Claude Opus 5 DESTROYS Fable 5

0:00 Claude Opus 5 has dropped. It has happened and it has totally blown my mind. It is better than Claude Fable 5. It is a fraction of the price. It is significantly faster, but it has three insane weaknesses I'm about to go over that change absolutely everything. But before we get into those three deal breakers with Claude Opus 5, let's talk about the incredible things that are like legitimately revolutionary. First of all, it beats Fable 5 on almost every single benchmark. This is not one of those channels where we look at charts and benchmarks all day. Totally boring.

0:33 No, I'm just letting you know right now it beats Fable 5 on every benchmark and in a second I'm going to take you through a world-famous new revolutionary benchmark I've been working on for weeks now that proves it's better than Fable 5 in almost every single way. It is half the price. So this was the biggest issue with Fable 5. It was totally uneconomical for the average user, but Opus 5 it's half the price. It comes in at a good price and you get your full limitations with your Claude plan.

1:03 Meaning you can use it to 100%. Claude Fable 5 for some reason won't let you use half your limitations, which is really stupid and annoying. It's significantly faster. It works lightning quick, much better than Fable. Which brings us to the question and I'll and I'll show you my benchmarks in 1 second here. Any reason to use Fable 5 anymore? No, with one small exception which I'll go through right after these benchmarks I'm about to show you. But no, there isn't a reason. And then as I said, there's three major weaknesses which we'll go over as well. Let's go into these world-famous Finn benchmarks I just created to show you why this is better than Fable 5. All right, so this is the new famous Finn benchmark. There are five tests here we put both Fable 5 and Opus 5 through. In a second I'm going to show you Opus 5 versus GPT 56 so we can know which one of those two is better. And Opus 5 won basically all of the benchmarks. So, starting with benchmark number one, this was a 3D roller coaster simulator. Both had to build a 3D roller coaster simulator.

2:06 Let's show you Opus 5 first. This was Opus 5, an absolutely beautiful simulation. It built the entire track, all the trees, the building route, the sky, the clouds. And if I hit ride, you can actually see the roller coaster in real time. You can see the from the user's perspective going around the roller coaster. This is really, really nice, detailed, beautiful, and was done lightning quick. As you can also see, it was done with 82 cents of credits and about 32,000 tokens. We go over to Fable 5. It was actually done with less tokens, but was significantly more expensive, about 50% more expensive.

2:45 Let's see the output of it. And as you can see, it's just not quite as beautiful, not quite as detailed or clear. It looks like just kind of like a generation behind. If we go on the ride, you can see the track doesn't look quite right. The trees all kind of look similar. There was no real detail to anything, so it doesn't look nearly as good. The next test is the pixel perfect test where it has to clone an entire website. It has to clone the Apple website. If we go to the actual Apple website, this is what it was tasked with cloning. You can see college sorted. It has a bunch of people holding Apple devices, iPhones, MacBook Airs, MacBook Pros. Now to Opus 5's recreation, obviously, it doesn't look incredible, but I'll show you Fable in a second. But you can see it's pretty close. It had to build every part of this website from scratch. It's not copying and pasting over images. It's building what a MacBook looks like from scratch. What a MacBook Pro, an iPad, a watch would look like. As you can see, it has names, recreates a TV. Let's see what this looks like with Fable. Fable 5, not quite the same. Remember this looked like human beings on the real website and in the Opus 5 website, the iPhones cut off, the MacBook looks nothing like a MacBook Air, the iPad looks nothing like iPads, the watch doesn't look anything like a watch. The cards kind of lazily done. As you can see, nothing looks quite the same. Opus 5, everything looked much better. Does it look perfect? No, but looks much better than Fable. The next test was the gauntlet test. And basically, this is a agentic test where it tests the tool use of the model. We give the model a whole bunch of documents, PDFs, Excel spreadsheets, a whole bunch of things, and have it basically do a scavenger hunt where it goes and has to find specific things in all the documents. It tests its agentic ability. Opus 5, it did a pretty good job. It got five out of the eight scavenger hunt items. Fable 5 cut off halfway through because of content blockage from Anthropic. It thought I was doing something with cybersecurity.

4:49 It cut it off. This has nothing to do with cybersecurity. It's about finding specific things in different documents. Fable 5 wouldn't allow me to do the agentic test, so that didn't count. There's a debug wall. So basically, what this benchmark does is go online and find like 15 different bugs from open-source GitHub repos. And then it hands it to each model and says, "Hey, go through this and fix all the bugs in all these open-source repos." Opus actually took a bit longer than Fable 5.

