An LLM agent with image-reading and answer-review tools scored 23.5/30 on IPhO 2025 theory problems, matching the median gold-medalist theory score.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Physics Supernova: AI Agent Matches Elite Gold Medalists at IPhO 2025
An LLM agent with image-reading and answer-review tools scored 23.5/30 on IPhO 2025 theory problems, matching the median gold-medalist theory score.