VideoOdyssey-AV - Visual Attribute 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 visual attributes; higher is better.

Metric: Multiple-choice accuracy (%) on the 58 visual attribute recognition questions (identify the visual attributes of specific entities, including humans, objects and scenes, 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 July 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen 3.5 Omni Plus46.6#254
2Gemini 2.5 Pro44.8#276
3Gemini 3.1 Pro (Preview)43.1#99
4Gemini 3 Flash36.2#175
5Ola-7B27.6#1557
6Unified-IO-2 XXL27.6
7Unified-IO-2 L27.6
8VideoLLaMA2-7B25.9#2385
9Unified-IO-2 XL24.1
10Qwen 3 Omni 30B A3B22.4#847
11OneLLM22.4#2372
12VITA-1.5-7B20.7#1853

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-visual-attribute-recognition · How It Works · Data refreshed daily, snapshot 2026-11-21.