[Spike] Benchmark GUI Solution

[WHALEEYE]

Description

Look into possible designs of the GUI for the benchmark system, such as how the frontend interacts with the backend, and what elements should we include in the frontend.

Notes

Anthropic Computer Use has provided a demo which has a GUI (they uses VNC). This is only a reference, and we don't need to necessarily follow this.
https://github.com/anthropics/anthropic-quickstarts/tree/main/computer-use-demo

Expected Output

A brief report covering the points above, along with any drawbacks found that can be improved.