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

Reasoning and Math research benchmarks · SOTA2 Research

Reasoning and Math

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

VLMEvalKit (test)

Gemini2.0-Flash

73.4MathVista Accuracy

13

Mar 5, 2026

GSM8K, CommonSense, BoolQ, ARC Challenge, and HellaSwag

87.8Average Accuracy

9

May 12, 2026

Popular datasets

VLMEvalKit GSM8K, CommonSense, BoolQ, ARC, and HellaSwag

Follow for updates

Join SOTA2 Contact