Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

🚨 GPT-6.1 Sol vs Claude Opus 5.5 Same prompt. Same high effort. Subway Surfers clone in Three.js - both had to build and test. Sol(Left) took : 12 min / 7.32M tokens Opus(right) took : 39 min / 5.6M tokens Sol was 3x faster. Opus used ~23% fewer tokens.... show more

Rajath Gowda

1,540 subscribers

10,763 views • 4 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

16 Comments

Yipeng | Daily AI4 days ago

picking based on which game is actually better, which the numbers don't tell me. 3x faster means nothing if the game is worse. speed is a tiebreaker, quality is the decision.

Rajath Gowda4 days ago

Yeah true...I agree quality matters more than anything

Yipeng | Daily AI4 days ago

would love to see a blind playtest added to the comparison. same prompt

Rajath Gowda4 days ago

Sure I will.

Dr. Clown, PhD4 days ago

Opus

meng m4 days ago

I’d 100% go with the one that’s 3 times faster and saves quota. Since you guys don’t spend 15 hours a day building games, you may not realize how much speed and efficiency matter. And I don’t use the AI’s default graphics — I use a 4K texture pipeline. That little boost from Opus? Honestly, nobody cares. But 6.1sol isn’t actually that fast. If it really were that fast, I would pick it! Right now, Opus is the winner~

Drew Wakefield3 days ago

This isn't even close. And 3x better means nothing if it's 3x worse for it

bhavesh shah4 days ago

Purely from looks opus looks way better

BlurstTewiter 🌊🌊4 days ago

So people need to get these comparisons right. You have to give each models the same budget and time.

stairstotop3 days ago

depends what broke less during testing

Minh Danh Ngo4 days ago

Sol speed wins every time

x0Do0mer0x4 days ago

What about cost?

Akash4 days ago

the difference is staggering

Septian4 days ago

I can already smell GPT's model right at the first second, the flickering surface on that train. Opus has more taste. @grok why is that.

TR Siber | Siber Bilgi Ağı3 days ago

Opus bence çok harika bir model, tabi bunu antropic bozmaz yada değiştirmezse, evet düşünme süresi uzun biraz ama çıkardığı iş ve limit konusunda çok iyi olduğunu düşünüyorum.

Full Stack Web4 days ago

You left out the most important thing: how much did they spend?

Related Videos

Opus 5.5 killed the game. We had it and GPT-6 Sol both draw Dario in Canva with ego (lite). Claude Opus 5.5: 1h 23m, $6.31 GPT-6 Sol: 26m, $14.97 Opus took 3x longer, cost less than half, and drew a much better Dario.

Opus 5.5 killed the game. We had it and GPT-6 Sol both draw Dario in Canva with ego (lite). Claude Opus 5.5: 1h 23m, $6.31 GPT-6 Sol: 26m, $14.97 Opus took 3x longer, cost less than half, and drew a much better Dario.

ego

178,578 views • 12 days ago

Claude Opus 5.5 completely MOGS GPT 6 Sol. Same prompt. Same task. Look at the results. Opus 5.5 has way better taste and design. It is not subtle. You can see it immediately. GPT 6 Sol is a step up from GPT 5.6 Sol. But next to Opus 5.5 it is not even close. Anthropic is back.

Claude Opus 5.5 completely MOGS GPT 6 Sol. Same prompt. Same task. Look at the results. Opus 5.5 has way better taste and design. It is not subtle. You can see it immediately. GPT 6 Sol is a step up from GPT 5.6 Sol. But next to Opus 5.5 it is not even close. Anthropic is back.

Bridgebench

55,327 views • 14 days ago

Same prompt. GPT-5.6 Sol vs Opus 5. All in Three.js. Opus produced the better raw visuals. The ocean, waves and atmosphere look noticeably richer. But it also: → cost ~10x more → took much longer → needed an extra prompt just to fix the camera controls Sol got surprisingly close on the first attempt, much faster and far cheaper. Opus wins visual fidelity. Sol wins the actual engineering test.

