VideoOdyssey-AV - Action Recognition: leaderboard
VideoOdyssey (2026) tests ultra-long video understanding with human-written multiple-choice questions on videos averaging 109 minutes, each annotated with how long a viewer must watch continuously to answer. This board is accuracy in percent on the audio-visual subset questions about recognizing actions; higher is better.
Metric: Multiple-choice accuracy (%) on the 60 action recognition questions (identify the actions of humans or other objects 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 September 2027. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 45 | #175 |
| 2 | Gemini 2.5 Pro | 40 | #276 |
| 3 | Gemini 3.1 Pro (Preview) | 40 | #99 |
| 4 | Qwen 3.5 Omni Plus | 38.3 | #254 |
| 5 | Qwen 3 Omni 30B A3B | 36.7 | #847 |
| 6 | VITA-1.5-7B | 30 | #1853 |
| 7 | Unified-IO-2 XL | 28.3 | |
| 8 | Ola-7B | 23.3 | #1557 |
| 9 | Unified-IO-2 XXL | 23.3 | |
| 10 | Unified-IO-2 L | 21.7 | |
| 11 | OneLLM | 21.4 | #2372 |
| 12 | VideoLLaMA2-7B | 16.6 | #2385 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=videoodyssey-av-action-recognition · How It Works · Data refreshed daily, snapshot 2026-11-21.