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

Comprehensive Reasoning research benchmarks · SOTA2 Research

Comprehensive Reasoning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

62Accuracy

18

May 5, 2026

Unsilencing Latent Reasoning

84.2Accuracy

18

May 5, 2026

Mathematical and General Reasoning Suite Combined

46.7Overall Accuracy

16

Mar 25, 2026

Aggregate Benchmarks

Qwen2.5-VL-7B + DUPL

66.9Average Accuracy

13

Jun 16, 2026

Popular datasets

ScienceQA Aggregate Benchmarks MM-Star Mathematical and General Reasoning Suite

Follow for updates

Join SOTA2 Contact