ODU-Bench (Audio-Visual) - Demand Detection: leaderboard
Demand detection in ODU-Bench (Chen et al., 2026): whether the final user turn carries a valid demand for the assistant, on 1,347 audio-visual scenes (1,070 synthetic and 277 human-recorded; user turns as video with audio, earlier assistant replies as text). Macro-F1 in percent over demand and no-demand scenes; higher is better.
Metric: Macro-F1 (%; whether the final user turn carries a valid demand for the assistant, over demand and no-demand scenes; 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). Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.7 Flash | 83.9 | #32 |
| 2 | Gemini 3.1 Pro (Preview) | 83 | #91 |
| 3 | Gemini 3.5 Flash Lite | 63.9 | #300 |
| 4 | Qwen 3.5 Omni Plus | 63.9 | #237 |
| 5 | Seed 2.0 Lite | 58.1 | #286 |
| 6 | Qwen2.5-Omni-7B | 53.8 | #1797 |
| 7 | Qwen3 Omni 30B A3B Instruct | 50.6 | #902 |
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-demand-detection · How It Works · Data refreshed daily, snapshot 2026-11-12.