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

Language Reasoning research benchmarks · SOTA2 Research

Language Reasoning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

BBH (BIG-Bench Hard)

87.5Average BBH Score

20

Jun 19, 2026

40.15Accuracy

12

Mar 19, 2026

Language Reasoning Average

73.25Accuracy

12

Mar 19, 2026

DeepAccident-CCoT (val)

84.2Accuracy

6

May 12, 2026

LangR unseen tasks (test)

60.8Pass@1

3

Mar 4, 2026

Popular datasets

TruthfulQA BIG-Bench LangR DeepAccident Language Reasoning

Follow for updates

Join SOTA2 Contact