VideoOdyssey-V - Object Recognition: 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 recognizing objects; higher is better.

Metric: Multiple-choice accuracy (%) on the 208 object recognition questions (recognize and classify specific objects presented in the video) 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)63#99
2Gemini 2.5 Pro59.6#276
3Kimi K2.557.7#266
4GPT-5.255.3#185
5Seed 2.0 Pro51.9#222
6Qwen 3 VL 32B45.2#622
7Qwen 3.5 27B43.8#375
8Qwen 3 VL 235B A22B43.3#485
9InternVL3.5-38B40.9#1021
10LLaVA-OneVision-1.5-8B37.5#1864
11Video-R136.5#1379
12Video-KTR-7B36.5
13LLaVA-NeXT-Video-7B-DPO30.8#8618
14Kimi-VL-A3B28.9#2340
15VideoLLaMA3-7B28.4#2050

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