2 models
Ranked by OSWorld 2.0
Reasoning Tools 81.8

Claude model for long-running agentic coding and knowledge work

anthropic/claude-opus-5-5 2026-09-22 1M context $4/M input $20/M output
35 providers
Reasoning Tools 70.6

Strongest Claude Opus model for coding, agents, and professional work

anthropic/claude-opus-5 2026-07-24 1M context $5/M input $25/M output
41 providers