UAVBench - Classification (ERA): leaderboard
Metric: Image-level event classification accuracy (%), zero-shot with the authors' task instructions (no fine-tuning on UAVIT-1M), on the UAVBench test unit built from the test split of ERA (aerial event videos), low-altitude drone imagery; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 84.91 | #237 |
| 2 | MiniCPM-V-2.6 | 78.8 | #825 |
| 3 | Qwen 2.5 VL 7B Instruct | 75.53 | #643 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=uavbench-classification-era · How It Works · Data refreshed daily, snapshot 2026-10-11.