VisReason (Vision-Centric) - Fill-in-the-Blank: leaderboard
VisReason Fill-in-the-Blank scores multimodal LLMs on the 441 fill-in-the-blank 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 441 fill-in-the-blank questions (answer 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 February 2027. 18 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | Low | 47.4 | #119 |
| 2 | GPT-5.2 | Thinking | 41.8 | #185 |
| 3 | GPT-5 | Low | 35.8 | #178 |
| 4 | GPT-5 Mini | High | 32.4 | #364 |
| 5 | O4 Mini | 30.4 | #368 | |
| 6 | Qwen 3 VL 32B (Thinking) | 22.2 | #573 | |
| 7 | Qwen 3 VL 235B A22B (Thinking) | 21.1 | #459 | |
| 8 | Qwen 3 VL 8B Instruct | 20.8 | #1029 | |
| 9 | Qwen 3 VL 30B A3B (Thinking) | 20.5 | #719 | |
| 10 | GPT-5 Nano | 20.2 | #906 | |
| 11 | GPT-4o | 18.6 | #751 | |
| 12 | Qwen 3 VL 8B (Thinking) | 17.5 | #910 | |
| 13 | Gemini 2.5 Flash | 16.3 | #463 | |
| 14 | Qwen 2.5 VL 32B Instruct | 14.5 | #1062 | |
| 15 | InternVL3-8B | 10.2 | #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-fill-in-the-blank · How It Works · Data refreshed daily, snapshot 2026-11-21.