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 June 2026
#ModelContextInput
- 11Claude Opus 4.8AnthropicThe default flagship, with the best end-to-end coding results.Context1MInput$5/M
- 22Claude Sonnet 4.6AnthropicUse for most work; switch to Opus for the hardest tasks.Context1MInput$3/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
June 2026