[0:00] In the last 24 hours, we have had huge
[0:02] updates to two of the biggest AI models
[0:04] on the planet. First, we got the release
[0:05] of GPT 5.5, which is boasting certain
[0:09] benchmark scores that beat out Claude's
[0:11] Mythos. Secondly, we got the release of
[0:14] DeepSeek V4, which is an open-source
[0:17] openweight model that has benchmarks
[0:19] that rival these frontier big players.
[0:22] So, with all these new models to choose
[0:24] from, what are you, the average user,
[0:26] supposed to do? Well, today I'm going to
[0:28] help you answer that question as I pit
[0:30] Opus 4.7, GPT 5.5, and DeepSeek V4
[0:34] against one another so you can see which
[0:37] one actually makes sense for you. Now,
[0:39] before we kick off this head-to-head
[0:41] test between GPT 5.5 inside of Codeex,
[0:45] Deepseek V4 inside of Open Code, and
[0:48] Opus 4.7 inside of Cloud Code. Let's
[0:51] first take a quick look at the
[0:52] benchmarks, especially these two latest
[0:54] models that dropped in the last 24
[0:56] hours. Now, let's first talk about cost.
[0:58] Now, DeepSeek V4, as you know, is an
[1:00] open- source openweight model, but that
[1:02] does not mean you can run this on your
[1:03] computer because this thing is huge. I'm
[1:05] talking 1.6 trillion parameters. You
[1:08] need some serious hardware to run this.
[1:10] So, we still got to pay for it. We're
[1:11] still going to have to use the API, but
[1:13] it is infinitely cheaper than the
[1:15] competition, about 8 times cheaper. And
[1:18] of the three models, the brand new GPT
[1:20] 5.5 is actually the most expensive,
[1:22] which is kind of surprising because by
[1:24] and large, OpenAI has been cheaper than
[1:26] its anthropic competition. In terms of
[1:29] what it will cost you per 1 million
[1:31] tokens of output for GPT 5.5, it's going
[1:34] to be $30. For Enthropic, it's going to
[1:37] be $25. And for DeepS, it's going to be
[1:39] $348.
[1:41] Now, if we're talking about input
[1:43] tokens, which is a smaller part of the
[1:46] hole, GPT 5.5 and Opus 5.7 are the same,
[1:49] it's going to be $5 per 1 million input.
[1:53] And for DeepSeek, it's about like $1.70.
[1:57] So, way cheaper on the input and way
[2:00] cheaper on the output. That being said,
[2:01] when it comes to 5.5, this is like twice
[2:04] as expensive as 5.4. However, OpenAI
[2:08] claims that it actually uses way less
[2:10] tokens due to its power. So, while it's
[2:12] double the price of 5.4, they say in
[2:14] terms of actual token spend and actual
[2:16] cost for the same task, it ends up only
[2:19] being like 20% more expensive when it's
[2:21] all said and done. So, just have that in
[2:23] the back of your mind. So, we've talked
[2:24] about the cost. Now, let's talk about
[2:25] the benchmarks. How good are these
[2:27] models on paper? I know we're all kind
[2:28] of numb to benchmarks in general. we
[2:31] need to take them with a grain of salt,
[2:32] but it's still worth taking a look,
[2:33] especially when we're looking at the
[2:35] numbers that are reported by each player
[2:37] on the same benchmark. So, there were
[2:40] three in the coding category that all
[2:42] three reported numbers that was Swebench
[2:44] Verified, SweetBench Pro, and Terminal
[2:46] Bench 2.0. Now, for SWEBench verified
[2:49] and SweetBench Pro, Opus was the winner
[2:51] there. On Terminal Bench 2.0, GPT was
[2:55] the winner by far at 87.2, 2, which by
[2:58] the way is a higher number than what
[3:00] Anthropic reported for Mythos, Mythos,
[3:03] sorry, which is kind of crazy. You know,
[3:05] the super secret model they can't
[3:06] release apparently does worse on
[3:08] Terminal Bench 2 than GPT 5.5. Now, the
[3:11] Terminal Bench 2.0 is the biggest
[3:12] outlier here. Opus 4.7 and V4 Pro are
[3:15] way behind, but take a look at Opus 4.7
[3:18] versus V4 Pro. It's less than two points
[3:21] while being eight times cheaper. And you
[3:23] see the same sort of story here with
[3:24] SweetBench Verified and SweetBench Pro.
