Ambiguous Speech Emotion - CREMA-D: leaderboard
Metric: Jensen-Shannon divergence (0-1; between the emotion distribution the model predicts for an utterance and the distribution of the human annotators' labels, mean over utterances; lower is better; CREMA-D, crowd-rated acted clips of six basic emotions). Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o Audio | 0.29 |
| 2 | Gemini 2.5 Pro | 0.3 |
| 3 | Qwen2-Audio-7B-Instruct | 0.32 |
| 4 | Gemini 2.0 Flash | 0.34 |
| 5 | Qwen2.5-Omni-7B | 0.42 |
Interactive version: theaggregate.ai/benchmark?slug=ambiguous-speech-emotion-crema-d · How It Works · Data refreshed daily, snapshot 2026-09-26.