UAVQA-Bench: leaderboard
Metric: Overall accuracy (%; sample-weighted accuracy over all 1,500 questions; direct answering over UAVQA-Bench: 1,500 human-annotated questions on images from 13 public UAV datasets, 16 tasks in six capability dimensions, multiple choice plus box grounding counted correct at IoU 0.5). Source: arxiv.org. Saturation forecast: Around December 2026. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 73 |
| 2 | Gemini 3 Flash | 70.73 |
| 3 | Qwen 3 VL 32B Instruct | 69.6 |
| 4 | Qwen 3 VL 32B (Thinking) | 68.27 |
| 5 | Qwen 3.5 9B | 63.8 |
| 6 | Qwen 3 VL 30B A3B (Thinking) | 62 |
| 7 | Qwen 3 VL 8B Instruct | 61.73 |
| 8 | Qwen 3 VL 30B A3B Instruct | 61.13 |
| 9 | Qwen 3 VL 8B (Thinking) | 52.6 |
| 10 | InternVL3.5-8B | 40.53 |
Interactive version: theaggregate.ai/benchmark?slug=uavqa-bench · How It Works · Data refreshed daily, snapshot 2026-09-29.