PhysicsFinals
math official site →
PHYSICS is a comprehensive benchmark for university-level physics problem solving, containing 1,297 expert-annotated problems covering six core areas: classical mechanics, quantum mechanics, thermodynamics and statistical mechanics, electromagnetism, atomic physics, and optics. Each problem requires advanced physics knowledge and mathematical reasoning. Even advanced models like o3-mini achieve only 59.9% accuracy.
Methodology
Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: math, physics, reasoning. Language: en. Verified by llm-stats: no.