Anthropic · Claude 5.5
Opus 5.5
Frontier agentic coding that finishes the job.
What it is
Opus 5.5 opens the Claude 5.5 family and leads on agentic coding, computer use and knowledge work. It plans, writes and runs code, drives a browser and tools, checks its own work, and holds the thread across long, multi-step runs.
That reliability over a whole task is what a Skill needs: read SKILL.md, gather the inputs, produce the deliverable, verify it, and hand back something that survives a review. It is the model to pick when the work is long rather than merely hard.
Profiles describe the model, not a guarantee: the Skill folder is what makes the work repeatable, and the agent's settings decide what the model can reach.
What it's best at
The work this engine is built for, and where it earns its place in a run.
Agentic coding
Writes, runs and debugs across a full codebase, including migrations and audits that span many files.
Long, multi-step work
Stays on task through long runs without losing the thread partway, which is where earlier models stalled.
Knowledge work
Research, analysis and professional deliverables that hold up to a second reader.
Computer use
Operates a browser and tools to complete real, multi-step workflows on its own.
A good first run
Three web Skills to try on Opus 5.5 — each one a folder of instructions the model can pick up straight away.
Other models
The rest of the engine room.
OpenAI · GPT-6
GPT-6 Astra
OpenAI's frontier model for end-to-end agentic work, reasoning across a task rather than a single turn.
- Context
- ≈1M tokens
- Best at
- End-to-end work
Anthropic · Claude Fable 5.1
Fable 5.1
Anthropic's top model for demanding reasoning and long-horizon agentic work, with adaptive thinking.
- Context
- 1M tokens
- Best at
- Demanding reasoning
Anthropic · Claude Opus 5
Opus 5
Anthropic's Opus-tier flagship: near-frontier intelligence for complex coding and enterprise work.
- Context
- 1M tokens
- Best at
- Complex coding
Ready to extend your agent?
Connect once, then install any Skill from our studio straight from your agent.
