VideoOdyssey-V - Summarization: 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 summarizing long stretches; higher is better.

Metric: Multiple-choice accuracy (%) on the 65 summarization questions (analyze the visual information to achieve a high-level, abstract understanding) 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
1Kimi K2.569.2#266
2Gemini 2.5 Pro61.5#276
3Gemini 3.1 Pro (Preview)56.9#99
4Seed 2.0 Pro55.4#222
5Qwen 3.5 27B49.2#375
6Qwen 3 VL 235B A22B47.7#485
7GPT-5.244.6#185
8InternVL3.5-38B44.6#1021
9Video-KTR-7B41.5
10Qwen 3 VL 32B40#622
11Video-R136.9#1379
12LLaVA-NeXT-Video-7B-DPO36.9#8618
13Phi-4 Multimodal Instruct32.3#4154
14LLaVA-NeXT-Video-DPO (34B)30.8#2489
15LLaVA-OneVision-1.5-8B29.2#1864

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