VideoOdyssey-AV - Object Recognition: leaderboard
Metric: Multiple-choice accuracy (%) on the 63 object recognition questions (recognize and classify specific objects presented in the video, based on both visual and audio cues) of VideoOdyssey-AV (human-written questions on 100 videos of 60 to 255 minutes that need both visual and audio cues; 1,062 in all), omni-modal models given video and audio, 64 frames (VITA-1.5-7B 16); higher is better. Source: arxiv.org. Saturation forecast: Around June 2027. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 52.4 |
| 2 | Qwen 3.5 Omni Plus | 50.8 |
| 3 | Gemini 3 Flash | 44.4 |
| 4 | Gemini 2.5 Pro | 41.3 |
Interactive version: theaggregate.ai/benchmark?slug=videoodyssey-av-object-recognition · How It Works · Data refreshed daily, snapshot 2026-10-07.