China’s Qwen 3.8 VS Fable 5!

Kuen 3.8 vs GPT 5.6 Sol vs Fable 5 vs Kimi K3 who wins? We've got 23 different builds to test out side-by-side today. I'll be walking through exactly how this performs. This is based on Kuen 3.8's post yesterday so they were talking about launching and going open way soon.

Massive 2.4 trillion parameter model and also this is according to them one of the most powerful AI models available today compatible to leading frontier AI models second only to Fable 5. And so far from what I've seen on the tests and you'll see some examples right here is looking really good like I mean for example if we have a look at this look at this flight simulator and the quality and the details and also the gameplay and how smooth it is like on this flight simulator we've got for example GPT 5.6 Sol over here which is not too bad this is a pretty cool game to play. I think Kimi K3 actually totally failed on this task and then Fable 5 really got stuck on the details here like it just didn't create anything as nice. However would I say that it's as good as Fable 5?

Would I prefer to use it? I'm gonna come on to that later but let's go through the builds first. So first of all we've got this game called Outrun as you can see right here it's really fun on the top left from Quen 3.8 if we have a look for example at Fable 5, GPT 5.6, even Kimi K3 they're all pretty decent I would say GPT 5.6 Sol probably came out worst right there. Fable 5 is literally my favorite model as of today and we'll come on to this final verdict in a minute and it can create some pretty nice stuff however what I will say is that Quen 3.8 by far created the best output.

It looks the nicest, most fun, most interesting. Let's move on to the Skyrim example here. So we've got the version from GPT 5.6 I would probably say that is the weakest out of all the generations here. You can see for example if we scroll through this world even the controls are weird so when I try to go forwards that actually takes me backwards.

Doesn't make sense. If we have a look at Fable 5, Fable 5 really nice like the quality, how smooth it is, how interesting it is to play, even the little details like the compass at the top, super nice. If we have a look at Kimi K3 I mean for me personally I would say Kimi K3 is probably second only to Fable 5 when you look at this example and then we can have a look at the example from the Skyrim game for Quen 3.8. I mean the gameplay is crazy like the gameplay is crazy.

The graphics not quite as nice, the details not quite as nice but is it a fun game to play? Is it pretty cool? I mean do the graphics look great? Absolutely, absolutely.

We can go full screen on any of these. By the way if you want to check out yourself it's all available at Goldy and also if you want training on Fable 5, GPT 5.6 or Quen or even Kimi K3 we have master classes on all of them inside the AIPUF. This is my best community for AI automation and also inside the community you can ask questions. I personally answer every single one every single day.

Inside the classroom you get access to all my best trainings, you can join my weekly coaching calls and you get all my best trainings on the models we're covering today. So let's get straight back into it. If we have a look here yeah yeah I mean Quen, I'm not gonna lie here like a lot of people say oh you know Quen 3.8 is not quite as good or it got cooked by Fable 5. From my tests I will say that it takes a bit of back and forth to get outputs like this but from my tests it holds its own.

That's what I would say. Would I say it's as good as Fable 5? Do I prefer it? No.

But does it hold its own? Is it still really good quality stuff? Can it build really amazing stuff? Absolutely and I was actually testing it through Q-Oda, so Coda, which is pretty cool.

I couldn't get the international API to work so I had to go through Coda and also the other thing that I found was that when you are trying to access Quen.com depending on where you are it's regional so I couldn't access it where I was based in the UK. If we have a look here at the quality of the output so GPT 5.6 Sol comes in second I would say on all these outputs. Fable 5 is coming in last and then we've got for example the output from KimiK3 which is just as strong as GPT 5.6 but I mean Quen 3.8's creativity here the 3d models everything about this game is super fun so a lot of these games like it is winning is leading the way I mean these are really cool examples. It creates something that's smooth I always notice with Quen 3.8 it just feels smooth when you're using it so there's no problems with the controls there's no problems with the navigation the UI is never quite as good in terms of like feeling the vibe or the ambience I don't know how to explain it but like I'm not a UI expert but I will say that I just generally prefer Fable 5 when it comes to UI.

