{"type":"post","id":"statebench-testing-how-language-models-track-state-changes-afffa2","slug":"statebench-testing-how-language-models-track-state-changes-afffa2","title":"StateBench: Testing how language models track state changes over long documents","description":"Ai2 has introduced StateBench, a benchmark that tests whether language models can track changing information across long sequences, from simple latest-value lookups to chained updates and dependencies.","retrieval_nugget":"Ai2 has introduced StateBench, a benchmark that tests whether language models can track changing information across long sequences, from simple latest-value lookups to chained updates and dependencies. Its results expose a gap between handling long input and reliably maintaining state, while showing that recurrent and hybrid architectures can generalize farther on tasks they are trained to solve directly.","published_at":"2026-11-03","updated_at":"2026-11-07","record_date":"2026-11-03","date_kind":"published_at","topics":["claude","gemini"],"entities":["Ai2","StateBench","Olmo 3","Olmo Hybrid","Gemini 3.8 Flash","Claude Opus 5.5","GPT-6 Sol","GPT-6 Luna"],"related_patterns":["scientific-agents-need-artifact-evidence"],"novelty_label":"new_fact","what_changed":"Introduces StateBench, a benchmark for long-document state tracking, and reports recurrent and hybrid models generalize farther than transformers on harder state-tracking tasks.","prior_refs":[],"source_url":"https://allenai.org/blog/statebench","source_urls":["https://allenai.org/blog/statebench"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:statebench-testing-how-language-models-track-state-changes-afffa2","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/statebench-testing-how-language-models-track-state-changes-afffa2/","markdown":"https://newruntime.com/posts/statebench-testing-how-language-models-track-state-changes-afffa2.md","json":"https://newruntime.com/posts/statebench-testing-how-language-models-track-state-changes-afffa2.json"},"markdown_url":"https://newruntime.com/posts/statebench-testing-how-language-models-track-state-changes-afffa2.md","next_reads":[{"type":"topic","path":"/topics/claude/","url":"https://newruntime.com/topics/claude/","title":"Claude","reason":"Explore the claude topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/claude.md","json_url":"https://newruntime.com/topics/claude.json"},{"type":"topic","path":"/topics/gemini/","url":"https://newruntime.com/topics/gemini/","title":"Gemini","reason":"Explore the gemini topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/gemini.md","json_url":"https://newruntime.com/topics/gemini.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}