ERGeoBench - Foundational Perception: leaderboard
Foundational Perception diagnostics on ERGeoBench (2026): multiple-choice and true or false questions about architecture, infrastructure, signage, terrain and vegetation in street-level views, averaged over the five categories. Accuracy in percent; higher is better.
Metric: Accuracy (%) on the foundational perception diagnostic questions: multiple-choice and true/false questions on architecture, infrastructure, signage, terrain and vegetation in a declared field of view, averaged over the five categories; unified structured prompt with egocentric observations, action history and in-context examples, temperature 0.1, first valid JSON object parsed (invalid outputs count as failures); higher is better. Source: arxiv.org. Saturation forecast: Around April 2027. 9 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 82.78 | #751 |
| 2 | Qwen-VL-Max | 81.1 | #1400 |
| 3 | InternVL3-8B | 75.99 | #1782 |
| 4 | Gemini 2.5 Pro | 70.26 | #276 |
| 5 | Qwen 3 VL 8B | 70.23 | #917 |
| 6 | InternVL2.5-8B | 69.45 | #2370 |
| 7 | Gemini 2.0 Flash | 69.08 | #723 |
| 8 | Gemini 3 Flash | 66.37 | #175 |
| 9 | Qwen 2.5 VL 7B | 61.52 | #1862 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=ergeobench-foundational-perception · How It Works · Data refreshed daily, snapshot 2026-11-21.