Here's another example this was a racer game here and actually on this one the controls are really bad it seems to be really difficult to move forward or backwards and that sort of thing if we have a look for example these are all kind of linear games whereas this one is a bit less linear then we've got the RPG style game here and this was super nice as well so if we have a look at this example from Quen 3.8 Max I do think the camera angle could be nice so it could be easier to use on camera angle but actually the game is nice like it's 3d and again like the controls are just a little bit strange here like you don't seem to have to go back and forward so much if we have a look for example at GPT 5.6 Soul I would say that is probably one of the better outputs here nice camera angle easy to use controls work perfectly there if we have a look at Kimi K 3 pretty nice yeah I would say that's a nice game and then if we look at Fable 5 pretty good as well so I'd actually say like the graphics are the nicest on the Quen 3.8 example but the controls are the worst the gameplay is worse if that makes sense especially the camera too. Then we've got the flight simulator here so it should be W or S for the throttle but it doesn't seem to quite work and you can use the arrows here but it doesn't seem to take off or anything so we can't really get lift off if that makes sense on that one. If we have a look at GPT 5.6 Soul it's okay there's a lack of detail there I would say Fable 5 created the nicest thing out of all of them and then Kimi K 3 not bad but just a little bit buggy as you can see when you're moving around the landscapes. Then we've got this GTA style game here and actually if we have a look at this like wow the quality from Quen 3.8 the detail how fun it is to play it absolutely crushes tests like a lot of fun really really nice actually awesome to be fair.

If we have a look at Fable 5 not quite as much detail not as fun. Kimi K 3 I'm not sure what it's doing here but it didn't actually create a car and the same for example for GPT 5.6 Soul actually it did but you have to enter the car as you can see here. Let's see if we can get away it seems super it's either a very difficult game or it doesn't work. Let's try again that is a hard one to play.

Now we've got Dragon Realm so this is like another kind of Skyrim style game it's a weird one here where the it just feels robotic when you play the Quen 3.8 example. Kimi K 3 absolutely crushed this example I mean like it looks nice it feels good the ambience is nice the UI and the design is good I can see why Kimi K 3 won the coding front-end benchmarks but I would say Quen 3.8 came up with the worst example maybe GPT 5.6 as well it's a bit blocky when you test it out. Let's have a look at Fable 5. Yeah it's smooth it's nice it's not quite as nice as Kimi K 3 but it's decent.

This one similar sort of style where it's quite blocky in the way that it's been designed. GPT 5.6 creates some really nice colors and design and everything else I like that first-person style. Fable 5 did something weird here so if you look at the style like the 3d game and this is Fable 5 by the way it is very it feels very linear and then the graphics are pretty bad and then if we have a look at Kimi K 3 it's much more smoother but there's no there's nothing to really interact with inside the game but I guess you could build that in quite quickly if you wanted to to change it out. The graphics aren't nice though.

Then we've got a Doom style game here and this is where it gets weird so Quen 3.8 like the gameplay is actually super nice on this. It's quite fun it's engaging it's entertaining however when you look at this example you see how the lighting is really really bad like very difficult to see anything there. That's something that confused me otherwise it would have been really good. Let's have a look at Fable.

It's more basic but it's more enjoyable to play for sure. Then we've got which actually probably created the most fun game even though the graphics are not quite as nice and then GPT 5.6 which is very similar to Fable 5 in the style that and the way that it's been done. Dragonflight was something that was super interesting with Quen 3.8 max like look how much nicer Dragonflight is on Quen 3.8 versus everything else like the colors the design the gameplay again it's holding its own in that example. If we look at the rest of the examples across all the games here I would say Kimi K 3 probably came in second.

Like nice speed of the game more fun more interesting and the other two didn't really create something nice here. I would never play this one from Fable 5 and GPT 5.6 as well not that great. So Quen came out third there. This was like a Nordic crypt game which is pretty fun to play graphics are nice colors are good.

Fable 5 create something nice there but look at the look and feel of the Kimi K 3 one. I would say that one feels like the nicest to me out of everything and then if we look at GPT 5.6 I think they all did a pretty decent job there to be fair. Now this was one that actually impressed me here so this is this is actually Quen 3.8 that probably won this one again. So you can see it's kind of a mixed bag where it can create some awesome stuff.

