Ambiguous Speech Emotion - IEMOCAP: 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; IEMOCAP, 4,373 acted dyadic utterances with neutral, happy, angry and sad labels). Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro0.34
2GPT-4o Audio0.34
3Gemini 2.0 Flash0.35
4Qwen2-Audio-7B-Instruct0.36
5Qwen2.5-Omni-7B0.39

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