All activity
Cheng Zuoleft a comment
Looks very promising on research tasks that require deep explorations. The only concern is the token costs that come with it I'm afraid.
Gemini Deep Research AgentThe best research agent is open for devs
Cheng Zuoleft a comment
It's quite good compared to GPT-5.1 in terms of daily coding and creative writing. But I'd still use Claude for the real difficult coding tasks, and Gemini for multimodal tasks.
GPT-5.2Frontier model for professional work and long-running agents