Navigation on CityNav Vienna 1.0
56SuccessAgentNav (GPT 5)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| AgentNav (GPT 5)Agent Config=AgentNav, Backbone=GPT 52025.12 | 56 | 22.6 | 54.82 | |
| AgentNav (O3)Agent Config=AgentNav, Backbone=O32025.12 | 38 | 19 | 50.73 | |
| AgentNav (GPT 4.1)Agent Config=AgentNav, Backbone=GPT 4.12025.12 | 32 | 18.2 | 49.95 | |
| AgentNav (GPT 4o)Agent Config=AgentNav, Backbone=GPT 4o2025.12 | 26 | 17 | 46.32 | |
| AgentNav (Gemini 2.5 Flash)Agent Config=AgentNav, Backbone=Gemini 2.5 Flash2025.12 | 17 | 13.7 | 46.35 | |
| AgentNav (Qwen 2.5 VL 32b)Agent Config=AgentNav, Backbone=Qwen 2.5 VL 32b2025.12 | 12 | 11.9 | 44.94 | |
| GPT 5Agent Config=Base2025.12 | 11 | 9.2 | 40.72 | |
| O3Agent Config=Base2025.12 | 9 | 8.3 | 39.82 | |
| GPT 4oAgent Config=Base2025.12 | 4 | 3.1 | 35.67 | |
| GPT 4.1Agent Config=Base2025.12 | 2 | 3.7 | 34.66 | |
| Gemini 2.5 FlashAgent Config=Base2025.12 | 1 | 1 | 29.31 | |
| Qwen 2.5 VL 32bAgent Config=Base2025.12 | 0 | 0 | 26.1 |