VisReason (Vision-Centric) - Cue Insight: leaderboard
VisReason Cue Insight is a conceptual-reasoning category of VisReason (2026): the model must combine textual and visual clues in an image to derive the answer. The score is accuracy in percent, higher is better.
Metric: Accuracy (%) on the Cue Insight category (conceptual reasoning: combine textual and visual clues in an image to derive the answer) 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 | 68.5 | #119 |
| 2 | GPT-5 Mini | High | 60.4 | #364 |
| 3 | GPT-5 | Low | 53.2 | #178 |
| 4 | O4 Mini | 46 | #368 | |
| 5 | GPT-5.2 | Thinking | 43.2 | #185 |
| 6 | Qwen 3 VL 8B Instruct | 34.3 | #1029 | |
| 7 | Qwen 3 VL 235B A22B (Thinking) | 30.6 | #459 | |
| 8 | GPT-5 Nano | 29.7 | #906 | |
| 9 | Qwen 3 VL 30B A3B (Thinking) | 28.4 | #719 | |
| 10 | GPT-4o | 27.1 | #751 | |
| 11 | Qwen 3 VL 32B (Thinking) | 27 | #573 | |
| 12 | Qwen 3 VL 8B (Thinking) | 25.2 | #910 | |
| 13 | Qwen 2.5 VL 32B Instruct | 21.6 | #1062 | |
| 14 | Gemini 2.5 Flash | 19.8 | #463 | |
| 15 | Keye-VL-1.5-8B | Thinking | 16.6 | #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-cue-insight · How It Works · Data refreshed daily, snapshot 2026-11-21.