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

Multi-Domain Evaluation Suite dataset and benchmarks · SOTA2 Research

Research Datasets

Multi-Domain Evaluation Suite

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Cross-domain language model performance evaluation

Multi-domain Evaluation Suite (mid-training evaluation)

60.4Math Score

4

Multi-Domain Language Modeling and Reasoning

Multi-Domain Evaluation Suite General, Code, Math 50B tokens (mid-training)

59.13General Accuracy

3

Popular tasks

Multi-Domain Language Modeling and Reasoning Cross-domain language model performance evaluation

Follow for updates

Join SOTA2 Contact