Agent Browser’s Rust binary talks to a Node daemon via JSON, so your agents get clear outputs and reliable automation steps.
🔔 The automatic evaluation on CodaLab are under construction. The MathVista dataset is derived from three newly collected datasets: IQTest, FunctionQA, and Paper, as well as 28 other source datasets.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback