Evaluate agents for end-to-end frontier physics research.

FrontierPhysics is a benchmark evaluating how AI agents do frontier physics research iteratively. We evaluate realistic research challenges with iteration loops from literature deep review to research plan implementation. Tasks come from real research problems that take at least weeks of effort for a physics PhD to do deep research and implement, and SOTA LLM agents struggle with. The tasks are evaluated with verifiable graders and per-task rubric-based reviewer agents to make sure agents are doing research in ways aligned with real frontier researchers.