23.03.2026·00:05:26

Composer 2 Better Than Opus 4.6?

In this video we talk about Cursor’s Composer 2 launch and the spicy claim that it benchmarks better than Claude Opus 4.6 (but sits below GPT 5.4), why “performance” might really mean speed, and how price isn’t just per-token when models “think” longer and rack up hidden cost. We also react to Theo saying Cursor dropped a T3 “code clone” in alpha, breaking down what’s visible in the tiny UI: an Open Project view, a diff panel, and a rendered plan that feels like a simplified agent workflow (plus why that could keep someone from canceling their Cursor subscription). — TIMESTAMPS: 00:00 Composer 2 Drop 00:35 Cheaper Than Opus 01:07 What Is “Performance” 01:40 Token Cost Reality 02:30 T3 Code Clone 03:09 Open Project View 04:22 Diff And Plan View 04:56 Alpha Access 05:11 Show Plug — Unlock the full potential of your online presence with Kabarza and Samuel—experts in web design and development (respectively), powered by cutting-edge AI solutions. We blend creative design with advanced tech to deliver smart, high-impact websites that stand out. Ready to elevate your business? Contact us today and see what AI-driven innovation can do for you! LINKS & RESOURCES: Website: https://cmdaishow.com Check out Kabarza's amazing work: https://kabarza.com Visit Samuel's website for more: https://samuelgregory.co.uk 📷 Follow on Instagram: https://www.instagram.com/cmdaishow — HASHTAGS: #ai #podcast #aidesign #aidevelopment #vibecoding #webdesign #webdevelopment #ainews #webnews #designnews #devnews #Cursor #Composer2 #ClaudeOpus #GPT54 #AICoding

Transcript
So, composer two by cursor is out. It's available now and it's super cheap but also better than Claude Opus 4.6. Command AI Am I reading this right? So, on the cursor bench well, cursor bench and that's that that says a lot but it is their own benchmark but what they are claiming here is that composer is better than Opus 4.6 the high version but not as good as GPT 5.4. So, it's kind of like right in between but it's significantly it is significantly cheaper than anything out there also cheaper than combo composer 1.5. I haven't tested it but I feel like this is something that would work great even if it's not really as smart as Opus. I don't think it is. Well, this is this is telling me that it's smarter or sorry, performs Yeah. Well, this is telling me that it's smarter or sorry, performs better. What is performance? I don't know. But that's what this is telling me. Yeah, and for the cost it is I don't know. Is it like 40 30 cents here? Uh where Opus is 2.5 dollars. So, it is over what five times six times uh I think this is again it's a it's a graphic cuz it's like well, you've got input and output tokens. You've got um cashed uh price of tokens but you've also got the actual just general cost to run the the thing. You could have a really cheap model that thinks and thinks and thinks and thinks GPT 5.4 which ends up using a bunch of which ends up costing more. Whereas you've got a you've got very um capable model that's very expensive like Opus and it's actually really good at preserving tokens. So, it doesn't cost Do you know what I mean? Yeah. Unless it's speed unless performance is typically you say performance is speed. So, it's faster than Opus and cheaper. That could be it. But not as fast as 5.4 but then the cursor the composer first model was lightning fast. It was crazy. Yeah. Anyway, I don't know. That's what you get that's what you get from this craft. That's a good point. It might be about how faster it is. We have a second thing about cursor that is apparently in alpha and Theo is saying cursor just dropped a T3 uh code clone and this video looks pretty interesting even though everything in this video in the UI is super tiny. So, Jesus. We've seen this. We've seen this with the with the code and the diff on the right or whatever like some content on the right. In the middle you do the chatting and uh etc. What is interesting here is I can't zoom but it is this open project. Let me zoom like this. You see this icon open project. So, it seems like this is a view similar to uh the Codex app which I love by the way. Last week I managed to get it to basically 0% like I had 2% left of my weekly limit. It is You you you've taken that on as a challenge, haven't you? Yes, I did. I did. So, I I I wrote big PRDs and started like big projects. Mhm. I do wonder cuz I I'm I'm I've hit my limit a couple of times. Yeah. Yeah, but but I I I did quite a lot with it. Uh I rebuilt like an app a few times. Anyway, the point being I really really love this view at where I have multiple projects. I have, you know, multiple threads for each and it seems like this is what cursor is trying to do which I think it's um the right move and I might not cancel my subscription um at the end of the month. I don't know. Maybe. We'll see. But it looks really nice. They all kind of look the same. What Do you know what it's doing different? I guess it's got the diff which Codex doesn't have but they'll adopt it. No, it doesn't matter. Well, the Codex does have it. The Codex does show you the the diff. Okay. Yeah. Okay. Uh they do show it but here you you also see the the plan and this is like kind of um rendered. This is similar to how we use um Warp. I I love Warp. I'm using Warp uh a lot and yeah, this is a super simplified it is even a more simplified version of the agent view of cursor. It seems like. It's not out yet. It's alpha. I checked. I don't have access to this view. Um but I would love to get my hands on it. Yeah. This is part of a larger conversation on my show Command AI which we stream live every single week. We discuss the news and all things related to AI in the world of design and web. Catch us next week and join in the banter. Command AI