GeoBrowse - Level 1 State (GATE Agent): leaderboard
Metric: Accuracy (%) on the state-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 July 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 42.6 |
| 2 | Claude Opus 4.5 | 32.7 |
| 3 | Gemini 2.5 Pro | 23.6 |
| 4 | GPT-5 | 23.6 |
| 5 | GPT-4o | 20 |
| 6 | GPT-4.1 | 20 |
| 7 | Llama 3.2 90B | 10.9 |
| 8 | Qwen 2.5 VL 7B | 9.1 |
Interactive version: theaggregate.ai/benchmark?slug=geobrowse-level-1-state-gate-agent · How It Works · Data refreshed daily, snapshot 2026-10-07.