Same prompt. GPT-5.6 Sol vs Opus 5. All in Three.js. Opus produced the better raw visuals. The ocean, waves and atmosphere look noticeably richer. But it also: → cost ~10x more → took much longer → needed an extra prompt just to fix the camera controls Sol got surprisingly close on the first attempt, much faster and far cheaper. Opus wins visual fidelity. Sol wins the actual engineering test.

Token Gremlin

12,914 views • 1 month ago

Something is wrong at OpenAI. Tibo and Sam said GPT-6.1 Sol would be faster today. Instead it appears to be running slower. Sonnet 5.5 and Opus 5.5 are much faster than Sol 6.1 and Grok 4.7 Check out the below comparison, same prompt on high reasoning with a 20 minute deadline.

Something is wrong at OpenAI. Tibo and Sam said GPT-6.1 Sol would be faster today. Instead it appears to be running slower. Sonnet 5.5 and Opus 5.5 are much faster than Sol 6.1 and Grok 4.7 Check out the below comparison, same prompt on high reasoning with a 20 minute deadline.

Eco

17,812 views • 5 days ago

First Opus 5.5 vs GPT-6 Astra test is 3D. One prompt, Blender only, all procedural. Render the 10-second shot, and record your own build timelapse. Opus 5.5: 35 min, 199.6k output tokens, about $13.3 in API terms. GPT-6 Astra: 28 min, 56.6k output tokens, about $14.5 in API terms. Feels like a worthy rival, and honestly I am glad about that. From what I watched, Opus juggles way more at once and is faster overall. Astra is still good imo.

First Opus 5.5 vs GPT-6 Astra test is 3D. One prompt, Blender only, all procedural. Render the 10-second shot, and record your own build timelapse. Opus 5.5: 35 min, 199.6k output tokens, about $13.3 in API terms. GPT-6 Astra: 28 min, 56.6k output tokens, about $14.5 in API terms. Feels like a worthy rival, and honestly I am glad about that. From what I watched, Opus juggles way more at once and is faster overall. Astra is still good imo.

Stefan 3D AI

469,986 views • 14 days ago

One shot prompt with no loops: GPT-Sol Ultra: 35,192,545 tokens used Opus 5.0 Ultracode: 1,171,676,041 tokens used Fable 5.1 Ultracode: 127,366,207 tokensused Same prompt… different results: Fable 5.1 runs at 5fps so I had to speed it up to demonstrate the rendering. Would need further optimisation. Opus 5.0 runs very nicely on first prompt. Doesn't need much in terms of performance optimisation. Just a few odd visual things here and there. My verdict: Fable looks impressive but struggles to run smoothly. Opus is a solid model when prompted properly. Sol is garbage.

One shot prompt with no loops: GPT-Sol Ultra: 35,192,545 tokens used Opus 5.0 Ultracode: 1,171,676,041 tokens used Fable 5.1 Ultracode: 127,366,207 tokensused Same prompt… different results: Fable 5.1 runs at 5fps so I had to speed it up to demonstrate the rendering. Would need further optimisation. Opus 5.0 runs very nicely on first prompt. Doesn't need much in terms of performance optimisation. Just a few odd visual things here and there. My verdict: Fable looks impressive but struggles to run smoothly. Opus is a solid model when prompted properly. Sol is garbage.

Adam Lyttle

593,084 views • 1 month ago

Opus 5.5 actually shows the difference. I honestly expected less. One prompt: build the DeLorean and the clock tower square, rig the car, animate the lightning strike. Both models drove Blender through the Higgsfield Blender plugin and hooked with Higgsfield MCP, where it can use Nano Banana Pro for images, Tripo for 3D models and more. The exact same test went to GPT-6 Astra. Both ran on max effort. Opus 5.5: 73 min, 218k output tokens, $27.3in API terms. Working doors, spinning wheels, the strike lands. GPT-6 Astra: 88 min, 136k output tokens, $21.3 in API terms. Skipped the generators and built all 517 objects itself.

