UAV-DualCog - Landmark Visibility Counting: leaderboard
Metric: Visibility-count accuracy (%; 1,024 flight videos in which the number of appearances of a target landmark must be counted with its visible intervals; structured JSON answers on renders of simulated AerialVLN scenes, the discrete answer scored whatever the predicted box or interval; instant mode with explicit thinking disabled where a model allows it; higher is better). Source: arxiv.org. Saturation forecast: Around 2029. 29 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Flash Lite (Non-reasoning) | 59.9 |
| 2 | MiMo-V2-Omni | 55.8 |
| 3 | Qwen 3.7 Plus (Non-reasoning) | 53.6 |
| 4 | InternVL3.5-8B | 52.9 |
| 5 | Qwen 3.6 Plus (Non-reasoning) | 52.3 |
| 6 | Qwen 3.5 Plus (Non-reasoning) | 48.3 |
| 7 | Qwen 3.5 9B (Non-reasoning) | 47.7 |
| 8 | Qwen 3.5 35B A3B (Non-reasoning) | 47.1 |
| 9 | Qwen 3.5 122B A10B (Non-reasoning) | 47.1 |
| 10 | Kimi K2.5 (Non-reasoning) | 45.3 |
| 11 | Qwen 3.5 27B (Non-reasoning) | 41.3 |
| 12 | Kimi K2.6 (Non-reasoning) | 39.9 |
| 13 | Qwen 3.5 397B A17B (Non-reasoning) | 36.6 |
| 14 | GLM-4.6V (Non-reasoning) | 30.2 |
| 15 | Qwen 3.5 4B (Non-reasoning) | 29.7 |
Interactive version: theaggregate.ai/benchmark?slug=uav-dualcog-landmark-visibility-counting · How It Works · Data refreshed daily, snapshot 2026-09-29.