VideoOdyssey-AV - Speech Content 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 what speech implies; higher is better.

Metric: Multiple-choice accuracy (%) on the 62 speech content reasoning questions (reason about implicit content that is not explicitly mentioned in the speech to answer questions, 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 March 2028. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Pro53.2#280
2Gemini 3 Flash53.2#180
3Qwen 3.5 Omni Plus45.2#261
4Ola-7B43.6#1568
5Gemini 3.1 Pro (Preview)41.9#102
6VITA-1.5-7B30.7#1870
7Qwen 3 Omni 30B A3B29#851
8VideoLLaMA2-7B25.8#2403
9Unified-IO-2 XL25.8
10OneLLM24.2#2388
11Unified-IO-2 XXL24.2
12Unified-IO-2 L24.2

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=videoodyssey-av-speech-content-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-22.