5:18 Did it at about the same amount of tokens, but did it at about a dollar cheaper overall. So about 25% cheaper. So this goes to Opus 5 as well. And then the last test is breaking point. And basically, the way this works is each model is tasked with building a bridge. It's basically a bridge simulator. They're tasked with building a bridge, and then the benchmark drives a car over the bridge over and over and over and over see how much weight the bridge can hold. It's basically testing the thinking ability. Okay, can you design a bridge that holds tons and tons of weight? Fable cost basically double Opus to do this, but only was able to hold slightly more weight than Opus. So, it goes to Fable, but it was a lot more expensive. Overall, Opus 5 beat Fable beat him in almost every single benchmark, did it for significantly cheaper. Total cost was $6 for Opus, $7.50 for Fable 5. And it's the winner.

6:15 Opus beats Fable for a fraction of the price. So, let's talk about the weaknesses of the model. There are a few deal breakers for me here that are stopping me from using this in my entire stack. Number one, the personality sucks. It absolutely sucks. I've never been so annoyed talking to a Claude model. This has actually been the advantage of Claude models up to this point. I've always loved talking to Claude models. It's been their biggest advantage against ChatGPT, but for the first time it has flipped. I loathe the personality of Opus 5. It is way too verbose. It is not nearly concise enough. It goes in a hundred different directions when it's talking to you. You ever have like that friend from high school who thinks he's just like way better than everyone else and way smarter than everyone else? And when you talk to them, they use like the biggest words possible and go in a million different directions to prove how smart they are? That's what it feels like with Opus 5. I've had to multiple times using Opus 5 hit the stop button to get it to shut up and I say "Please be way more simple and concise and talk to me like I'm 5 years old." I'm not kidding. For the first time I've had to go to Claude.md to edit its personality. I just said, "Speak as simple as humanly possible." And I highly recommend when you use this model you do the same thing. It's unfortunate cuz it also kind of leaks into the way it works sometimes, where I'll be like, "Fix this bug." And it'll just do a hundred other things before fixing the bug, which is really, really annoying. It It appears like it's just this like erratic, super hyper intelligent being that can't stay focused. For me, Fable 5 was actually way more focused. And I actually enjoyed talking to Fable 5 more. The issue is Fable 5, you can only use 50% of your budget on it, and it uses up all your credits. So, I have to replace Fable 5 with Opus. So, highly recommend editing your personality for Opus 5. It's just It's just too much and it does too much.

8:09 The limits suck. Even though you can use 100% of your budget on Opus 5, the Claude limits just absolutely suck compared to ChatGPT. ChatGPT, that that Tibo dude from Twitter is constantly restarting the limits like every 5 minutes. You basically get unlimited usage with ChatGPT. Claude, even though you can use all your budget on Opus 5, it still has lower budgets overall Anthropic versus ChatGPT. I can still see the meter going quicker, which gives me like a level of anxiety as I'm giving prompts. It makes me want to do less.

8:43 Because ChatGPT has unlimited usage basically, there's no anxiety when using I I'm more free to be creative and explore and do more things and do interesting things. So, I you know, the limits still here are a deal breaker for me. And then the harness for Claude code is still just not as good as Codex or I guess it's the ChatGPT app now. The ChatGPT app is a significantly better harness. Their new voice mode, which video on that coming in like the next 24 hours, maybe 48 hours, turn on notifications now and subscribe, especially if this video has been helpful for you. Video on that coming very soon, but it is incredible.

9:20 It is excellent. Claude just added a voice mode, but it's not nearly even like a quarter of what the ChatGPT voice mode is. That's coming soon again, notifications on. Also, by the way, I'm doing a boot camp on Opus 5 in an hour from me filming this. It's going to be recorded. It'll be in the Vibe Coding Academy. Link for that down below. Number one AI community on planet Earth. Join that link down below. I promise it'll be the best decision you ever make. Now, here is my new stack. With all that being said, here is my new stack for super hard problems, Opus 5.

9:51 It's the smartest model out there. It has the highest intelligence. It's smarter than Fable 5. Fable 5 was slightly smarter than 5.6. Opus 5 is slightly smarter than Fable 5. If I'm doing massive planning, I'm still relying on Fable 5, mostly because I just don't like the output of Opus from like a talking perspective. So, if I need talking, if I need a plan, if I need to go back and forth, if I need a brainstorm, I'd rather do with Fable 5.

10:15 I don't want to talk to Opus 5 to do planning. I just want to shut up and write code. Daily driver though, that's ChatGPT 5.6. You get so much higher limits. The voice mode is incredible. Again, video coming soon. It is just better to use overall out of the three. So, daily driver, ChatGPT 5.6 it is. Have you used Opus 5? How's it compare to Fable 5 for you? Let me know down below in the comments section. Hope this was helpful. Way more videos coming out on Opus 5, Claude Code, GPT voice mode, Hermes agent, Opus 5 and Hermes agent, all coming very soon. Make sure to subscribe. Leave a like if you learned anything at all. I'll see you in the next video.