EmoTrans: leaderboard
Metric: Average accuracy (%) over Emotion Change Detection, Emotion State Identification and Next Emotion Prediction on EmoTrans, built from 1,000 manually annotated real-world video clips (OpenHumanVid and CH-SIMS v2) over 12 scenarios with one or more target persons; zero-shot, video with its text (and audio where the model accepts it); higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 49.3 |
| 2 | Seed 2.0 Lite | 47.4 |
| 3 | Qwen 3.5 122B A10B | 47 |
| 4 | Gemini 3 Pro | 46.7 |
| 5 | Qwen 3.5 27B | 46.4 |
| 6 | GLM-4.6V | 46.1 |
| 7 | GLM-4.5V | 45.2 |
| 8 | Qwen 3 VL 32B Instruct | 43.5 |
| 9 | Qwen 2.5 VL 72B Instruct | 43.5 |
| 10 | Gemini 2.5 Flash (Non-reasoning) | 40.9 |
Interactive version: theaggregate.ai/benchmark?slug=emotrans · How It Works · Data refreshed daily, snapshot 2026-10-07.