AI Dynamics

Global AI News Aggregator

About

Anthropic Reveals Claude Mythos Benchmarks

BREAKING : ANTHROPIC ANNOUNCED CYBERSECURITY PROJECT GLASSWING AND MYTHOS BENCHMARKS! Claude Mythos scored 93.9% on SWE Bench Verified and 87.3 on SWE Bench Multilingual! “We do not plan to make Claude Mythos Preview generally available, but our eventual goal is to enable

→ View original post on X — @testingcatalog