[3:26] Yeah, Opus wins, but when we compare the
[3:30] second place with the third place, and
[3:31] V4 is always third place, there isn't
[3:33] the huge gap you would expect. I mean,
[3:36] five points isn't nothing, you know, on
[3:39] Sweetbench verified 85 to 86, but again,
[3:42] eight times cheaper, open- source, you
[3:45] know, there there's some actual
[3:46] trade-offs here that we can make if we
[3:48] don't need the most power. Another thing
[3:49] that's interesting to talk about is long
[3:51] context where oddly opus 4.7 is really
[3:55] bad by the numbers like significantly
[3:57] worse than 4.6 which kind of blows my
[3:59] mind. And when we're talking about long
[4:01] context where we're trying to retrieve
[4:02] things between 500,000 tokens and 1
[4:05] million tokens 4.7 is actually terrible
[4:08] and does way worse than deepseek and GPT
[4:11] 5.5. Now you can have a whole discussion
[4:13] about why are you even in the 500,000 to
[4:16] 1 million token range to begin with? how
[4:18] many people are actually operating there
[4:20] because we are hitting context rot no
[4:21] matter what at that place no matter what
[4:23] model you're using but it is interesting
[4:25] that for whatever reason we've seen some
[4:27] regression when it comes to the
[4:28] anthropic models but big picture I think
[4:30] the takeaway is 5.5 is really strong it
[4:33] beats opus 4.7 in certain metrics loses
[4:36] in certain metrics but it's an extremely
[4:38] robust model and on top of that while V4
[4:41] Pro is kind of you know lagging behind
[4:44] by and large it's within striking
[4:47] distance while being infinitely cheaper,
[4:48] which again is a great option for your
[4:51] average customer because right now it
[4:53] feels like you don't have a lot of
[4:54] options on the open source side that
[4:56] actually can compete. Now, let's jump
[4:57] into the actual head-to-head test with
[4:59] all three of these models. And we're
[5:00] using a harness for each of these
[5:02] models. With 5.5, it's going to be
[5:04] codeex. With Opus 4.7, it's going to be
[5:06] Claw Code. And with DeepSeek V4 Pro, I
[5:08] am using Open Code. And for the first
[5:10] test, what we're going to do is we're
[5:12] going to have them create a flight
[5:13] simulator for us in 3JS that runs in the
[5:16] browser. You can see the prompt right
[5:17] here. I'm saying I want it to feel good
[5:19] to fly. I want it to have some weight to
[5:21] it. I want some strong visuals, and I
[5:24] want it to use whatever structure and
[5:25] tooling it thinks is correct. So, it's
[5:29] straightforward enough that they know
[5:30] what to do, yet there's enough leeway so
[5:32] we can see some divergence between the
[5:33] models. And while we are going to look
[5:35] at what they're able to oneshot, we are
[5:37] going to go through multiple iterations
[5:38] of this and have follow-on prompts
[5:40] because as cool as it is to see how well
[5:42] it does on one shot, that isn't how we
[5:45] really work in real life, is it? Right.
[5:46] I want to see how it does when I give it
[5:48] follow-on prompts and how quickly it
[5:50] takes to get it to something I like. And
[5:52] when we compare these three models,
[5:54] there's really four things I'm going to
[5:55] look at. It's going to be time. How long
[5:57] does it take to build this? Cost, how
[5:59] many tokens are we using? Quality, how
[6:01] good is it? And then four is sort of
[6:04] vibes, and that sort of relates to
[6:05] quality. It's very subjective. Which one
[6:07] do I actually like more? And also of
[6:09] note, all three models, all three
[6:11] harnesses are also using the exact same
[6:13] skills. So, let's begin with Deepseek in
[6:15] the questions. It's asking us, it's
[6:16] asking what sort of flight model we
[6:18] want. Let's go with full sim. It's
[6:20] recommending oceans and islands for the
[6:22] terrain. We'll go with that. Let's see
[6:24] how. And then it's asking camera
[6:25] preference. Let's do both. Let's see if
[6:26] it's able to give us a toggle for both
[6:28] first person and third person. We'll go
[6:30] with its recommended tooling preference.
