VisualNeedle - Without Tools: leaderboard
VisualNeedle (2026) tests active visual search on 300 questions over information-dense high-resolution scenes whose decisive evidence is a small region not readable at a glance. This board is accuracy in percent when the model answers from the full image without the crop tool, mean of three runs; higher is better.
Metric: Accuracy (%) on the 300 VisualNeedle questions when the model answers from the full image without the Crop tool, mean of three runs at the generation settings of Table 4; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 9 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Seed 1.8 | High | 17.89 | #252 |
| 2 | Gemini 3.1 Pro (Preview) | High | 16.34 | #99 |
| 3 | Gemini 3 Flash | High | 15.12 | #175 |
| 4 | Qwen 3.5 Plus | Thinking | 15 | #242 |
| 5 | GPT-5.4 | xHigh | 14.32 | #135 |
| 6 | Seed 2.0 Pro | High | 13.11 | #222 |
| 7 | Kimi K2.5 | Thinking | 10.78 | #266 |
| 8 | GPT-5.2 | xHigh | 10.56 | #185 |
| 9 | Qwen 3 VL 235B A22B (Thinking) | 8.34 | #459 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=visualneedle-without-tools · How It Works · Data refreshed daily, snapshot 2026-11-21.