Posts

Cursor vs. Claude Code vs. GitHub Copilot: Which One's Actually Worth Paying For

Three tools keep coming up in every "what should I pay for" conversation among developers right now, and they're not really competing for the same job — which is exactly why so many teams end up paying for more than one. Tool Entry price Best fit Notable limit GitHub Copilot Free tier (50 agent/chat requests, 2,000 completions); Pro $10/mo Broadest editor support, cheapest way in Pro+ jumps to $39/mo for Opus-tier model access Cursor Free (Hobby); Pro $20/mo Deepest AI-native IDE experience Ultra tier hits $200/mo for heavy multi-model usage Claude Code Pro $17/mo; Max $100+/mo; pay-per-use API Autonomous, multi-step agentic tasks across terminal/IDE/Slack Cost scales fast on Max/API for heavy daily use The actual decision framework Solo developer, tight budget, wants AI help without changing how you work: start with Copilot's free tier, upgrade to the $10/mo Pro plan once you're relying on it daily. It's the cheapest entry poin...

Claude Sonnet 5's Price Cut Is the Real Story, Not the Benchmarks

Anthropic's Claude Sonnet 5 launched on June 30 with the kind of benchmark chart every model release ships with these days: 63.2% on SWE-bench Pro, up from Sonnet 4.6's 58.1%, closing in on flagship Opus 4.8's 69.2%. On Humanity's Last Exam, it hits 57.4% with tool use, essentially matching Opus 4.8's 57.9%. On GDPval-AA v2, a knowledge-work benchmark, Sonnet 5 actually edges past Opus 4.8, 1,618 to 1,615. Those numbers are real and worth noting. But they're not the interesting part. The interesting part is the price tag attached to them. Sonnet 5 is shipping at an introductory $2 per million input tokens and $10 per million output tokens through August 31, dropping to a standard $3/$15 after that. For a model landing within a few points of a frontier-tier system on agentic coding and reasoning benchmarks, that's a meaningfully different cost structure than what "near-frontier performance" has historically demanded. Why this matters more than th...