VideoOdyssey-AV - Object 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 objects; higher is better.

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 February 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)52.4#99
2Qwen 3.5 Omni Plus50.8#254
3Gemini 3 Flash44.4#175
4Gemini 2.5 Pro41.3#276
5Qwen 3 Omni 30B A3B34.9#847
6Ola-7B30.2#1557
7Unified-IO-2 L28.6
8VITA-1.5-7B28.6#1853
9OneLLM27#2372
10Unified-IO-2 XXL25.4
11VideoLLaMA2-7B22.2#2385
12Unified-IO-2 XL22.2

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