ERGeoBench: leaderboard
Multimodal large language models (MLLMs) have shown strong potential as embodied agents, yet embodied geo-localization remains underexplored due to the lack of fine-grained evaluation. We introduce ERGeoBench, a diagnostic benchmark for vision-driven embodied geo-localization. ERGeoBench evaluates models under three progressive settings -- single-view, panorama-view, and embodied-view -- where age
Metric: Street (%) (self-reported). Source: benchmarklist.com. Saturation forecast: Around February 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash | 8.83 | #99 |
| 2 | Gemini 2.5 Pro | 6.4 | #152 |
| 3 | Gemini 2.0 Flash | 5.77 | #342 |
| 4 | GPT-4o | 4.3 | #343 |
| 5 | InternVL3-8B | 2.66 | #620 |
| 6 | Qwen 2.5 7B | 2.24 | #922 |
| 7 | Qwen 3 8B | 1.1 | #674 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=ergeobench · How It Works · Data refreshed daily, snapshot 2026-10-20.