Benchmark AI / Public workspace

CritPt

Science

CritPt evaluates scientific understanding and multi-step reasoning and computation on research-level physics problems. Its public dataset contains 70 challenges with problem descriptions and code templates.

Japanese introduction

研究水準の物理問題で、科学的理解と多段階の推論・計算を評価するベンチマークです。公開データには70の課題があり、問題文とコード雛形を組み合わせて解答を構成します。

critpt

Full text70 tasksProblems imported

Official source

Full text: eligible public problems include text, images and discussion.

Tasks

Whole public benchmark.

Public problems
70
Formats
text (70)
Problems with images
0
Answer availability
Answer published by the source (70)
Configs
Default (70)
Splits
train (70)
Awaiting a first discussion
70

Discussion