Visual Question Answering on Dyn (en)
1,907.6Search TimeMultimodal Planning Agent
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Multimodal Planning AgentBase Model=GPT-4o2026.01 | 1,907.6 | 1,179.8 | 3,087.4 | |
| OmniSearchBase Model=GPT-4o2026.01 | 11,449.4 | — | — |
Loading the SOTA2 catalog…