This is a test 2

Claude Sonnet 4.6 covers similar ground from Anthropic's side — improved computer use, stronger agent planning, and a 1M-token context window in beta. Anthropic also published their own Tool Search numbers: 85% reduction in token usage, and accuracy on MCP evaluations jumping from 49% to 74% for Opus 4. Two companies independently shipping the same capability with similar results is a good signal that the underlying idea is sound, not just one team's internal benchmark.