VisReason (Vision-Centric) - Sudoku Solving: leaderboard
VisReason Sudoku Solving is a structural-reasoning category of VisReason (2026): the model must solve visually presented Sudoku variants. The score is accuracy in percent, higher is better.
Metric: Accuracy (%) on the Sudoku Solving category (structural reasoning: solve visually presented Sudoku variants) 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 February 2027. 20 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-5.2 | Thinking | 38.2 | #185 |
| 2 | Gemini 3 Pro (Preview) | Low | 30 | #119 |
| 3 | GPT-5 | Low | 22.5 | #178 |
| 4 | O4 Mini | 15.5 | #368 | |
| 5 | GPT-5 Mini | Low | 15 | #364 |
| 6 | Qwen 3 VL 8B Instruct | 9.2 | #1029 | |
| 7 | GPT-5 Nano | 9 | #906 | |
| 8 | InternVL3-8B | 8.5 | #1782 | |
| 9 | Qwen 3 VL 30B A3B (Thinking) | 8.5 | #719 | |
| 10 | Qwen 2.5 VL 32B Instruct | 8 | #1062 | |
| 11 | GPT-4o | 7.5 | #751 | |
| 12 | Qwen 3 VL 32B (Thinking) | 7 | #573 | |
| 13 | Gemini 2.5 Flash | 6 | #463 | |
| 14 | Qwen 3 VL 8B (Thinking) | 6 | #910 | |
| 15 | Keye-VL-1.5-8B | Thinking | 4.5 | #1720 |
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-sudoku-solving · How It Works · Data refreshed daily, snapshot 2026-11-21.