GeoBrowse - Level 1 City (Direct): leaderboard

GeoBrowse (2026) Level 1: models compose weak visual cues in a street scene into a location. This board scores the city-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 city-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 March 2028. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Pro13.5#145
2Claude Opus 4.513.5#160
3Gemini 2.5 Pro11.5#276
4GPT-511.5#178
5Gemini 2.5 Flash7.7#463
6GPT-5.27.7#185
7Qwen 3 VL 32B7.7#622
8GPT-4o5.8#751
9GPT-4.15.8#505
10Llama 3.2 90B3.8#1755
11Qwen 2.5 VL 32B3.8#941
12Qwen 2.5 VL 7B1.9#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-city-direct · How It Works · Data refreshed daily, snapshot 2026-11-21.