[6:32] And we'll just go with a low poly model
[6:33] for the aircraft and visuals itself.
[6:35] Now, moving over to Codeex. Same sort of
[6:37] questions, although it's only asking us
[6:39] three. Saying what kind of flight should
[6:41] this plane optimize for? Let's go with
[6:43] hard simulation. Which playable
[6:45] experience matters most for the browser?
[6:48] Let's do island takeoff loop. It is kind
[6:50] of interesting how they all have the
[6:51] same one. And what camera and aircraft
[6:53] presentation? I'm going to do toggle for
[6:55] this as well. And for cloud code, we'll
[6:57] do study sim learning. For the field,
[7:00] ocean, and islands input, we will do
[7:02] keyboard and mouse. It will let it go to
[7:04] work. So plan mode by the large very
[7:07] similar across all three. pretty much
[7:09] the same questions of like what do you
[7:11] want the physics to be? What do you want
[7:13] the terrain to be? What do you want the
[7:14] camera angle to be? So, no huge
[7:16] difference there. And let's see what
[7:17] they come back with in terms of a plan.
[7:19] All right, so all three plans are
[7:20] complete. So, let's go through each of
[7:21] them pretty quickly and see some of the
[7:23] differences. First one we're looking at
[7:25] here is Deepseek and it's pretty bare
[7:27] bones in terms of the plan it lays out.
[7:29] So, gives us the project structure and
[7:31] then talks very quickly about light
[7:33] physics, environment, camera, and HUD
[7:35] overlay and really just a few bullet
[7:36] points. On the other hand, when we're
[7:38] looking at 5.5 inside of codeex, it
[7:40] gives us a summary, key changes, goes
[7:43] into implementation details, the test
[7:45] plan, and as well as the assumptions. It
[7:47] spells all that out for us. And then we
[7:49] have Claude codes plan, which took the
[7:50] longest, took it about 5 minutes, but by
[7:52] far is the most thorough because it's
[7:53] the context, the stack layout, talks
[7:56] about the flight model. It's going into
[7:58] like the actual different moments,
[8:00] talking about stalls, like the stall
[8:01] buzzer, like it's it's going very very
[8:03] detailed. goes into the controls, the
[8:05] world, the mod, the actual aircraft
[8:06] we're going to be using, performance,
[8:08] and just keeps going on and on. So, very
[8:11] detailed. So, now we're going to have
[8:12] all three implement their plan, and
[8:14] we'll see what the final result looks
[8:15] like. So, GPT 5.5 inside of Codex was
[8:18] the first to finish. So, let's see what
[8:20] it looks like. So, here's the flight
[8:21] simulator it got us. We have, you know,
[8:24] some clouds in the sky. We have what
[8:28] looks like an AOA indicator up there. We
[8:31] have our speed down below. And let's see
[8:34] if we can actually get this thing off
[8:36] the ground. I will note there's no more
[8:37] like runway. It's just like straight
[8:39] grass and it said it was going to be
[8:40] like an island thing. Although when the
[8:44] camera kind of spazzes out, you can see
[8:45] the runway down below there for a
[8:47] second. All right, we're stalling out
[8:49] and we just we can't even get off the
[8:50] ground. All right, so this this one's
[8:53] actually just a little is actually kind
[8:54] of difficult. Um, so what I'm going to
[8:58] do is I'm going to give it a second
[9:01] prompt asking it to make it a little bit
[9:02] easier to fly because it has a lot going
[9:04] on here, but this is this is tough. So I
[9:07] wrote, "It is really hard to fly. Can we
[9:09] make this easier to use?" Aka a little
[9:11] bit more arcadey and also the graphics
[9:14] could use some work. So let's see how
[9:16] that does. Now, of note, um it took 5.5
[9:20] about 7 minutes to create that first
[9:22] pass for us, and it took 63,000 tokens.
[9:26] All right, it said it made it a little
[9:27] bit easier to fly and updated the
[9:29] graphics. So, let's see what the second
[9:31] pass looks like. So, here's what we got.
[9:33] Graphics definitely look better, but
[9:34] let's see if we can actually get off the
[9:36] runway this time. So, all right,
[9:38] throttle's at 100%.
