VisReason (Vision-Centric) - Pattern Counting: leaderboard
VisReason Pattern Counting is a perceptual-reasoning category of VisReason (2026): the model must identify all target patterns in a complex scene and count their occurrences. The score is accuracy in percent, higher is better.
Metric: Accuracy (%) on the Pattern Counting category (perceptual reasoning: identify all target patterns in a complex scene and count their occurrences) 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 | Gemini 3 Pro (Preview) | Low | 50 | #119 |
| 2 | GPT-5 Mini | High | 37 | #364 |
| 3 | GPT-5.2 | Thinking | 26.1 | #185 |
| 4 | O4 Mini | 21.7 | #368 | |
| 5 | GPT-5 | Low | 21.7 | #178 |
| 6 | Qwen 3 VL 235B A22B (Thinking) | 19.6 | #459 | |
| 7 | GPT-5 Nano | 17.4 | #906 | |
| 8 | Qwen 3 VL 32B (Thinking) | 17.4 | #573 | |
| 9 | Qwen 3 VL 30B A3B (Thinking) | 15.2 | #719 | |
| 10 | Keye-VL-1.5-8B | Thinking | 10.9 | #1720 |
| 11 | MiMo-VL-7B-RL | 10.6 | #1155 | |
| 12 | GPT-4o | 8.7 | #751 | |
| 13 | Gemini 2.5 Flash | 8.7 | #463 | |
| 14 | Qwen 3 VL 8B Instruct | 8.6 | #1029 | |
| 15 | InternVL3-14B | 6.5 | #1214 |
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-pattern-counting · How It Works · Data refreshed daily, snapshot 2026-11-21.