VideoOdyssey-AV - Object Reasoning: 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 reasoning about objects and their relations; higher is better.

Metric: Multiple-choice accuracy (%) on the 56 object reasoning questions (infer a specific object that meets a certain condition, or infer its function, attributes, or relationships between objects, 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 October 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Pro42.9#276
2Gemini 3 Flash42.9#175
3Gemini 3.1 Pro (Preview)41.1#99
4Qwen 3.5 Omni Plus35.7#254
5Ola-7B30.4#1557
6VideoLLaMA2-7B30.4#2385
7VITA-1.5-7B30.4#1853
8Unified-IO-2 XXL28.6
9Qwen 3 Omni 30B A3B23.2#847
10OneLLM21.4#2372
11Unified-IO-2 XL21.4
12Unified-IO-2 L19.6

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