GeoRC: leaderboard
Geolocation reasoning benchmark for vision-language models, measuring location inference, F1, and country-level accuracy.
Metric: F1 (self-reported). Source: benchmarklist.com. Status: saturation imminent. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 | 42.3 |
| 2 | Gemini 2.5 Pro | 41.51 |
| 3 | Gemini 2.5 Flash | 41.3 |
| 4 | Gemini 3 Pro | 40.98 |
| 5 | GPT-5 | 40.56 |
| 6 | Qwen 2.5 VL 7B Instruct | 31.63 |
| 7 | Gemma 3 12B (IT) | 31.21 |
| 8 | Llama 3.2 11B Instruct | 25.86 |
| 9 | Qwen 3 VL 8B Instruct | 23.81 |
Interactive version: theaggregate.ai/benchmark?slug=georc · How It Works · Data refreshed daily, snapshot 2026-09-05.