HumDial-EIBench - Emotional Trajectory (English): leaderboard
Metric: Accuracy (%) on Task 1 emotional trajectory detection (pick the user's emotion shift across 3-5 turns) four-option multiple-choice questions (English, 150 dialogues) 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 January 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Flash | 91.33 |
Interactive version: theaggregate.ai/benchmark?slug=humdial-eibench-emotional-trajectory-english · How It Works · Data refreshed daily, snapshot 2026-10-07.