Opus 5.5 actually shows the difference. I honestly expected less. One prompt: build the DeLorean and the clock tower square, rig the car, animate the lightning strike. Both models drove Blender through the Higgsfield Blender plugin and hooked with Higgsfield MCP, where it can use Nano Banana Pro for images, Tripo for 3D models and more. The exact same test went to GPT-6 Astra. Both ran on max effort. Opus 5.5: 73 min, 218k output tokens, $27.3in API terms. Working doors, spinning wheels, the strike lands. GPT-6 Astra: 88 min, 136k output tokens, $21.3 in API terms. Skipped the generators and built all 517 objects itself.

Stefan 3D AI

23,573 views • 14 days ago

🚨codex users!!!! I tested GPT-6 Sol on $20 plan I set the effort to "MAX" I am NOT happy with the results - 15 Million tokens - 7% weekly limit used - $4.21 API cost - 35 minutes of work So... you are getting 857 Million tokens of GPT-6 Sol And wierd part is... only $250 API usage / month?? Claude was $1100 / month with Opus 5 at Max at $20 sub AND Again!! IT IS EXTREMELY SLOW!!! it did NOT complete the task!! I specifically mentioned it to test in THIS SPECIFIC way it only tested "builds" and called it a day Tbh, this is my 4th test with Codex... and I'd prefer Claude (with Opus 5) NOTE: This was a test, I don't use gpt-6 or Opus 5.5 on max for my own workflows... this just shows how much you are getting in "tokens" for the "price" you are paying.

🚨codex users!!!! I tested GPT-6 Sol on $20 plan I set the effort to "MAX" I am NOT happy with the results - 15 Million tokens - 7% weekly limit used - $4.21 API cost - 35 minutes of work So... you are getting 857 Million tokens of GPT-6 Sol And wierd part is... only $250 API usage / month?? Claude was $1100 / month with Opus 5 at Max at $20 sub AND Again!! IT IS EXTREMELY SLOW!!! it did NOT complete the task!! I specifically mentioned it to test in THIS SPECIFIC way it only tested "builds" and called it a day Tbh, this is my 4th test with Codex... and I'd prefer Claude (with Opus 5) NOTE: This was a test, I don't use gpt-6 or Opus 5.5 on max for my own workflows... this just shows how much you are getting in "tokens" for the "price" you are paying.

shownotover

82,881 views • 13 days ago

GPT-5.6 Sol Ultra lost to GPT-5.5 on physics at 3× the cost! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: - A monster truck backflipping onto a parked car - A stunt car jumping six buses into a brick wall - A train derailing off a broken bridge into the water Outputs: GPT-5.6 Sol Ultra: 32.9K tokens, $0.33 Opus 4.8: 9.2K tokens, $0.24 GPT-5.5: 12.4K tokens, $0.11 Grok 4.5: 7.0K tokens, $0.08 Sol Ultra draws just like GPT-5.5, only with more detail and it shows clearest on the bus jump where the two look almost identical. In the other tests Sol Ultra came out worse than its predecessor and the physics really got weaker. We think GPT-5.5 took the truck flip and the train outright. With Sol Ultra you basically get GPT-5.5 with weaker physics and a nicer picture for 3x the price. Newborn Grok 4.5 failed two of the three tests and only came good on the train

