GeoBrowse - Level 2 Country (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 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 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 June 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Opus 4.527#160
2Gemini 3 Pro23.8#145
3GPT-520.6#178
4GPT-5.220.6#185
5Gemini 2.5 Pro17.5#276
6GPT-4.115.9#505
7GPT-4o11.1#751
8Gemini 2.5 Flash9.9#463
9Llama 3.2 90B9.5#1755
10Qwen 3 VL 32B9.5#622
11Qwen 2.5 VL 32B6.3#941
12Qwen 2.5 VL 7B3.2#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-2-country-direct · How It Works · Data refreshed daily, snapshot 2026-11-21.