[9:41] 50 60. What's the rotation speed on a
[9:44] Cessna? All right. 70 80 90. We got to
[9:50] be able to get off the ground now. Okay.
[9:52] Wrong way. Let's go. Get off the ground.
[9:55] Get off the ground. Nope. This is
[9:57] probably going to stall me out, isn't
[9:58] it? Yeah. Stall. Okay.
[10:01] This still needs this still needs some
[10:02] work. So, let's let's give Codeex one
[10:04] more shot. Let's give 5.5 one more
[10:06] chance to make this actually playable.
[10:08] So, I told it I can't even get the
[10:09] aircraft off the ground and enter
[10:11] flight. We definitely need to make it
[10:12] easier to take off and actually fly the
[10:13] thing. Okay, so it says it fixed the
[10:15] takeoff problem. Apparently the brakes
[10:17] started locked on before. I don't know
[10:19] if that's why we weren't able to do it.
[10:21] Oh, we it didn't automatically set it to
[10:24] takeoff flaps. Yeah, this was we had
[10:26] this on like super super simulator mode.
[10:29] Here is attempt number three at our
[10:31] flight simulator. Let's see how we do.
[10:34] So, can we get off the ground? Oh, we're
[10:36] bouncing on the runway with this time.
[10:38] That's something. All right, cool. We're
[10:40] off the ground. We're actually moving.
[10:43] Let's see if we can get on one of these
[10:45] rings. I mean, the graphics aren't that
[10:48] bad, you know, for something just
[10:50] generated in less than 10 minutes. Um,
[10:53] it seems to be pretty accurate in terms
[10:55] of, you know, it's giving me like my
[10:57] vertical, you know, feet per minute down
[10:59] at the bottom, my actual altitude, the
[11:02] knots, heading, AGL. So, like it's
[11:05] relatively sophisticated in terms of
[11:07] tracking everything. I mean, this little
[11:09] indicator in the front, I mean, looks to
[11:11] be like an angle of attack, you know,
[11:13] indicator, which is kind of cool. So, it
[11:15] has some good stuff going on. The the
[11:19] actual like controls are a little janky.
[11:21] As you can see, I can't control this for
[11:22] anything, but by and large, not bad. You
[11:25] know, we can kind of like kamicazi this
[11:27] and see what happens at, you know,
[11:28] 18,000 ft per minute.
[11:31] But yeah, you know, for 66,000 tokens,
[11:36] about 10 minutes, 15 minutes or so, give
[11:39] or take, you know, with the back and
[11:41] forth. I don't think that's bad at all.
[11:42] So, now let's take a look at DeepSk. It
[11:44] took about 10 minutes to do this. And in
[11:46] terms of tokens, 63,000
[11:50] 44. So, 44 cents, 10 minutes. And here
[11:53] is what Deep Seek came up with for us. I
[11:57] have no idea
[12:00] what I'm looking at.
[12:04] This is supposed to be third person.
[12:06] This is supposed to be the cockpit. And
[12:08] obviously,
[12:09] our first pass with Deepseek was an
[12:12] utter disaster. So, I'm telling Deepseek
[12:14] the simulator is a complete mess. The
[12:16] graphics are completely buggy and I
[12:18] cannot fly anything. Please fix. And
[12:21] here's what our second pass looks like.
[12:24] I still have no idea. Absolutely no clue
[12:29] what the heck Deep Seek is. Oh, hey,
[12:31] there's a plane. You know, there's
[12:33] something.
[12:35] I Yeah, this is This is brutal. And to
[12:38] be honest, I feel like even giving it
[12:40] another prompt to do this, I would need
[12:43] to start getting very, very specific
[12:44] about what we're trying to do, which
[12:47] again like falls pretty short of what we
[12:48] did with Codex. Like it was very, you
[12:50] know, kind of bland prompts. was able to
[12:51] get something at least close even on the
[12:53] first pass. Like this clearly it's
[12:56] completely struggling with the graphics.
