Topic
StateBench Benchmark
1 story tagged StateBench Benchmark, newest first.
Nov 3, 2026, 5:15 PMArtificial Intelligence
StateBench Finds GPT-6, Claude and Gemini Falter on Long State Tracking
StateBench finds recurrent and hybrid models outlast transformers on long state tracking, while frontier AI falls to 13% on the hardest tests as inputs grow.
DateSectionHeadlineSource