HumDial-EIBench - Consistent Emotion (English): leaderboard

Control set of the acoustic-semantic conflict task of HumDial-EIBench (2026): 50 single-turn English human recordings whose vocal emotion and text sentiment agree, where the model identifies the emotional state of the speaker among four options. Accuracy in percent; higher is better.

Metric: Accuracy (%) of identifying the speaker's true emotional state on 50 single-turn English consistent samples, where vocal emotion and text sentiment agree (four options, human-recorded); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen2.5-Omni86#1588
2Step-Audio-2-mini82
3Kimi-Audio80#1735
4Gemini 2.5 Flash70#463
5GPT-4o Audio68#1129
6Doubao-realtime64
7Freeze-Omni60
8GLM-4-Voice54

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=humdial-eibench-consistent-emotion-english · How It Works · Data refreshed daily, snapshot 2026-11-21.