VideoOdyssey-V - Object Reasoning: leaderboard
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 January 2027. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 65.3 |
| 2 | Gemini 2.5 Pro | 60.1 |
| 3 | GPT-5.2 | 60.1 |
| 4 | Kimi K2.5 | 53.8 |
| 5 | Qwen 3.5 27B | 52.6 |
| 6 | Seed 2.0 Pro | 52.6 |
| 7 | Qwen 3 VL 235B A22B | 50.3 |
| 8 | Phi-4 Multimodal Instruct | 27.2 |
Interactive version: theaggregate.ai/benchmark?slug=videoodyssey-v-object-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-07.