GeoBrowse - Level 2 State (Direct): leaderboard
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 October 2027. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.5 | 26.3 |
| 2 | GPT-5.2 | 21.1 |
| 3 | Gemini 3 Pro | 21.1 |
| 4 | GPT-4o | 15.8 |
| 5 | Gemini 2.5 Pro | 10.8 |
| 6 | GPT-5 | 10.8 |
| 7 | Gemini 2.5 Flash | 10.8 |
| 8 | GPT-4.1 | 5.3 |
| 9 | Llama 3.2 90B | 5.3 |
| 10 | Qwen 2.5 VL 7B | 0 |
Interactive version: theaggregate.ai/benchmark?slug=geobrowse-level-2-state-direct · How It Works · Data refreshed daily, snapshot 2026-10-07.