GPT-5.6 Sol Ultra lost to GPT-5.5 on physics at 3× the cost! We gave 4 models the same prompt: build three self-contained HTML5 canvas scenes with real physics demos Prompts: - A monster truck backflipping onto a parked car - A stunt car jumping six buses into a brick wall - A train derailing off a broken bridge into the water Outputs: GPT-5.6 Sol Ultra: 32.9K tokens, $0.33 Opus 4.8: 9.2K tokens, $0.24 GPT-5.5: 12.4K tokens, $0.11 Grok 4.5: 7.0K tokens, $0.08 Sol Ultra draws just like GPT-5.5, only with more detail and it shows clearest on the bus jump where the two look almost identical. In the other tests Sol Ultra came out worse than its predecessor and the physics really got weaker. We think GPT-5.5 took the truck flip and the train outright. With Sol Ultra you basically get GPT-5.5 with weaker physics and a nicer picture for 3x the price. Newborn Grok 4.5 failed two of the three tests and only came good on the train

atomic.chat

898,646 views • 2 months ago

we asked GLM 5.2 and Claude Opus 4.8 to find and fix the bugs in two different scripts while Opus 4.8 finished a few seconds faster in both tests, GLM 5.2 burned roughly 17k–38k fewer tokens and absolutely crushed it on cost, coming in 15x to 22x cheaper! Test 1: GLM 5.2 ($0.068) vs. Opus 4.8 ($1.06) Test 2: GLM 5.2 ($0.045) vs. Opus 4.8 ($1.02)

we asked GLM 5.2 and Claude Opus 4.8 to find and fix the bugs in two different scripts while Opus 4.8 finished a few seconds faster in both tests, GLM 5.2 burned roughly 17k–38k fewer tokens and absolutely crushed it on cost, coming in 15x to 22x cheaper! Test 1: GLM 5.2 ($0.068) vs. Opus 4.8 ($1.06) Test 2: GLM 5.2 ($0.045) vs. Opus 4.8 ($1.02)

GMI Cloud

86,755 views • 3 months ago

Opus 5.5 vs GPT 6 astra tested both with the same prompt at their highest reasoning settings, using the same devin harness: > opus took 2 hours 10 mins and cost $75 > astra took 1 hour 25 mins and cost $61 opus 5.5 attention to details is on point, it took time to make everything perfect as i wanted but still super slow and ended up costing way more then astra which one did better here?

Opus 5.5 vs GPT 6 astra tested both with the same prompt at their highest reasoning settings, using the same devin harness: > opus took 2 hours 10 mins and cost $75 > astra took 1 hour 25 mins and cost $61 opus 5.5 attention to details is on point, it took time to make everything perfect as i wanted but still super slow and ended up costing way more then astra which one did better here?

J A Z I I

55,525 views • 14 days ago

Crazy. Opus 5 outperformed Fable 5 on 3d modeling at 2/3 the price We tested Opus 5, Fable 5, and GPT 5.6 Sol on the same prompt: build an explorable Japanese suburban street in Three.js, full 3D, rendered like a hand-drawn anime background. All on Max effort. Opus 5 took the longest but delivered the most varied scenery: clean dark outlines, flat cel-shaded color bands, dense street details down to the vending machine signage. Fable paid more attention to details, and while GPT 5.6 Sol was 3-4x cheaper and the fastest, but the render shows it: sparse, washed out, barely styled. Opus 5: 1hr 21min · $26.7 Fable 5: 1hr 5min · $35 GPT 5.6 Sol: 41min · $7.1

Crazy. Opus 5 outperformed Fable 5 on 3d modeling at 2/3 the price We tested Opus 5, Fable 5, and GPT 5.6 Sol on the same prompt: build an explorable Japanese suburban street in Three.js, full 3D, rendered like a hand-drawn anime background. All on Max effort. Opus 5 took the longest but delivered the most varied scenery: clean dark outlines, flat cel-shaded color bands, dense street details down to the vending machine signage. Fable paid more attention to details, and while GPT 5.6 Sol was 3-4x cheaper and the fastest, but the render shows it: sparse, washed out, barely styled. Opus 5: 1hr 21min · $26.7 Fable 5: 1hr 5min · $35 GPT 5.6 Sol: 41min · $7.1

GMI Cloud

54,140 views • 2 months ago

Claude Opus 5.5 vs GPT-6 Astra in 3D gaming. From a single prompt: “Build the highest-quality playable PUBG you can.” I went to sleep. When I woke up, both had built a fully playable game🤯 Opus worked for 10 hours end to end, while Astra took just 3.

