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

STORIES dataset and benchmarks · SOTA2 Research

Research Datasets

STORIES

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Variable-length Language Modeling

Stories

21.07PPL

12

Language Modeling

Stories (test)

0.809Bits Per Byte

6

Sentence Infilling

STORIES (test)

45Performance Score

4

Language Model Inference

stories100m 110M parameters

298.7Tokens/s

3

Open-ended text generation evaluation (Discriminator Accuracy)

Stories

0.643Gen. PPL

1

Popular tasks

Language Modeling Sentence Infilling Open-ended text generation evaluation (Discriminator Accuracy)Language Model Inference Variable-length Language Modeling

Follow for updates

Join SOTA2 Contact