# Ai2 releases StateBench, a dataset for testing state tracking in models

> Original title: We’re releasing StateBench so researchers can test new models, extend our work, & build better state-tracking data.

- Source: Ai2
- Published: 2026-11-03T17:28:39.000Z
- Bad Influence: https://badinfluence.news/items/ll32i2af4qahgpmau9lmn6p4k
- Original: https://x.com/allen_ai/status/2117670302398197894

## Summary

Ai2 releases StateBench, a benchmark dataset for researchers to test new models and build better state-tracking training data. The dataset is available on Hugging Face at allenai/state-bench, with more detail in an Ai2 blog post.

## Post

We’re releasing StateBench so researchers can test new models, extend our work, & build better state-tracking data.

Explore more in our blog: https://allenai.org/blog/statebench
Download the dataset: https://huggingface.co/datasets/allenai/state-bench