[12:58] We are just I I don't even know how to
[13:00] describe this. But hey, it was super
[13:03] cheap. So now let's take a look at what
[13:06] Claude Code was able to give us. For
[13:08] reference, it took 13 minutes to
[13:11] actually execute the plan. The plan
[13:12] itself took 5 minutes. So let's call it
[13:15] 20 minutes to come up with the first
[13:17] pass. And then for total tokens, this
[13:19] run took about 15% plus the 5% before
[13:21] for plan. So we're looking at well sorry
[13:24] we are looking at 11% context plus 5%
[13:28] before. So call it 20 minutes 150,000
[13:31] tokens for Claude Code which is
[13:33] definitely the most expensive and
[13:34] slowest out of all of them. And here is
[13:37] Claude Code's attempt at this. Um for
[13:41] whatever reason we are instantly in the
[13:42] air. We are stalling. We are an IFR. I
[13:46] don't know what's happening. We are
[13:48] about to crash something. Let's Can we
[13:50] save this? Can we pull this out of a
[13:53] dive? No, we're stalling. No, we're
[13:54] dead. Okay, that's interesting. Um,
[13:57] again, it instantly slingshots us into
[13:59] the air. We are in the clouds. We are
[14:02] stalling. I don't know what is
[14:04] happening. We need We need a second
[14:08] pass. So, I wrote, "Upon loading, I'm
[14:10] instantly thrown into the air. It's hard
[14:12] to control. I want to start on the
[14:13] runway, and I want it easier to fly. Oh,
[14:15] and by the way, improve those graphics,
[14:16] too. So, it took about four minutes, but
[14:18] it made some changes. We're going to
[14:20] spawn on the runway. It changed the
[14:22] gear. So, now it's tricycle gear and a
[14:24] few other stuff. So, let's see what it
[14:25] looks like. All right, so here it is
[14:27] again. We are thrown immediately into a
[14:28] fog bank. I'm trying to control this
[14:30] thing. And I just Yeah, there's there's
[14:32] no controlling this at all. All right,
[14:34] we are going to give we're going to give
[14:35] Cloud Code one more chance here. So, I
[14:37] told it's still instantly slingshotting
[14:39] me into the sky. I said, let's go with a
[14:41] much more arcade type feel with the
[14:42] controls. I think we probably should
[14:43] have done that with the initial prompt
[14:45] for all three. I think going for a more
[14:48] realistic sim type thing, it it really
[14:51] struggles to
[14:53] I think do that in a way where it's
[14:55] still user friendly. I think it's
[14:57] probably doing a good job under the hood
[14:59] in terms like okay like angle of attack.
[15:01] All right, you're stalling at this you
[15:02] know angle versus the speed and all that
[15:04] but actually manipulating this from the
[15:07] computer is basically impossible.
[15:09] Although I I think the fog stuff is
[15:11] really strange. So, let's see if after
[15:14] the second round of prompts, it's able
[15:15] to do a little bit better because right
[15:17] now GPT 5.5 did much much better. So,
[15:20] Cloud Code made some more changes, made
[15:22] it more user friendly, and let's see if
[15:23] I'm still going for my instrument rating
[15:25] this time. So, yep, we're still going
[15:28] we're still going for instrument rating.
[15:30] RIP men's here, but you know, I can kind
[15:32] of see it. You know, I can I can check
[15:34] my instrument panel. All right, we're
[15:36] coming off the runway.
[15:38] Um,
[15:40] yeah. Okay. Can I Why is there a tree in
[15:43] the runway? Trying to trying to go up.
[15:46] Can I go up? Can I pitch? Click canvas
[15:50] to lock mouse. I What? Oh, we're in the
[15:54] We're in the air.
