Deploy your site using here.now completely for free, copy the prompt for your agent here! https://here.now/r/twt I accidentally discovered Cursor's new Composer 2.5 model mid-project — and it was completing tasks 3–4x faster than Opus 4.7 with results that were just as good, if not better. I had no idea it had even switched. So I ran a proper head-to-head test: Composer 2.5 vs Opus 4.7 vs GPT 5.5 — all given the exact same prompt inside Cursor. The results surprised me. Want to make real money with coding? I share high-signal insights on careers, monetization, and leverage in my free newsletter. Join here and get my guide How to Make Money With Coding instantly: https://techwithtim.net/newsletter 🚀 Tools I Use Get 10% off with code techwithtim Openclaw setup: https://www.hostinger.com/techwithtim VPS setup: https://www.hostinger.com/techwithtim10 Wispr Flow (Best AI Dictation): https://ref.wisprflow.ai/techwithtim ⏳ Timestamps ⏳ 00:00 | My Experience with Composer 01:10 | What is Composer 2.5 02:28 | Composer 2.5 Benchmarks & Stats 04:30 | Understanding Agent Harnesses 08:36 | Here.now 10:35 | Live Demo - Composer vs Opus 4.7 16:27 | Live Demo - Composer vs GPT 5.5 Hashtags #CursorAI #AIComposer #CodingAgent UAE Media License Number: 3635141
ADVERTISEMENT
BTW ,Thanks for the free python courses,they were too helpful.
I love composer and have been using it more. Been doing this for months - Use higher end model to discuss / plan. Use Composer 2 or 2.5 now to find and suggest code changes if they weren't directly called out in the plan, then ..... implement the code changes myself. Yes, even if I'm copy/pasting. For a while I got caught in the trap of just depending too much on the AI and I got really burned out and didn't understand what was going on. This method lets me better understand, feel more productive, and is cheaper because I'm not using high end models for everything
Spend less time advertising/theory/useless benchmarks Spend more time SHOWING US same task done by Opus VS Composer.
sponsored by cursor?
How high was the usage for the projects in the end?
another tech tuber bites the dust seems like he sold himself to AI
Harness doing the heavy lifting. Fits the pattern - diminishing returns on scale, real gains from orchestration and context management. We've been oversold on parameter count as a proxy for capability.
The Plan > Build > Run in Parallel on Cursor is epic for me. Gotta hit that dropdown arrow on 'Build' button, that's the only trick, rest is default and yeah, awesome. I even get it to make plans around having the subagents in parallel now.
Composer 2.5's been great, mainly tried out as the token usage via Opus 4.8 was just not manageable.
What about Composer vs 5.5 ?
be honest, is this a sponsored video by cursor ?
how much cursor paid for ad video?
Great point about harness, but it would be also nice to actually see Opus in Claude Code vs Opus in Cursor (or GPT in Codex vs Cursor)
Cursor just crushed Claude Code? Not bad for a Claude fork
How would you compare antigravity’s IDE w cursors IDE in terms of running Claude/codex extensions?
i tried your prompt with opus 4.8, on high effort. it took 18 min (but it asked clarification questions first to confirm it builds what i want).. after 18 min, drawing shapes didn't work same as your demo. i told it drawing shapes doesn't work, it took 5 mins to fix, then it worked.. typing still doesnt work.. so yeah i see your point that composer 2.5 is faster.. will give it a shot
I always wondered why the same model acted differently in different tools. Does the Composer harness work well with bigger codebases or mostly fresh projects I have been looking at Llamapress ai since they have a free plan and I keep hearing good things. How does Cursor compare to something like llamapress
what about opus 4.8 in vs code or terminal ?
can composer only be accessed inside of cursor? i’m already using VS code and pretty comfortable using that and many of my things are working properly. Is there a way I can integrate composer into VS code?
I've been using cursor pro for 2 weeks, then pro+ for 1 week so far. Damn, it's great, Opus, Sonnet, Gemini, work perfect and Composer does a really good job too. Token usage is crazy tho