HumDial-EIBench - Causal Reasoning (Chinese): leaderboard
Implicit causal reasoning on the Chinese dialogues of HumDial-EIBench (2026), real human-recorded multi-turn dialogues from the ICASSP 2026 HumDial Challenge: an audio language model infers the unstated cause of the current emotion of the user, among four options whose distractors are synthesized in the voice of the speaker. Accuracy in percent; higher is better.
Metric: Accuracy (%) on Task 2 implicit causal reasoning (infer the unstated cause of the user's current emotion) four-option multiple-choice questions (Chinese, 134 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 February 2027. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 76.12 | #463 |
| 2 | GPT-4o Audio | 72.39 | #1129 |
| 3 | Kimi-Audio | 71.64 | #1735 |
| 4 | Step-Audio-2-mini | 67.16 | |
| 5 | GLM-4-Voice | 58.96 | |
| 6 | Doubao-realtime | 52.24 | |
| 7 | Freeze-Omni | 23.88 |
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-causal-reasoning-chinese · How It Works · Data refreshed daily, snapshot 2026-11-21.