InsightVQA - Intent Reasoning: leaderboard
Metric: Accuracy (%) on single-choice questions asking for the most appropriate underlying response intent given the emotional state and its visual evidence, in InsightVQA-Bench, the held-out test split (a tenth of the data, about 30,000 questions) of emotion-annotated images from six public sources; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.7 Sonnet | 61.87 |
| 2 | Qwen 2.5 VL 72B Instruct | 57.24 |
| 3 | Gemini 2.5 Flash | 56.08 |
| 4 | GPT-4o | 50.34 |
| 5 | Qwen 2.5 VL 32B Instruct | 44.02 |
| 6 | DeepSeek V3.2 | 41.6 |
| 7 | InternVL3.5-8B | 31.18 |
| 8 | Qwen 2.5 VL 7B Instruct | 30.92 |
Interactive version: theaggregate.ai/benchmark?slug=insightvqa-intent-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-29.