VideoOdyssey-AV - Spatial 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 locations and paths; higher is better.

Metric: Multiple-choice accuracy (%) on the 60 spatial reasoning questions (analyze the audio-visual information to reason about the spatial locations of objects) 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 November 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen 3.5 Omni Plus31.7#254
2Gemini 3 Flash30#175
3Gemini 3.1 Pro (Preview)28.3#99
4Unified-IO-2 XXL28.3
5Ola-7B26.7#1557
6Unified-IO-2 L25
7Gemini 2.5 Pro23.3#276
8VideoLLaMA2-7B23.3#2385
9OneLLM23.3#2372
10Unified-IO-2 XL23.3
11Qwen 3 Omni 30B A3B16.7#847
12VITA-1.5-7B16.7#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-spatial-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.