VideoOdyssey-V: 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 over all questions of the visual subset; higher is better.

Metric: Multiple-choice accuracy (%) over all questions of VideoOdyssey-V (human-written questions on 100 videos of 60 to 255 minutes that need visual cues and long continuous viewing; 1,618 in all), 128 frames for proprietary models and each open model's maximum frame setting; higher is better. Source: arxiv.org. Saturation forecast: Around June 2027. 18 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)56.3#99
2Gemini 2.5 Pro50.4#276
3Seed 2.0 Pro49.7#222
4GPT-5.249#185
5Kimi K2.548.6#266
6Qwen 3.5 27B44.6#375
7Qwen 3 VL 235B A22B40.6#485
8InternVL3.5-38B36.7#1021
9Qwen 3 VL 32B36.2#622
10Video-KTR-7B33.8
11Video-R133.7#1379
12VideoLLaMA3-7B30.8#2050
13LLaVA-OneVision-1.5-8B29.6#1864
14Kimi-VL-A3B26.3#2340
15Phi-4 Multimodal Instruct25.7#4154

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=videoodyssey-v · How It Works · Data refreshed daily, snapshot 2026-11-21.