ODU-Bench (Audio-Visual) - Key-Point Coverage: leaderboard
The primary semantic dimension of ODU-Bench (Chen et al., 2026): the share of reference key points on the intended outcome and required context that the predicted demand covers, on the demand scenes of 1,347 audio-visual scenes (1,070 synthetic and 277 human-recorded; user turns as video with audio, earlier assistant replies as text). Percent, judged by Qwen3.6-Flash; higher is better.
Metric: Key-point hit rate (%; share of reference key points on structured intent and required context covered by the predicted intent and context, demand scenes only; 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 August 2027. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 Omni Plus | 65.8 | #237 |
| 2 | Seed 2.0 Lite | 64.1 | #286 |
| 3 | Gemini 3.1 Pro (Preview) | 63.4 | #91 |
| 4 | Gemini 3.7 Flash | 60.2 | #32 |
| 5 | Qwen3 Omni 30B A3B Instruct | 53.1 | #902 |
| 6 | Gemini 3.5 Flash Lite | 49.9 | #300 |
| 7 | Qwen2.5-Omni-7B | 42.1 | #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-key-point-coverage · How It Works · Data refreshed daily, snapshot 2026-11-12.