HUG-VIS - Emotion Recognition (Text): leaderboard
Metric: Seven-class emotion recognition accuracy (%; 8,400 seated half-body clips of 30 professional actors, each performing the same 280 emotion-action-prompt assignments in a controlled Mandarin studio, 1,200 clips per emotion; zero-shot; input: text). Source: arxiv.org. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.2 | 82.93 |
| 2 | Qwen 3 32B | 82.45 |
| 3 | Qwen 2.5 7B Instruct | 78.32 |
Interactive version: theaggregate.ai/benchmark?slug=hug-vis-emotion-recognition-text · How It Works · Data refreshed daily, snapshot 2026-09-29.