VideoOdyssey-AV - Acoustic Event 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 sound events; higher is better.

Metric: Multiple-choice accuracy (%) on the 86 acoustic event recognition questions (identify and classify the type of a sound 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 October 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Pro38.4#276
2Qwen 3.5 Omni Plus38.4#254
3Gemini 3.1 Pro (Preview)37.2#99
4Gemini 3 Flash32.6#175
5Ola-7B30.2#1557
6Unified-IO-2 XXL27.9
7Qwen 3 Omni 30B A3B25.6#847
8Unified-IO-2 L25.6
9Unified-IO-2 XL24.4
10VideoLLaMA2-7B20.9#2385
11VITA-1.5-7B20.9#1853
12OneLLM19.8#2372

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