--- title: "The Pulse: Interesting AI coding stats from Cursor" url: https://daily.dev/posts/the-pulse-interesting-ai-coding-stats-from-cursor-1yvl6aii3 source_url: https://blog.pragmaticengineer.com/the-pulse-interesting-ai-coding-stats-from-cursor type: article source: "The Pragmatic Engineer" published: 2026-07-09T17:25:33.834Z updated: 2026-07-09T18:07:59.522Z tags: ["ai-coding"] reading_time: 6 upvotes: 0 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # The Pulse: Interesting AI coding stats from Cursor **[The Pragmatic Engineer](https://daily.dev/sources/pragmaticengineer)** · 6 min read · 0 upvotes · 0 comments ## Summary Cursor released a report based on two years of aggregated usage data revealing several notable findings. Power users (p90) generate ~9,000 lines of code per week versus the median of ~700, while the top 1% produce 30-40K lines weekly. Token usage is dominated 10:1 by input over output tokens, mirroring the classic read-to-write ratio in software development. Smart context caching reduces effective token costs dramatically — without it, costs would be 10x higher. Opus 4.7 is nearly 10x more expensive per agent request than Cursor's own Composer model, though cost-per-line-accepted narrows that gap. Most strikingly, the share of developers accepting AI-generated commits without manual review jumped from 10% to ~40% in a single month, coinciding with the release of Opus 4.7 and GPT-5.5. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: --- Tags: [#ai-coding](https://daily.dev/tags/ai-coding) [View this post on daily.dev](https://daily.dev/posts/the-pulse-interesting-ai-coding-stats-from-cursor-1yvl6aii3)