VideoOdyssey-V - Temporal Ordering: 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 ordering events in time; higher is better.

Metric: Multiple-choice accuracy (%) on the 89 temporal ordering questions (arrange multiple key visual events from the video in temporal order) 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)70.8#99
2GPT-5.269.7#185
3Gemini 2.5 Pro64#276
4Kimi K2.557.3#266
5Seed 2.0 Pro56.2#222
6Qwen 3.5 27B55.1#375
7Qwen 3 VL 32B40.5#622
8InternVL3.5-38B36#1021
9LLaVA-NeXT-Video-DPO (34B)36#2489
10Qwen 3 VL 235B A22B34.8#485
11LLaVA-OneVision-1.5-8B33.7#1864
12VideoLLaMA3-7B30.3#2050
13Video-R129.2#1379
14Video-LLaVA-7B23.6#3879
15LLaVA-NeXT-Video-7B-DPO23.6#8618

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-temporal-ordering · How It Works · Data refreshed daily, snapshot 2026-11-21.