GeoBrowse - Level 2 State (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 state-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 state-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 May 2027. 12 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.5 | 26.3 | #160 |
| 2 | GPT-5.2 | 21.1 | #185 |
| 3 | Gemini 3 Pro | 21.1 | #145 |
| 4 | GPT-4o | 15.8 | #751 |
| 5 | Gemini 2.5 Pro | 10.8 | #276 |
| 6 | GPT-5 | 10.8 | #178 |
| 7 | Gemini 2.5 Flash | 10.8 | #463 |
| 8 | GPT-4.1 | 5.3 | #505 |
| 9 | Llama 3.2 90B | 5.3 | #1755 |
| 10 | Qwen 3 VL 32B | 5.3 | #622 |
| 11 | Qwen 2.5 VL 7B | 0 | #1862 |
| 12 | Qwen 2.5 VL 32B | 0 | #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-state-direct · How It Works · Data refreshed daily, snapshot 2026-11-21.