ODU-Bench (Audio-Visual): leaderboard
ODU-Bench (Chen et al., 2026) tests Omni Demand Understanding: whether a model infers whether the final spoken user turn in a multimodal interaction carries a demand for the assistant and recovers it from visual, acoustic and dialogue context. Weighted score in percent over 1,347 audio-visual scenes (1,070 synthetic and 277 human-recorded; user turns as video with audio, earlier assistant replies as text), combining demand detection, key-point coverage, temporal localization, transcription and user profile; higher is better.
Metric: Weighted demand-understanding score (%; 0.15 demand detection + 0.60 key-point coverage + 0.10 temporal localization + 0.10 transcription + 0.05 user profile, on 1,347 audio-visual scenes (1,061 with a demand, 286 without; 1,070 synthetic and 277 human-recorded), user turns as video with audio, earlier assistant replies as text; key points judged by Qwen3.6-Flash with thinking). Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 72.6 | #91 |
| 2 | Gemini 3.7 Flash | 69.6 | #32 |
| 3 | Qwen 3.5 Omni Plus | 69.6 | #237 |
| 4 | Seed 2.0 Lite | 67.9 | #286 |
| 5 | Gemini 3.5 Flash Lite | 57.4 | #300 |
| 6 | Qwen3 Omni 30B A3B Instruct | 55.2 | #902 |
| 7 | Qwen2.5-Omni-7B | 45.2 | #1797 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=odu-bench-audio-visual · How It Works · Data refreshed daily, snapshot 2026-11-12.