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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 53.2 | #280 |
| 2 | Gemini 3 Flash | 53.2 | #180 |
| 3 | Qwen 3.5 Omni Plus | 45.2 | #261 |
| 4 | Ola-7B | 43.6 | #1568 |
| 5 | Gemini 3.1 Pro (Preview) | 41.9 | #102 |
| 6 | VITA-1.5-7B | 30.7 | #1870 |
| 7 | Qwen 3 Omni 30B A3B | 29 | #851 |
| 8 | VideoLLaMA2-7B | 25.8 | #2403 |
| 9 | Unified-IO-2 XL | 25.8 | |
| 10 | OneLLM | 24.2 | #2388 |
| 11 | Unified-IO-2 XXL | 24.2 | |
| 12 | Unified-IO-2 L | 24.2 |
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.