Comparison · under IB-CODE-2026.2
Claude Code vs Windsurf
| Claude Code | Windsurf | |
|---|---|---|
| Vendor | Anthropic | Cognition (formerly Codeium) |
| Pricing | Claude Pro $20/mo; Max $100/mo (5x) or $200/mo (20x); API at $3 / $15 per Mtok (Sonnet 4.6 in/out) | Free 25 credits/mo; Pro $15/mo (500 credits); Teams $30/user/mo |
| Default model | claude-sonnet-4-6 (Opus 4.6 on flagship tasks) | SWE-1.5 (Cognition proprietary, trained with Devin's engineering stack); Claude/GPT switchable |
| CLI surface | ✓ | — |
| Eval status | published · read | out of scope |
One side evaluated, one side pending
Claude Code has been evaluated under IB-CODE-2026.2: read the Claude Code evaluation →
The other side (Windsurf) is currently out of scope . When that eval lands, this page will update to a full head-to-head comparison.
About each tool
Claude Code
Claude Code is Anthropic's agentic coding CLI, GA as of early 2026. Ranked #1 most-loved in the Pragmatic Engineer dev survey (Feb 2026, 15K respondents). Default model is Sonnet 4.6 with Opus 4.6 routing on flagship tasks. The eval anchor for Indie Bench because it's the tool being operated to run …
Windsurf
Windsurf is the agentic IDE acquired by Cognition (the Devin team) in late 2025. The Cascade multi-step engine is genuinely strong — but it is IDE-only, with no standalone CLI or SDK as of May 2026. This puts Windsurf out of scope for IB-CODE-2026.2 (autonomous CLI/API evaluation). When the upcoming…