AirGroundBench - Scene Perception: leaderboard
Metric: Accuracy (%) on the scene-perception VQA task; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 96.86 |
| 2 | GLM-4.6V | 96.55 |
| 3 | Qwen 3.5 397B A17B | 93.1 |
| 4 | Seed 2.0 Pro | 93.1 |
| 5 | Qwen 3 VL 235B A22B | 92.17 |
| 6 | GPT-5.2 | 89.66 |
| 7 | Kimi K2.5 | 89.66 |
| 8 | Qwen 3.5 27B | 89.66 |
| 9 | Gemini 3.1 Pro (Preview) | 86.21 |
| 10 | Qwen 3.5 Plus | 86.21 |
| 11 | ERNIE 5.0 | 86.21 |
Interactive version: theaggregate.ai/benchmark?slug=airgroundbench-scene-perception · How It Works · Data refreshed daily, snapshot 2026-09-29.