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

Open-form mathematical reasoning research benchmarks · SOTA2 Research

Open-form mathematical reasoning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

DeepMind MATHEMATICS

42.13Exact-match Accuracy

7

May 15, 2026

Full-data Fine-tuning

66.12Exact Match Accuracy

7

May 15, 2026

52.45Accuracy

7

May 15, 2026

Popular datasets

GSM8K DeepMind-Mathematics SVAMP

Follow for updates

Join SOTA2 Contact