GeoBrowse - Level 2 City (Direct): leaderboard

GeoBrowse (2026) Level 2: models geolocate an image and then follow an obfuscated BrowseComp-style multi-hop knowledge query. 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 2 (101 BrowseComp-style instances that add long-tail knowledge and obfuscated entities on top of the geolocation; 19 city, 19 state and 63 country targets), 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 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1GPT-5.221.1#185
2Gemini 3 Pro21.1#145
3Claude Opus 4.521.1#160
4GPT-515.8#178
5Gemini 2.5 Pro10.8#276
6GPT-4o10.5#751
7Gemini 2.5 Flash5.3#463
8GPT-4.15.3#505
9Llama 3.2 90B5.3#1755
10Qwen 2.5 VL 7B0#1862
11Qwen 3 VL 32B0#622
12Qwen 2.5 VL 32B0#941

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-2-city-direct · How It Works · Data refreshed daily, snapshot 2026-11-21.