ANTHROPIC

Claude Sonnet 4.6 nears Opus on agentic work and computer use at half the cost. Benchmarks, adaptive thinking, model card findings and the 1M context beta.

Claude Opus 4.6 adds agent teams, a million-token context window, adaptive thinking and context compaction. The benchmarks and what changes for agentic coding.

Claude Cowork brings the Claude Code agent loop to non-coding work like decks and documents. What it is, which plans include it and what changed since launch.

Claude Opus 4.5 is the Anthropic model built for coding agents and computer use. Its pricing, benchmarks, token efficiency, effort parameter and agent features.

Claude Code is a terminal-based AI agent that writes code, runs commands and tests its own output. A 30-day review of its modes, task list and who it suits.

Anthropic's agentic coding CLI. Runs in your terminal, edits files autonomously, spawns sub-agents, and maintains memory across sessions. Defaults to Claude Opus 5.5 on paid plans as of October 2026.

Anthropic's SDK for building agents on the same tools, agent loop, and context management that power Claude Code. Python and TypeScript. Subagents, hooks, MCP, and permissions.

Anthropic's model family. As of October 2026: Opus 5.5 as the default, Fable 5.1 for the hardest long-horizon work, Sonnet 5.5 for speed, Haiku 5.5 for cost. 1M context. Max from $100/mo.