VideoOdyssey-V - Action Recognition: leaderboard
Metric: Multiple-choice accuracy (%) on the 192 action recognition questions (identify the actions of humans or other objects 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 July 2027. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 57.8 |
| 2 | Seed 2.0 Pro | 54.7 |
| 3 | Kimi K2.5 | 50 |
| 4 | Qwen 3.5 27B | 50 |
| 5 | Gemini 2.5 Pro | 49.5 |
| 6 | GPT-5.2 | 46.9 |
| 7 | Qwen 3 VL 235B A22B | 44.3 |
| 8 | Phi-4 Multimodal Instruct | 24.5 |
Interactive version: theaggregate.ai/benchmark?slug=videoodyssey-v-action-recognition · How It Works · Data refreshed daily, snapshot 2026-10-07.