MSU-Bench - Emotion Recognition: leaderboard

Metric: Accuracy (%) on the emotion recognition task (Tier 1), four-option multiple choice on MSU-Bench (2,300 human-verified questions over Chinese and English multi-speaker conversations from telephone, meeting, podcast and movie audio), zero-shot with one instruction template requiring a single option letter, exact-match accuracy (x100); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 9 models tracked.

Top models

#ModelScore
1Gemini 3 Flash58
2Gemini 2.5 Flash54
3Gemini 2.5 Pro52

Interactive version: theaggregate.ai/benchmark?slug=msu-bench-emotion-recognition · How It Works · Data refreshed daily, snapshot 2026-09-29.