[15:56] Nope. Nope. We died. So, yeah, I think
[15:59] this one is pretty clear. Uh, GPT 5.5
[16:04] easily the winner. I think Cloud Code
[16:07] was second place. I would give it second
[16:09] place. You know, it definitely struggled
[16:13] even with the prompts we gave it. We
[16:14] didn't give it great prompts. Let's be
[16:15] totally honest. I think given more time,
[16:18] better prompts, a few more back and
[16:19] forth, we could have got it to where we
[16:21] wanted to go. Like, it was at least it
[16:22] had an aircraft, it had a runway, it had
[16:25] trees in the runway, but it had the the
[16:28] actual things we needed versus Deepseek
[16:31] with Open Go. I have no idea what was
[16:33] going on there. That was a complete
[16:34] mess. I feel like I would have had to
[16:36] start over from the beginning, like give
[16:37] it a very specific prompt. like it
[16:38] wasn't even close to being messed with,
[16:40] but GPT 5.5 right off the rip, you know,
[16:42] with pretty vague prompts. I thought it
[16:44] did really good. 5.5 also used a total
[16:47] of 66k tokens. We're looking at over
[16:50] here with Opus altogether about 200,000
[16:53] tokens. So, a quarter of the tokens
[16:55] essentially quarter the cost and it was
[16:57] a bit faster. I mean, at this point, I
[16:59] don't even care about how open code
[17:01] actually took longer than GPT 5.5 as
[17:03] well. And it just sucked. Let's just be
[17:06] honest, it just sucked. Now let's move
[17:07] on to test number two. This time we are
[17:11] going to be asking them to create a
[17:13] landing page that shows off web GPU
[17:15] shader work using 3JS. Now web GPU
[17:19] shader work is the kind of stuff you see
[17:21] on awards websites. I'm talking websites
[17:24] like Igloo. This kind of thing like very
[17:27] high-end graphics. It looks like a video
[17:29] game. It's essentially using your
[17:31] computer's graphics card to render all
[17:33] this stuff. Now, I don't expect any of
[17:35] these to get anything even close to what
[17:37] we see here, but I want to see what they
[17:39] can do using essentially the shaders
[17:42] technology. This is definitely a step
[17:43] above your basic SAS templated landing
[17:46] page. I want to see what they can do and
[17:48] push them to the limits in the world of
[17:50] web design. Now, I've given all of them
[17:51] a skill that actually breaks down how to
[17:54] do this sort of thing. So, it's not like
[17:56] they're completely in the dark and one
[17:58] also doesn't have an advantage over the
[18:00] other. The only thing I've told them is
[18:01] I want it to feel modern and visually
[18:03] striking. something you would see on
[18:05] awards and to make smart use of GPU
[18:07] compute. So they can pick whatever stack
[18:09] and project structure they like and use
[18:11] good judgment on hero concept UI and
[18:14] interactions. And just like the first
[18:15] test, they're all on plan mode. So let's
[18:18] get started. Okay, so they all finished
[18:19] their plan and funny enough, none of
[18:21] them asked me any questions even though
[18:23] we put them in plan mode. So let's take
[18:24] a look at GPT 5.5 first. So it's telling
[18:28] us it's going to do a fullbleleed
[18:30] interactive GPU driven hero. The concept
[18:32] will be a living signal field with some
[18:35] like dense particle thing it's going to
[18:36] do. We'll see what that ends up looking
[18:38] like. And overall, it's a minimal awards
[18:40] style landing copy. Fully interactive
[18:42] web GPU scene with pointer reactive
[18:44] compute simulation.
[18:46] All right, for Deep Seek, it's a pretty
[18:48] short and sweet plan just like we saw
[18:51] with the flight simulator. Hopefully, we
[18:53] get a better output this time. But a
[18:55] hero section with 75,000 GPU computer
[18:57] particles. I am kind of guessing that
[19:00] all of them are going to go for some
[19:01] sort of like particle theme on the on
[19:04] the hero.
[19:05] So, it's gonna have mouse interaction
[19:07] integration. It'll have a one-time
[19:09] initialization. And then we should see
[19:11] stuff like bloom, chromatic aberration,
[19:14] a custom vignette, and some film grain.
[19:16] So, we'll see what that actually ends up
[19:18] looking like. And then we have Opus
[19:20] 4.7's playing again going for this
[19:22] particle thing with bloom, and it's
[19:24] going to be interactive with the mouse.
[19:25] So, we'll see if any of these actually
[19:26] look different because on the surface
[19:28] all their plans sound very similar. So,
[19:30] the first one done was 5.5. It took
[19:33] about 6 minutes. And in terms of tokens,
[19:35] we've used 107K. So, let's see what it
[19:39] built us. And here's what it created for
[19:42] us. Now, this is very bright. Um, so
[19:45] it's hard to even see the actual
[19:47] particles, but you know, as we scroll up
[19:49] and down, it does have an animation
[19:52] going on in the background as well as,
[19:54] you know, some subtle color changes.
