StreamPro-Bench - Object Understanding: leaderboard
Metric: StreamPro-F1 (%; a response counts only when a Gemini 2.5 Pro judge credits its content and it arrives inside the task time window, and precision and recall over the response trajectory penalize extra and missed responses; videos streamed at 1 FPS; confirm object state changes as they happen, within 3 seconds). Source: arxiv.org. Saturation forecast: Around August 2028. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | MiniCPM-o-4.5 | 13.9 |
| 2 | Qwen 2.5 VL 7B | 11.3 |
| 3 | Qwen 3 VL 8B | 3 |
Interactive version: theaggregate.ai/benchmark?slug=streampro-bench-object-understanding · How It Works · Data refreshed daily, snapshot 2026-09-26.