VideoOdyssey-AV - Speech Fact Retrieval: 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 retrieving facts stated in speech; higher is better.

Metric: Multiple-choice accuracy (%) on the 173 speech fact retrieval questions (retrieve explicitly mentioned factual information from 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 February 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)59.5#99
2Gemini 3 Flash50.9#175
3Gemini 2.5 Pro50.3#276
4Qwen 3.5 Omni Plus43.4#254
5Qwen 3 Omni 30B A3B28.9#847
6Ola-7B28.3#1557
7Unified-IO-2 L26
8Unified-IO-2 XL23.1
9VITA-1.5-7B22.5#1853
10Unified-IO-2 XXL22
11OneLLM21.4#2372
12VideoLLaMA2-7B20.8#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-speech-fact-retrieval · How It Works · Data refreshed daily, snapshot 2026-11-21.