[19:56] Looks like right now our mouse is
[19:59] supposed to attract the particles and we
[20:01] have I'll move this over here. It gave
[20:04] some options for like repelling it
[20:06] versus drift, but again, it's kind of
[20:09] tough to to see it um due to how bright
[20:11] it is. So, I told that it's hard to
[20:13] actually see the particles due to the
[20:14] brightness. It also takes over a lot of
[20:16] the hero text. So, can we turn down the
[20:17] brightness a bit and also push it to the
[20:18] right a bit more because right now it is
[20:21] kind of overpowering. You can't even
[20:23] really read the text over here on the
[20:25] left due to just how freaking bright
[20:26] these particles are. And here's the
[20:28] update after the second run. It's a
[20:30] little bit better. It isn't as
[20:31] overpowering and leaves some room for
[20:34] the text. Um, although I will say it
[20:37] it's kind of blurry almost, but you
[20:40] know, it's not bad. Like it it set out
[20:43] to do what we told it to do given the
[20:46] somewhat vague prom. So, I'm not blown
[20:47] away by sort of the design it came up
[20:49] with, but I'm not like upset about it.
[20:51] Now, let's take a look at Clawude Code
[20:53] because as we've been doing all this,
[20:55] Deep Seek is still over here in the
[20:57] trenches trying to figure this out. And
[20:59] here's what Claude Code gave us.
[21:03] So,
[21:05] kind of nothing.
[21:07] I'm not sure if it's saying the
[21:10] background. I guess the entire
[21:11] background is supposed to be
[21:16] the WebGL. I'm I'm assuming it's very
[21:19] understated,
[21:21] which I guess is something you could
[21:23] totally do. I mean, like on screen it
[21:25] doesn't look like it looks kind of cool,
[21:26] but I I'll be honest, I was looking for
[21:28] something a little more flashy. So on
[21:31] the second pass when I told it to make
[21:32] it a bit more flashy, there wasn't a
[21:34] huge difference. Although like it's it's
[21:37] really subtle. There's kind of like this
[21:39] film grain almost like this blur that
[21:42] goes from bottom to top. So it's a
[21:44] pretty subtle thing. And you can see
[21:46] here on the bottom it tracks like the
[21:48] frames per second. It's using 250,000
[21:50] particles. So I mean honestly it looks
[21:54] cool. It's just not super flashy. So
[21:56] it's definitely like a taste thing. Now,
[21:58] total tokens on the cloud code side was
[21:59] about 175,000 and it took just slightly
[22:02] longer than 5.5 inside of Codeex. Now,
[22:06] let's take a look at DeepSk, which has
[22:08] taken 116,000 tokens at this point. It
[22:11] took the longest um as well, but total
[22:13] cost, we're talking again under a
[22:14] dollar. And here's what it gave us. So,
[22:18] it's
[22:20] kind of this particle field thing that
[22:22] uh somewhat follows my mouse.
[22:26] Interesting. I think it might give you
[22:28] like an epileptic seizure,
[22:31] honestly. Um, beyond that, it's pretty
[22:33] bland. Um, the flux, you know, text
[22:37] right here kind of changes colors, but
[22:40] yeah, pretty much just created this this
[22:42] thing. And after telling Deep Seek to do
[22:44] another pass, it then came back with
[22:46] this where now it kind of has like some
[22:48] weird parallax thing. It's got some like
[22:51] blue stuff going on in the background.
[22:53] And now this thing looks like a UFO,
[22:55] which kind of responds to your mouse,
[22:58] but
[22:59] yeah, it's it's it's something. And
[23:02] overall, the token count from Deep Seek
[23:04] was 130K tokens, coming in at a $143.
[23:08] So, after all those tests, where does
[23:12] that really leave us? So, now let's talk
[23:13] about the final results. When it comes
[23:15] to test number one, which was the flight
[23:17] simulator, clear winner. That was GPT
[23:19] 5.5 inside of Codeex. It was quicker
[23:22] than Opus 4.7 inside of Cloud Code. It
[23:25] was also faster and the end result was
[23:27] by far the best. Deepseek did terribly
[23:31] in the flight simulator. It wasn't even
[23:33] close to what we were trying to do. I
[23:34] would have had to continue to prompt it,
[23:35] prompt it, prompt it to even get it to
[23:37] like close to the first pass from 5.5.
