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

MMLU dataset and benchmarks – Page 32 · SOTA2 Research

Research Datasets

MMLU

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Error Recognition

MMLU-Pro

69.1Acc@1

4

Multiple-choice Question Answering

MMLU

91Pass@1

4

Multi-task Language Understanding

MMLU

33.52Throughput (TPS)

4

Multi-task Language Understanding

MMLU-Pro

45.75Throughput (TPS)

4

General Language Understanding

MMLU

21.23TPS

4

Multi-task Language Understanding

MMLU

38.01Tokens Per Second (TPS)

4

Multi-task Language Understanding

MMLU-pro

35.86TPS

4

Question Answering

MMLU

85EM Score

4

Drift Detection

MMLU

0Alarm Rate

4

Reasoning Consistency Evaluation

MMLU-Pro

52.9LAFF Score

4

General Language Understanding

MMLU

7.576Average Accepted Length (m)

4

Machine Unlearning

MMLU

3.1Refusal Rate

4

Malicious agent monitoring

MMLU

97.7Algebra Accuracy

4

Attacker Detection

MMLU

97Algebra Score

4

Massive Multitask Language Understanding

MMLU

2.39CPr-value

4

Multitask Language Understanding

MMLU

36.35MMLU Aggregate Score

4

Instruction Tuning

MMLU

74MMLU Score

4

Multi-task Language Understanding

MMLU

69.5MMLU Accuracy

4

Language Modeling

MMLU-Pro

191.3Tokens Per Second (TPS)

4

Language Modeling

MMLU

216.6Throughput (tok/s)

4

Robustness Evaluation

MMLU-Pro

0.781VAcc

4

Robustness Evaluation

MMLU

88VAcc

4

Language Understanding

MMLU

59.39MMLU Score

4

Question Answering

MMLU

65.27Accuracy

4

Uncertainty Quantification

MMLU OOD via Math Prompts

67.7AUROC

4

Page 32 of 40

Popular tasks

Language Understanding Multi-task Language Understanding Question Answering Multiple-choice Question Answering Multitask Language Understanding

Follow for updates

Join SOTA2 Contact