Claude Opus 5.5 vs GPT-6 Astra in 3D gaming. From a single prompt: “Build the highest-quality playable PUBG you can.” I went to sleep. When I woke up, both had built a fully playable game🤯 Opus worked for 10 hours end to end, while Astra took just 3.

Emm | scenario.com

58,207 views • 13 days ago

Opus 4.8 vs GLM 5.2 everyone is praising Glm on my timeline, so i had to test it myself > both models were given the same prompt > GLM was super fast and used like 2% of my weekly limit > Opus took over 20 mins and used like 3% of weekly limits which one do you think won?

Opus 4.8 vs GLM 5.2 everyone is praising Glm on my timeline, so i had to test it myself > both models were given the same prompt > GLM was super fast and used like 2% of my weekly limit > Opus took over 20 mins and used like 3% of weekly limits which one do you think won?

J A Z I I

48,130 views • 3 months ago

Let's keep benchmarking with the Night train this time, with GPT-6 Sol and GPT-6 Luna, so here are all four! 🚀 I gave each model the exact same prompt: “Build a Night train.” •Opus 5.5 • GPT-6 Astra • GPT-6 Sol • GPT-6 Luna Something that really surprised me: GPT-6 Sol produced almost the exact same rocket launch as Opus 5.5! The colors are slightly different, but the overall result is remarkably similar. For this prompt, I’d even put Sol ahead of Astra. I’m seriously impressed by Sol, especially at half the API price of Opus 5.5! 🤯 I’m starting to use this approach in my own workflow. I kept one Codex subscription so I can run a bunch of Sol sub-agents while keeping my main agent on Astra. Sol is so cheap for what it can do! Knowing when to switch models based on the task, the quality you need, and the cost is becoming an essential skill in this new AI era.

Let's keep benchmarking with the Night train this time, with GPT-6 Sol and GPT-6 Luna, so here are all four! 🚀 I gave each model the exact same prompt: “Build a Night train.” •Opus 5.5 • GPT-6 Astra • GPT-6 Sol • GPT-6 Luna Something that really surprised me: GPT-6 Sol produced almost the exact same rocket launch as Opus 5.5! The colors are slightly different, but the overall result is remarkably similar. For this prompt, I’d even put Sol ahead of Astra. I’m seriously impressed by Sol, especially at half the API price of Opus 5.5! 🤯 I’m starting to use this approach in my own workflow. I kept one Codex subscription so I can run a bunch of Sol sub-agents while keeping my main agent on Astra. Sol is so cheap for what it can do! Knowing when to switch models based on the task, the quality you need, and the cost is becoming an essential skill in this new AI era.

Tony

112,633 views • 12 days ago

Gemini 4 Pro vs Opus 5 (max) i gave both models same prompt to build 3D dragon using three.js the hype around Gemini 4 Pro is insane so here's a direct comparison against Opus 5 on max effort tbf Gemini does keeps up with Opus 5's performance which is on max effort and that's impressive in itself, who do you think better? prompt used: create a 3D dragon using three.js, use white theme background so main object is visible

Gemini 4 Pro vs Opus 5 (max) i gave both models same prompt to build 3D dragon using three.js the hype around Gemini 4 Pro is insane so here's a direct comparison against Opus 5 on max effort tbf Gemini does keeps up with Opus 5's performance which is on max effort and that's impressive in itself, who do you think better? prompt used: create a 3D dragon using three.js, use white theme background so main object is visible

Tim Jayas

104,140 views • 18 days ago

Opus 4.8 vs MiniMax M3 tested both on default settings with the same prompt > Opus one shotted everything in 7 minutes > M3 needed an extra prompt to fix the "break block" feature and took 20+ minutes both got super close, judge both and lemme know which one looks better?

