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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 56.3 | #99 |
| 2 | Gemini 2.5 Pro | 50.4 | #276 |
| 3 | Seed 2.0 Pro | 49.7 | #222 |
| 4 | GPT-5.2 | 49 | #185 |
| 5 | Kimi K2.5 | 48.6 | #266 |
| 6 | Qwen 3.5 27B | 44.6 | #375 |
| 7 | Qwen 3 VL 235B A22B | 40.6 | #485 |
| 8 | InternVL3.5-38B | 36.7 | #1021 |
| 9 | Qwen 3 VL 32B | 36.2 | #622 |
| 10 | Video-KTR-7B | 33.8 | |
| 11 | Video-R1 | 33.7 | #1379 |
| 12 | VideoLLaMA3-7B | 30.8 | #2050 |
| 13 | LLaVA-OneVision-1.5-8B | 29.6 | #1864 |
| 14 | Kimi-VL-A3B | 26.3 | #2340 |
| 15 | Phi-4 Multimodal Instruct | 25.7 | #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.