VideoOdyssey-AV - Temporal Grounding: 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 locating when an event happens; higher is better.

Metric: Multiple-choice accuracy (%) on the 61 temporal grounding questions (locate the timestamp of specific audio-visual events) 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 July 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen 3.5 Omni Plus42.6#254
2Gemini 3.1 Pro (Preview)39.3#99
3Gemini 2.5 Pro37.7#276
4Qwen 3 Omni 30B A3B37.7#847
5Gemini 3 Flash32.8#175
6Ola-7B32.8#1557
7VideoLLaMA2-7B31.2#2385
8Unified-IO-2 XXL31.2
9OneLLM24.6#2372
10Unified-IO-2 XL21.3
11Unified-IO-2 L19.7
12VITA-1.5-7B13.1#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-temporal-grounding · How It Works · Data refreshed daily, snapshot 2026-11-21.