwen 3 VL 235B A22B (Thinking) | 40.8 | #459 | |
| 3 | GPT-5.2 | Thinking | 39.4 | #185 |
| 4 | GPT-5 Mini | Medium | 36.4 | #364 |
| 5 | Qwen 3 VL 32B (Thinking) | 34.5 | #573 | |
| 6 | GPT-5 | Low | 34 | #178 |
| 7 | Gemini 2.5 Flash | 31.5 | #463 | |
| 8 | O4 Mini | 30.9 | #368 | |
| 9 | Qwen 3 VL 30B A3B (Thinking) | 30.9 | #719 | |
| 10 | Qwen 3 VL 8B (Thinking) | 30.6 | #910 | |
| 11 | Qwen 3 VL 8B Instruct | 27.8 | #1029 | |
| 12 | GPT-4o | 25.2 | #751 | |
| 13 | GPT-5 Nano | 23.6 | #906 | |
| 14 | Qwen 2.5 VL 32B Instruct | 22.9 | #1062 | |
| 15 | InternVL3-8B | 22.1 | #1782 |
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-multiple-choice · How It Works · Data refreshed daily, snapshot 2026-11-21.