VideoOdyssey-AV - Captioning: 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 describing a scene; higher is better.

Metric: Multiple-choice accuracy (%) on the 47 captioning questions (generate a descriptive text that details the observable visual actions and audible acoustic events, including speech, environmental sounds, and scene dynamics, occurring in the video) 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 2.5 Pro74.5#276
2Qwen 3.5 Omni Plus72.3#254
3Gemini 3 Flash66#175
4Gemini 3.1 Pro (Preview)61.7#99
5VideoLLaMA2-7B46.8#2385
6Unified-IO-2 XXL44.7
7Ola-7B42.6#1557
8Qwen 3 Omni 30B A3B38.3#847
9Unified-IO-2 XL36.2
10Unified-IO-2 L36.2
11OneLLM21.3#2372
12VITA-1.5-7B6.4#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-captioning · How It Works · Data refreshed daily, snapshot 2026-11-21.