GeoBrowse - Level 1 City (GATE Agent): 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 inside the GATE agent workflow of the benchmark with image and web 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 the benchmark's GATE agentic workflow: a ReAct loop with five image tools (crop, super-resolution and others) and four knowledge tools (web text and image search, page visits, code) under a fixed protocol, tool suite and call budget; higher is better. Source: arxiv.org. Saturation forecast: Around September 2027. 9 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 3 Pro24#145
2Claude Opus 4.515.4#160
3Gemini 2.5 Pro13.5#276
4GPT-511.5#178
5GPT-4o7.7#751
6GPT-4.17.7#505
7Qwen 3 VL 32B7.7#622
8Qwen 2.5 VL 7B3.8#1862
9Llama 3.2 90B3.8#1755

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-gate-agent · How It Works · Data refreshed daily, snapshot 2026-11-21.