E3mo-Bench (Expressed) - Open-Vocabulary Recognition (Emotion Wheel): leaderboard
Metric: Emotion-wheel set F-score (%; the OV-MER semantic emotion wheel alignment F-EW between the predicted and reference open-vocabulary emotion sets; 16 MLLMs on videos from eight emotion datasets, each assigned one affective perspective; subset: the emotion expressed by the people on screen). Source: arxiv.org. Saturation forecast: Around 2031. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 57.73 |
| 2 | InternVL3-8B | 55.57 |
| 3 | Qwen2.5-Omni-7B | 52.5 |
| 4 | Claude Sonnet 4.6 | 52.04 |
Interactive version: theaggregate.ai/benchmark?slug=e3mo-bench-expressed-open-vocabulary-recognition-emotion-wheel · How It Works · Data refreshed daily, snapshot 2026-09-29.