verified
Verdict
Cursor leads
Cursor leads the overall Airecmark score 89.2 vs 86.1 (+3.1 pts). Cursor scores higher on Features, Usability, Performance; Claude Code leads on Quality, Value. Five-dimension deterministic composition, as of 2026-09-06.
Overall Airecmark Score
Five-Dimension Breakdown · v2-5dim
Dimension-by-Dimension
Quality
93 · 94
Cursor
93
Claude Code
94
Features
92 · 88
Cursor
92
Claude Code
88
Usability
90 · 75
Cursor
90
Claude Code
75
Performance
88 · 85
Cursor
88
Claude Code
85
Value
82 · 84
Cursor
82
Claude Code
84
Overall = 0.25·Quality + 0.20·Features + 0.15·Usability + 0.20·Performance + 0.20·Value — Methodology
Pricing & Plans
Claude Code
In Claude Pro ($17–20 / mo) · Max from $100 · API optional
Model: subscription
Source: Claude Pricing · checked 2026-09-06
Strengths & Watch-outs
smart_toyCursor
Strengths
- check_circleComposer multi-file agentic refactoring
- check_circleFine-grained symbol indexing
- check_circleVS Code-native interaction, low migration cost
Watch-outs
- error_outlineHard VS Code fork — some vendor lock-in
- error_outlineHeavy Agent usage requires higher tiers
smart_toyClaude Code
Strengths
- check_circleHeadless refactors and CI/test fixes, fully scriptable
- check_circleTerminal-native workflow with deep git/MCP integration
- check_circleUnderlying model has a public, traceable SWE-bench self-report
Watch-outs
- error_outlineNo GUI — terminal only
- error_outlineAPI/subscription costs add up under heavy use
Both scores are deterministic compositions of the same five dimensions — no manual overrides, no undisclosed weights. See how we score.