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

CMMLU dataset and benchmarks – Page 2 · SOTA2 Research

Research Datasets

CMMLU

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

CMMLU (test)

32.11Knowledge CMMLU Test Accuracy

3

Knowledge Reasoning

CMMLU c

36.08Accuracy (Normalized)

3

General Language Understanding

CMMLU 5-shot

90.61Accuracy

3

Language Understanding

CMMLU Cantonese

27.72Accuracy (Humanities)

3

Downstream Performance Prediction

CMMLU

0.003MSE

3

General Competence Evaluation

CMMLU

84.94Accuracy

2

Chinese Massive Multitask Language Understanding

CMMLU

57.4CMMLU Score

2

Page 2 of 2

Popular tasks

General Language Understanding Language Understanding Chinese Language Understanding Knowledge Multi-task Language Understanding

Follow for updates

Join SOTA2 Contact