GeoBrowse - Level 1 Country (Direct): leaderboard

GeoBrowse (2026) Level 1: models compose weak visual cues in a street scene into a location. This board scores the country-level targets with the model answering directly without tools; accuracy in percent from an LLM judge, mean of three runs, higher is better.

Metric: Accuracy (%) on the country-level targets of GeoBrowse Level 1 (199 street-scene instances whose location must be composed from weak, fragmented visual cues), judged correct by an LLM judge with the Humanity's Last Exam judging prompt, mean of 3 runs, under direct inference: the model answers in a single pass without tool calls; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Pro53.3#145
2Claude Opus 4.543.4#160
3Gemini 2.5 Pro41.3#276
4Gemini 2.5 Flash40.2#463
5GPT-538#178
6GPT-4o35.7#751
7GPT-5.230.4#185
8GPT-4.130.4#505
9Llama 3.2 90B19.6#1755
10Qwen 2.5 VL 32B17.3#941
11Qwen 3 VL 32B16.3#622
12Qwen 2.5 VL 7B11.1#1862

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=geobrowse-level-1-country-direct · How It Works · Data refreshed daily, snapshot 2026-11-21.