InsightVQA - Insight Ranking Top-1: leaderboard
Metric: Top-1 accuracy (%): share of situational-judgment items whose top-ranked candidate insight sequence matches the ground truth, 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 | DeepSeek V3.2 | 65.77 |
| 2 | Qwen 2.5 VL 32B Instruct | 65.32 |
| 3 | Gemini 2.5 Flash | 63.51 |
| 4 | Claude 3.7 Sonnet | 63.49 |
| 5 | GPT-4o | 61.06 |
| 6 | Qwen 2.5 VL 72B Instruct | 56.83 |
| 7 | Qwen 2.5 VL 7B Instruct | 51.27 |
| 8 | InternVL3.5-8B | 43.44 |
Interactive version: theaggregate.ai/benchmark?slug=insightvqa-insight-ranking-top-1 · How It Works · Data refreshed daily, snapshot 2026-09-29.