RS-Neg VQA - Attribute Negation: leaderboard
Metric: Accuracy (%; yes/no questions that negate a present or an absent scene element; the 2,379 items whose negation is attribute-level; zero-shot). Source: arxiv.org. Saturation forecast: Around December 2026. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 VL 7B Instruct | 69.48 |
| 2 | Qwen 3 VL 8B Instruct | 63.64 |
Interactive version: theaggregate.ai/benchmark?slug=rs-neg-vqa-attribute-negation · How It Works · Data refreshed daily, snapshot 2026-09-26.