Navigation on CityNav Tokyo 1.0
0.3Success RateAgentNav (GPT 5)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| AgentNav (GPT 5)Agent Config=AgentNav, Backbone=GPT 52025.12 | 0.3 | 0.163 | 0.5497 | |
| AgentNav (O3)Agent Config=AgentNav, Backbone=O32025.12 | 0.27 | 0.142 | 0.5256 | |
| AgentNav (GPT 4.1)Agent Config=AgentNav, Backbone=GPT 4.12025.12 | 0.17 | 0.101 | 0.4367 | |
| AgentNav (Gemini 2.5 Flash)Agent Config=AgentNav, Backbone=Gemini 2.5 Flash2025.12 | 0.17 | 0.066 | 0.4687 | |
| AgentNav (GPT 4o)Agent Config=AgentNav, Backbone=GPT 4o2025.12 | 0.14 | 0.099 | 0.409 | |
| AgentNav (Qwen 2.5 VL 32b)Agent Config=AgentNav, Backbone=Qwen 2.5 VL 32b2025.12 | 0.12 | 0.094 | 0.4003 | |
| GPT 5Agent Config=Base2025.12 | 0.1 | 0.088 | 0.4124 | |
| Gemini 2.5 FlashAgent Config=Base2025.12 | 0.08 | 0.049 | 0.3997 | |
| O3Agent Config=Base2025.12 | 0.07 | 0.049 | 0.4033 | |
| GPT 4.1Agent Config=Base2025.12 | 0.05 | 0.044 | 0.3883 | |
| GPT 4oAgent Config=Base2025.12 | 0.04 | 0.046 | 0.3679 | |
| Qwen 2.5 VL 32bAgent Config=Base2025.12 | 0.02 | 0.023 | 0.3001 |