[23:41] And Opus 4.7 and Cloud Code was like,
[23:43] eh,
[23:45] it wasn't awful. like it really didn't
[23:47] work at the beginning, but after a
[23:49] couple prompts, you could tell we could
[23:50] get it to a place where it was
[23:51] equivalent to what GPT 5.5 was doing,
[23:54] but that would have taken more prompts.
[23:55] It would have taken more time, and
[23:57] ultimately would be more expensive. So,
[23:59] clear winner for 5.5. In terms of the
[24:02] web GPU landing page, again, DeepSeek
[24:04] struggled here. I was not a fan of this.
[24:06] I don't really know what this is
[24:08] supposed to be. Sure, I didn't give it a
[24:09] super great prompt, but like is this
[24:12] what we're going to be getting as a
[24:14] baseline median outcome if I don't like
[24:17] grab Deep Seek by the reins and really
[24:20] force it to do something? I guess so.
[24:22] Now, when we compare Opus in 5.5, I
[24:24] would have gone with Opus 4.7 and Claude
[24:27] Code with how it handled the web GPU
[24:29] thing. I think that has to do with sort
[24:30] of a taste kind of deal. Yeah, you could
[24:32] argue the 5.5 was flashier, but I
[24:35] thought it was kind of ugly. Um, again,
[24:39] in all these tests, we kept the prompts
[24:40] rather vague to see what sort of path it
[24:42] would go down. So, I would definitely
[24:44] give Opus the lead here, although it was
[24:48] more expensive and it also took slightly
[24:50] longer. So, if they were given a more,
[24:53] you know, hands-on prompt that was very
[24:55] specific about what she wanted to do
[24:57] because 5.5 did what we wanted it to do,
[24:59] like it did create a web GPU landing
[25:01] page. I just thought it was ugly. So, it
[25:04] still completed the task. It just didn't
[25:06] complete it as well, I think, as Opus.
[25:08] Now, big picture, what does it mean if
[25:10] we take all that together? Well, I think
[25:11] it means great news for anybody who's
[25:15] using agent coders. We have options,
[25:18] right? You can use Opus and Claude Code
[25:20] or you can use GPT 5.5 and codecs.
[25:23] You're not wrong with either. I think
[25:26] it's totally a personal preference at
[25:27] this point. And the best part is if you
[25:30] go down the cloud code route, it pretty
[25:32] much all applies to Codex. If you go
[25:34] down the codeex route, it pretty much
[25:35] all applies to clawed code. So, I don't
[25:38] really think there's vendor lock in the
[25:39] sense like, oh, I've only learned about
[25:41] clawed code, like I can't go to codeex
[25:43] or vice versa. That's not the case at
[25:45] all. If you're doing this the right way,
[25:46] what you're really learning is AI
[25:47] fundamentals and how to build things.
[25:49] And that applies to both of these guys.
[25:51] And the more competition, the better it
[25:53] is for us, the consumer. Now, as for
[25:55] DeepSeek, n I don't know. I wasn't very
[25:59] impressed. This might be a situation
[26:01] we're like, okay, like Deep Seek makes
[26:02] sense if we're doing simpler tasks where
[26:04] we just don't need the power of
[26:05] something like Opus or we just don't
[26:07] need the power of something like GPT 5.5
[26:10] because remember we're talking about
[26:11] something that is eight times cheaper.
[26:13] Sure, I didn't like the web GPU landing
[26:16] page this thing came up with, but was it
[26:18] eight times worse?
[26:20] Maybe, maybe not. Kind of hard to
[26:22] actually, you know, articulate that and
[26:24] quantify that, but obviously that's
[26:26] something we need to take into account.
[26:27] So, you know, I don't think it's really
[26:29] competition to be frank with 4.7 or 5.5.
[26:33] I think though if you're doing simpler
[26:34] task and you're like very token
[26:36] conscious, very cash conscious, then
[26:38] hey, maybe Deep Seek makes sense for
[26:40] you. So, that's all I got for you guys
[26:42] today. I hope that sheds some light on
[26:44] these three models and how they kind of
[26:46] stack up to one another. I think it's a
[26:47] great time to be in the space. More
[26:49] competition is better for everyone. So,
[26:52] as always, if you want to get your hands
[26:53] on the Claude Code Masterass, make sure
[26:55] to check out Chase AF Plus. There's a
[26:57] link to that in the description and I'll
[26:59] see you