news
Hugging Face
November 3rd, 2026 at 5:15 PMStateBench: Testing how language models track state changes over long documents
Get stories like this every Monday
The week's most important AI news in one email. Free, unsubscribe anytime.
Score: 2.45
Engagement proxy: 0
Canonical link: https://huggingface.co/blog/allenai/statebench