Best models for Claude Code
Claude Code is tuned for the Claude family, but it's worth knowing where each model lands on capability and cost for your workload.
The ranking
Updated July 2026
#ModelContextInput
- 11Claude Sonnet 5AnthropicThe default for most Claude Code work, with strong agentic performance and lower pricing.Context1MInput$2/M
- 22Claude Opus 4.8AnthropicUse for harder agentic coding and enterprise work when capability matters more than cost.Context1MInput$5/M
- 33Claude Haiku 4.5AnthropicGreat for fast sub-agents and high-volume, low-stakes steps.Context200KInput$1/M
Intelligence vs. price
Each model's Artificial Analysis Intelligence Index score against its blended price per 1M tokens. Toward the top right is more intelligence per dollar.
Full interactive leaderboard on our Intelligence Index page.
Details:
Agent
Claude Code
Models
3Updated
July 2026