InsightVQA - Insight Ranking: leaderboard
InsightVQA (2026) is a hierarchical visual question answering benchmark on emotion-annotated images drawn from six public sources. This board is the Spearman rank correlation (times 100, from -100 to 100) between the model ranking of candidate insight sequences and the ground truth in a situational-judgment test; higher is better.
Metric: Spearman rank correlation (x100, -100 to 100) between the model ranking of candidate insight sequences and the ground-truth ranking in the situational-judgment test of 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: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.7 Sonnet | 81.77 | #458 |
| 2 | Gemini 2.5 Flash | 80.56 | #453 |
| 3 | DeepSeek V3.2 | 80.24 | #406 |
| 4 | GPT-4o | 77.51 | #741 |
| 5 | Qwen 2.5 VL 72B Instruct | 76.3 | #846 |
| 6 | Qwen 2.5 VL 32B Instruct | 69.24 | #1053 |
| 7 | Qwen 2.5 VL 7B Instruct | 34.95 | #1833 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=insightvqa-insight-ranking · How It Works · Data refreshed daily, snapshot 2026-11-13.