GeoBench ACW — leaderboard

GeoGuessr for LLMs (ACW subset) - identify location from a single static image using the Around-the-Clock-and-World dataset. Tests visual geographic reasoning and world knowledge.

Metric: Average Score. Source: geobench.org. Status: saturation imminent. 48 models tracked.

Top models

#ModelScore
1Claude Fable 54403.7
2Gemini 3 Flash (Preview)4332.77
3Gemini 3.5 Flash4288.21
4Gemini 3.1 Flash Lite (Preview)4229.08
5Gemini 3.1 Pro (Preview)4172.19
6Gemini 3 Pro (Preview)4144.58
7Claude Opus 4.8 (Thinking)4127.75
8Human Expert4100
9Gemini 2.5 Pro (Preview 03-25)4092.5
10Gemini 2.5 Pro4019.35
11GPT-53937
12Gemini 1.5 Flash3933.94
13O3 (High)3929.63
14O13924.6
15Gemini 2.0 Flash3897.45

Interactive version: theaggregate.ai/benchmark?slug=geobench-acw · How the rankings work · Data refreshed daily, snapshot 2026-07-22.