benchmark
Wenge AI subsidiary unveils four AI products in Hong Kong
D2 Intelligence, a subsidiary of Wenge AI, has unveiled four AI products for different use cases at Hong Kong FinTech Week 2026. The solutions span decision support and…
LangChain says the right browser tool can cut costs fourfold
LangChain compared seven browser-control tools for autonomous agents and chose Browserbase's Stagehand solution. The company says code-based operation, compact page…
StateBench to examine state changes in long documents
The StateBench initiative tests how language models track state changes in long documents. The post was published on Hugging Face.
Safety and ethicsCogent’s VR-1.1 model fixed 57.9% of vulnerabilities
Cogent Security has released VR-1.1, a cybersecurity reasoning model that produced working fixes for 57.9% of the public LiveCVEBench test, according to the company’s…
Google sets a new benchmark for testing what AI engineers can do
Google has introduced a new benchmark and open competition called Physical-Engineering's Last Exam, which tests whether AI agents can complete complex mechanical…