VideoOdyssey-V - Object 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 visual subset questions about reasoning about objects and their relations; higher is better.

Metric: Multiple-choice accuracy (%) on the 173 object reasoning questions (infer a specific object that meets a certain condition, or infer its function, attributes, or relationships between objects) 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 February 2027. 18 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3.1 Pro (Preview)65.3#99
2Gemini 2.5 Pro60.1#276
3GPT-5.260.1#185
4Kimi K2.553.8#266
5Qwen 3.5 27B52.6#375
6Seed 2.0 Pro52.6#222
7Qwen 3 VL 235B A22B50.3#485
8Qwen 3 VL 32B43.4#622
9VideoLLaMA3-7B39.3#2050
10InternVL3.5-38B35.8#1021
11Video-R135.8#1379
12Video-KTR-7B35.3
13LLaVA-OneVision-1.5-8B30.1#1864
14Video-LLaVA-7B27.8#3879
15Phi-4 Multimodal Instruct27.2#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-object-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.