EmoTrans - Emotion State Identification: leaderboard
Metric: Accuracy (%) on Emotion State Identification (724 questions: each person's emotion before and after the change), 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 | Seed 2.0 Lite | 41.2 |
| 2 | GPT-5.4 | 40.5 |
| 3 | Qwen 3.5 122B A10B | 38.8 |
| 4 | Qwen 3.5 27B | 38.4 |
| 5 | GLM-4.5V | 38 |
| 6 | GLM-4.6V | 37.4 |
| 7 | Gemini 3 Pro | 36.5 |
| 8 | Qwen 2.5 VL 72B Instruct | 33.1 |
| 9 | Qwen 3 VL 32B Instruct | 31.2 |
| 10 | Gemini 2.5 Flash (Non-reasoning) | 26.8 |
Interactive version: theaggregate.ai/benchmark?slug=emotrans-emotion-state-identification · How It Works · Data refreshed daily, snapshot 2026-10-07.