🛠️ Portal2Bench – Can AI agents solve Portal 2?

Summary
Portal2Bench is a benchmark designed to test whether AI agents can successfully solve the video game Portal 2.

Why it’s interesting
It evaluates AI agent capabilities using a complex 3D puzzle video game environment.

Target user
AI researchers and developers

Source metrics: Points 3 · Comments 0
HN discussion · Project
Source: #HackerNews / Show HN