VideoOdyssey-AV - Intentional 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 inferring motives; higher is better.

Metric: Multiple-choice accuracy (%) on the 52 intentional reasoning questions (infer the underlying purposes or motivations behind a specific character’s actions, 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)65.4#99
2Gemini 2.5 Pro48.1#276
3Gemini 3 Flash48.1#175
4Qwen 3.5 Omni Plus40.4#254
5Ola-7B38.5#1557
6Qwen 3 Omni 30B A3B26.9#847
7Unified-IO-2 XL26.9
8Unified-IO-2 L25
9Unified-IO-2 XXL23.1
10OneLLM19.2#2372
11VITA-1.5-7B11.5#1853
12VideoLLaMA2-7B9.62#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-intentional-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.