HumDial-EIBench - Emotional Trajectory: leaderboard
Emotional trajectory detection on HumDial-EIBench (2026): from real human-recorded multi-turn dialogues from the ICASSP 2026 HumDial Challenge, an audio language model picks how the emotion of the user shifts across three to five turns, among four options whose distractors are synthesized in the voice of the speaker. Accuracy in percent, mean of the Chinese and English sets; higher is better.
Metric: Accuracy (%), mean of the Chinese and English accuracies, on Task 1 emotional trajectory detection (pick the user's emotion shift across 3-5 turns) four-option multiple-choice questions built from real human-recorded dialogues from the ICASSP 2026 HumDial Challenge test set, audio language models answer from the audio, with three adversarial distractors synthesized in the speaker's voice; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 88 | #463 |
| 2 | GPT-4o Audio | 83 | #1129 |
| 3 | Qwen2.5-Omni | 73.67 | #1588 |
| 4 | Doubao-realtime | 68.33 | |
| 5 | Kimi-Audio | 66.34 | #1735 |
| 6 | Step-Audio-2-mini | 34.67 | |
| 7 | GLM-4-Voice | 30.34 | |
| 8 | Freeze-Omni | 11 |
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-emotional-trajectory · How It Works · Data refreshed daily, snapshot 2026-11-21.