Comparison · under IB-CODE-2026.2
Claude Code vs Cursor
| Claude Code | Cursor | |
|---|---|---|
| Vendor | Anthropic | Anysphere |
| Pricing | Claude Pro $20/mo; Max $100/mo (5x) or $200/mo (20x); API at $3 / $15 per Mtok (Sonnet 4.6 in/out) | Pro $20/mo + token-based SDK usage |
| Default model | claude-sonnet-4-6 (Opus 4.6 on flagship tasks) | Composer 2 (proprietary) — switchable to Opus 4.7, GPT-5.5, Gemini 3.5 Pro |
| CLI surface | ✓ | ✓ |
| Eval status | published · read | queued |
One side evaluated, one side pending
Claude Code has been evaluated under IB-CODE-2026.2: read the Claude Code evaluation →
The other side (Cursor) is currently queued . 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 …
Cursor
Cursor is the IDE-first agentic coding tool with $2B ARR by Feb 2026 (fastest B2B SaaS scaling on record). The Cursor SDK released April 29 2026 exposes the agent harness programmatically for the first time — codebase indexing, semantic search, subagent spawning, hooks, MCP. Evaluations under IB-COD…