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

#ModelScore
1GPT-4o Audio0.29
2Gemini 2.5 Pro0.3
3Qwen2-Audio-7B-Instruct0.32
4Gemini 2.0 Flash0.34
5Qwen2.5-Omni-7B0.42

Interactive version: theaggregate.ai/benchmark?slug=ambiguous-speech-emotion-crema-d · How It Works · Data refreshed daily, snapshot 2026-09-26.