Opus 4.8 vs MiniMax M3 tested both on default settings with the same prompt > Opus one shotted everything in 7 minutes > M3 needed an extra prompt to fix the "break block" feature and took 20+ minutes both got super close, judge both and lemme know which one looks better?

J A Z I I

67,862 views • 4 months ago

i just compared DeepSeek-v4.1-Flash against Opus 5 gave same prompt to both models to build ocean sandbox using three.js DeepSeek-v4.1-Flash was almost 90% cheaper and 50% faster than Opus 5 💀 maybe the benchmarks are not broken.. do you think DeepSeek is better?

i just compared DeepSeek-v4.1-Flash against Opus 5 gave same prompt to both models to build ocean sandbox using three.js DeepSeek-v4.1-Flash was almost 90% cheaper and 50% faster than Opus 5 💀 maybe the benchmarks are not broken.. do you think DeepSeek is better?

Tim Jayas

28,561 views • 26 days ago

SAKANA FUGU ULTRA vs. CLAUDE OPUS 4.8 RESULTS Prompt: "build a really high quality single html file crossy road game with three.js" Sakana Fugu Ultra: - Tokens Used: ~89k ($7.32) - Time Elapsed: 22 minutes - Issues: inverted directional turn, wonky camera, no sfx, not identical to Crossy Road game Claude Opus 4.8 Ultracode: - Tokens Used: ~940k (~$37.85) - Time elapsed: 79 minutes - Issues: got stuck twice in a retry loop (had to prompt to self-correct), wrong character position after restart, difficult from the start (whereas Fugu's version got significantly more difficult as you progress, which is the correct behaviour) I think in terms of application functionality, quality, and design, Opus won. In terms of model speed and performance, Fugu on Opencode won. What are your thoughts? Comment down below who you think won! ⬇️

SAKANA FUGU ULTRA vs. CLAUDE OPUS 4.8 RESULTS Prompt: "build a really high quality single html file crossy road game with three.js" Sakana Fugu Ultra: - Tokens Used: ~89k ($7.32) - Time Elapsed: 22 minutes - Issues: inverted directional turn, wonky camera, no sfx, not identical to Crossy Road game Claude Opus 4.8 Ultracode: - Tokens Used: ~940k (~$37.85) - Time elapsed: 79 minutes - Issues: got stuck twice in a retry loop (had to prompt to self-correct), wrong character position after restart, difficult from the start (whereas Fugu's version got significantly more difficult as you progress, which is the correct behaviour) I think in terms of application functionality, quality, and design, Opus won. In terms of model speed and performance, Fugu on Opencode won. What are your thoughts? Comment down below who you think won! ⬇️

Mark Santos

685,792 views • 3 months ago

Spend of OpenAI vs Anthropic vs Open (Vercel AI Gateway, last 2 months) • Anthropic still #1 in spend, but went 69% → 40% • OpenAI: 10% → 24% in spend • GPT-6 Astra + GPT 5.6 Sol are ripping • OpenAI now leads in tokens # • Kimi K3 + DeepSeek took ~half of Anthropic's loss • Opus 5.5 is up to 10% of spend in 2 days • OpenAI is 62% of image generations Watch here:

Spend of OpenAI vs Anthropic vs Open (Vercel AI Gateway, last 2 months) • Anthropic still #1 in spend, but went 69% → 40% • OpenAI: 10% → 24% in spend • GPT-6 Astra + GPT 5.6 Sol are ripping • OpenAI now leads in tokens # • Kimi K3 + DeepSeek took ~half of Anthropic's loss • Opus 5.5 is up to 10% of spend in 2 days • OpenAI is 62% of image generations Watch here:

Guillermo Rauch

207,049 views • 12 days ago