Fable 5 really struggled with colors there. Kimi K 3 probably came in second and then the one from GPT 5.6 it's really bad really really bad doesn't make any sense. This one was super nice the the flying game from Quen 3.8 and you see some others here. You might also be wondering okay what is everyone else's experience because I don't want to just show you mine I also don't want you to just believe me when I say it's good and it can create nice stuff I mean test it for yourself see what you think.

Me the reason I created GoldieBench was just to test it out. I ran it across 23 different tests. We'll run it across 50 once it's completed it's just running the background it will take about a full day to run every single test but so far from what I've seen it is an impressive model. Yeah would I say it's better than Fable 5?

No. Would I say it's on par with Kimi K 3? Not quite. Would I say it's better than GPT 5.6?

So I think it's just kind of up there probably they're all right up there but Fable 5 is still my favorite and then I think Kimi K 3 is probably second to that but you'll see some people who are posting on X and they've compared it side-by-side and they didn't like it at all so for example like Omed the vibe coder he posted about it and he actually said that Quen was nowhere near the same level so you will see a bunch of examples where people say it's not quite as good that's why I always recommend just testing out yourself. For me though I do think there's something in it this there's definitely a big step up between Quen 3.7 and the previous version Quen 3.8 is still building this one but this was like a Minecraft style game and I would say Fable 5 and Kimi K 3 absolutely crushed it but you look at some of this stuff like fluid dynamics it's called Kimi K 3 did the best whereas Fable 5 and GPT 5.6 did okay and Quen 3.8 didn't even come closer. The matrix tests they all pretty much come out on par they all look very similar this was like a bird a bunch of birds flocking together I would say they're all pretty good but actually honestly side-by-side I'm gonna say that Quen 3.8 did the best job here create the nicest outputs this one Quen 3.8 just just didn't do anything interesting. I'm gonna go with Kimi K 3 for this because I can actually move the cloth here and we can bounce it around I would say that Kimi K 3 did the best on the physics here whereas for example GPT 5.6 you can't move the cloth and the same for example with Fable 5 and then it's really weird so for example Quen 3.8 is just continuously moving but you can't move the cloth around or pick it up or anything like that only Kimi K 3 can you do that the fireworks example Quen 3.8 I would say came in last there all the others pretty nice Kimi K 3 winning again now the landing page really surprised me on this one so if we have a look at all of these outputs like in GPT 5.6 Sol just created something super basic here it feels very much like an AI driven website Fable 5.6 was not nice at all it feels so basic when you're looking at that page almost like something from a year ago and then if we have a look at Kimi K 3 it did pretty good but look at the output from Quen here like this is by far the nicest design that we created it doesn't feel or look like AI so much it breaks the sort of boundaries of what you'd normally see with a web design from AI even like the font Netflix it looks nice much much nice in the rest lava lamps all kind of look a bit meh and this is an interesting one so this is a video side-by-side so we get the AI to create a video using Reemotion as a trailer for the AI profitable and what you can see here is that Kimi K 3 came in last and GPT 5.6 Sol didn't do too badly but I would genuinely say that Fable 5 did the best followed by Quen 3.8 those are the two designs I look at I'm like I could actually use those those are decent Galaxy emulation all kind of look the same but it was actually Kimi K 3 that struggled with that one my point being that there's not always one AI that's the best like sometimes you're gonna prompt it in exactly the same way across every generation you just won't get the same outputs I mean GPT 5.6 Sol probably created the nicest thing right there for the orbit you can see again Kimi K 3 struggled but overall yeah I mean Quen holds its own not quite as good as the rest on some tests but it's a mixed bag so test it out for yourself and thanks very much for watching if you want to get more training on AI automation how to save time how to scale your business how to grow with AI automation feel free to get the AI Profitable Boardroom link in the comments description or just go to the AI Profitable Boardroom.com inside the community you can ask questions get help and support in real time I personally answer all of the questions inside the community in the calendar you can ask on live call any questions you have you get coaching in real time you can meet the rest of the members that's on a live zoom call four times a week inside the classroom you get my master classes on Fable 5, Quen, Kimi K 3 and also Fable 5 we've got loads of trainings on each and we had new daily updates based on what's just dropped as you can see right here plus we have a bunch of courses and beginner to expert roadmap as well and if you want to meet people in your local area who are building with AI agents like you feel free to get that inside the map section here you can meet people in your area DM them etc and I hope to see you inside there link in the comments description