Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

MATH-Perturb dataset and benchmarks · SOTA2 Research

Research Datasets

MATH-Perturb

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Mathematical Problem Solving

MATH-Perturb MP-simple

72.8Exact Match Accuracy

12

Mathematical Reasoning

Math-Perturb

79.1Math-P Hard Score

5

Popular tasks

Mathematical Reasoning Mathematical Problem Solving

Follow for updates

Join SOTA2 Contact