Claude vs. Cursor: Which AI Built the Better App?
Краткое содержание
Pixel's announcement shares a head-to-head test of Claude Code and Cursor building the same Excuse Court mini app from one prompt. Claude finished in 4 minutes and 25 seconds with a 329-line HTML file, while Cursor produced 742 lines before its free-plan limit; the comparison also tests both judges on identical excuses.
DEV Community
I made Claude and Cursor build the same app. Then I put them on trial.
Cursor built my app, then told me I'd used up my free plan. Claude built the same app in four and a half minutes, then told me it had tested it on a phone. One of them was telling the truth. This week is MLH Global Hack Week, and one of the challenges was "Build a Mini App with Cursor." So I built Excuse Court: you type your excuse, a cartoon judge bangs a gavel, and you get a verdict, a sentence and a believability score out of 100. Then I asked Claude Code to build it from the exact same prompt. Head to head. The race Cursor (free plan) Claude Code Prompt the challenge app the exact same prompt Result one HTML file, 742 lines one HTML file, 329 lines Time it finished, then my free usage ran out 4 min 25 s from my message to the link Claude's own guess at its time "about 7 minutes" Ready for round two? no, usage limit hit yes Yes, Claude overestimated its own time. That is the most humble thing an AI has ever done to me. Meet the judges Cursor gave me The Honorable June Burden. "She has heard worse. Not often." She is scowling before you've typed a word, and she never stops. Claude gave me Judge Dubious, in a powdered wig. His eyebrows go up when you're acquitted and crash down when you're guilty. He also gives you five excuses to tap if you can't think of one, which is the most useful legal advice I've ever received. Same excuse, two judges I typed the same four excuses into both courts. These are the real verdicts and scores. Excuse Cursor's judge Claude's judge My dog ate my homework GUILTY, 10/100: "There are tooth marks on nothing. The dog walks. You do not." GUILTY, 1/100: "Your dog has been subpoenaed. He pleaded the fifth, then ate the subpoena." The AI said it was fixed GUILTY, 23/100: "entered as Exhibit Vague, and the exhibit is sweating" GUILTY, 17/100: "The AI has filed a counter-suit, its lawyer is also an AI, and it billed 900 hours overnight." I was late because of traffic GUILTY, 16/100: "It was a Honda Civic and a calendar you treated as fan fiction." GUILTY, 30/100: "You were not stuck in traffic. You ARE traffic." A raccoon stole my car keys, I swear ACQUITTED, 56/100 ACQUITTED, 15/100 (see below) Honestly? Cursor's lines are longer and weirder, and some are better. "Sentence: leave fifteen minutes earlier, which is not cruel, it is a clock" is a perfect sentence. Claude's are shorter and punchier, and Claude explains your score: say "I swear" and you lose 12 points, because "nobody innocent says that." The raccoon incident Here's the part I didn't expect. I told both judges a raccoon stole my car keys. Cursor's judge: "You lost an argument to a raccoon and I have no follow-up questions. That is precedent." Claude's judge issued a warrant for the animal and then said: "The court has met a goose and fears it too." It was a raccoon. Claude wrote one line for every animal and named the goose in it, so the raccoon gets accused of being a goose. It gets better. Claude's judge acquitted me with a believability score of 15 out of 100. Not guilty, but also, nobody believes you. And on a phone-sized screen, the big green ACQUITTED stamp runs straight off the edge of the card. Remember how Claude said it had tested the app at phone width "with no errors"? Technically, a stamp falling off the page is not an error. Also, Claude gave the dog excuse 1 out of 100 and docked me 10 points for blaming "3 different things at once." The three things: the dog, the homework, and the word "ate," which Claude files under snacks. The scorecard Cursor Claude Topics it has a joke for 40 36 Catch-all lines when nothing matches 4 4 Gavel sound and screen shake yes yes Tap-to-try example excuses none 5 Judge's face reacts to the verdict no yes Explains your score no yes Accuses a raccoon of being a goose no yes Usage left for a rematch no yes These counts come straight from the two files, so you can check them. The verdict When Claude finished, I looked at both and told it "you win." Mostly because it finished fast, the judge's fac...

Powered by Readybot.io