Search

2 results for “benchmark transparency”

Technology 22 Sep 2026

UK AISI and EvalEval Release Reproducible Evaluation Results for Frontier Models

UK AISI and EvalEval published verified evaluation results for six frontier models across five benchmarks and two cyber evaluations. Results ship as Evaluation Cards with the settings needed to reproduce them.

Technology 06 Aug 2026

Meta Launches Muse Code, a Terminal AI Agent for Large Codebases Powered by Muse Spark 1.2 Follow-up

Meta has entered the AI coding agent arena with Muse Code, a terminal-based tool now in beta that targets professional developers working across large. Meta's entry reshapes the competitive dynamics of AI-assisted software development.