# StateBench tests how language models track state changes over long documents

> Original title: StateBench: Testing how language models track state changes over long documents

- Source: Hugging Face Blog
- Published: 2026-11-03T17:15:21.000Z
- Bad Influence: https://badinfluence.news/items/ra5wohiuy9pj2w61519vpbzhm
- Original: https://huggingface.co/blog/allenai/statebench

## Summary

Hugging Face introduces StateBench, a benchmark for long-context state tracking across four difficulty levels, from immutable assignment to assignment by reference. In its tests, recurrent and hybrid models generalize much farther than transformers when trained directly on these tasks. The report says frontier models including Gemini 3.8 Flash, Claude Opus 5.5, and GPT-6 Sol and Luna still break down on harder forms of state tracking as inputs grow longer.