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.

🤯KIMI K3 ABSOLUTELY MOGS! BEATING Opus 4.8, GPT 5.5, and even Fable 5 in multiple benchmarks. They scored 1688 on GDPval-AA v2 🔥 This is a completely different breed of open-source models Kimi creates better games and front-end designs than Fable 5, but it's 8x cheaper! The results coming... show more

Mark Santos

4,047 subscribers

128,202 views • 2 months ago •via X (Twitter)

Science & Technology Gaming

Anya Rossi• Live Now

Private livecam show

29 Comments

Mihnea Peteu2 months ago

true

Mark Santos2 months ago

post some more tests

AshutoshShrivastava2 months ago

Incredible man..

Mark Santos2 months ago

Thanks! I posted a few more results here:

Ronaldo Ballecer2 months ago

It's really good. But I saw a post the 20 dollar sub can one shot the 5 hour limit and still not finish. So it should be plan for the first 5 hour limit then implement in the next and add only features or sub-features for more complex tasks.

linyishan2 months ago

早上立马订阅了一年，K3正式进入生产线

Shubham Sharma | Video Editor2 months ago

8x cheaper while beating that many benchmarks is a strong claim to watch play out

Nulledge2 months ago

我不信任国产的，肯定又是蒸馏

Mark Santos2 months ago

try it out yourself

AI Mastery Guide2 months ago

8x cheaper while beating that many benchmarks is a strong claim to watch play out

Joy Haines2 months ago

cool～The smoothness of the interactions is what stands out to me.

The Full Read2 months ago

More will come

Maximilian2 months ago

What a headline 😂😂😂

Adeel Khan (عدیل)2 months ago

i dont understand what will be the outcome of this race?

WorldClaw2 months ago

🔥 Get Kimi K3 at the Lowest Price Online — 30% Off: Cache Hit: $0.30 → $0.21 / 1M Cache Miss: $3.00 → $2.10 / 1M Output: $15.00 → $10.50 / 1M

Ty7725212 months ago

注册可领会员额度

Joey2 months ago

But have you built anything with it?

A Salty Vet2 months ago

Can you prove you used the same prompt and the same model settings for both?

Isaac Rojas2 months ago

Fake... Impossible

💡Blue 🚀🌙2 months ago

@Kimi_Moonshot how’s a 8GB GGUF pls

Ask-Zai2 months ago

You're lying, you're lying! Actually, put it to work. It doesn't come close. Stop falling for the hype! China is not about to take $15 per mill from anybody. They priced themselves out of the market, and you're hyping up a model that sits somewhere between Sonnet 5 and Opus 4.8, realistically.

安叫兽|Bird🕊️ 🔶 BNB2 months ago

碾压先别急，等实测多跑几轮

Setumeni Effy2 months ago

Orca router is giving free KIMI K3 CREDITS,grab whilst it's valid

Arindam Majumder 𝕏2 months ago

This is cool, Also planning to test it against GLM & Minimax models!

Davidd Tech2 months ago

I'll be testing it to backtest and automate a new trading strategy. Can't wait to share the results.

Ashutosh Mishra2 months ago

Impressive drop—Kimi K3 is cooking 🔥 When do the full tests drop?

Sebastian Buzdugan2 months ago

1m context matters less when tool loops make latency the product bottleneck

Bizlink2 months ago

is only way to use KIMI K3 is via API?

Nur Web32 months ago

Also the price💩🤡

Related Videos

Kimi K3 absolutely mogs every open source model this is on par , head on head all case i tried in coding with fable , i feel weird to write , but sometimes it output better quality than fable too I don't know how to comprehend this , i have lots of test and comparison 😼

Kimi K3 absolutely mogs every open source model this is on par , head on head all case i tried in coding with fable , i feel weird to write , but sometimes it output better quality than fable too I don't know how to comprehend this , i have lots of test and comparison 😼

Chetaslua

131,304 views • 2 months ago

Kimi K3 Standard’s first shot at my indie spaceship game! Without a shadow of a doubt, this is better than GPT-5.5’s first pass. It’s crazy that we already have an open-source model in the GPT-5.5 to GPT-5.6 class. The estimated API cost for this was just $2.50 worth of tokens. Fable 5: $22 GPT-5.5: $14 I will say that Fable 5 made the game look more visually impressive, but the gap is not that large. I think I could easily get Kimi to match its visual quality within a few iterations. What surprised me most was that Kimi’s version felt much more cohesive and coherent, with fewer bugs than GPT-5.5’s.

Kimi K3 Standard’s first shot at my indie spaceship game! Without a shadow of a doubt, this is better than GPT-5.5’s first pass. It’s crazy that we already have an open-source model in the GPT-5.5 to GPT-5.6 class. The estimated API cost for this was just $2.50 worth of tokens. Fable 5: $22 GPT-5.5: $14 I will say that Fable 5 made the game look more visually impressive, but the gap is not that large. I think I could easily get Kimi to match its visual quality within a few iterations. What surprised me most was that Kimi’s version felt much more cohesive and coherent, with fewer bugs than GPT-5.5’s.

Chris

47,926 views • 2 months ago

fable 5.2 > gpt 6 astra tested both models with same prompt at high reasoning and results came out really different fable next model entered stealth testing today, so i don’t think it's coming out anytime soon from early testing: > huge step up from current fable > output looks better than astra > slower and expensive still running more tests and will drop the outputs soon

fable 5.2 > gpt 6 astra tested both models with same prompt at high reasoning and results came out really different fable next model entered stealth testing today, so i don’t think it's coming out anytime soon from early testing: > huge step up from current fable > output looks better than astra > slower and expensive still running more tests and will drop the outputs soon

J A Z I I

62,958 views • 19 days ago

KIMI K3 is here, and it blew my mind 🤯 yes, it is expensive and very slow Took over 30 minutes, and blew an ENTIRE $20 kimi sub before it even finished the one prompt for this game. BUT OMG... the output geniuinly has fable 5 level magic built into it, this model falls between gpt 5.6 and fable 5 imo. you can play the game at kimisurfers (dot) com right now, and see what I mean. This model is too expensive to replace fable 5, BUTT it shows that the chinese open source labs are CATCHING anthropic and open ai FASTTT.

KIMI K3 is here, and it blew my mind 🤯 yes, it is expensive and very slow Took over 30 minutes, and blew an ENTIRE $20 kimi sub before it even finished the one prompt for this game. BUT OMG... the output geniuinly has fable 5 level magic built into it, this model falls between gpt 5.6 and fable 5 imo. you can play the game at kimisurfers (dot) com right now, and see what I mean. This model is too expensive to replace fable 5, BUTT it shows that the chinese open source labs are CATCHING anthropic and open ai FASTTT.

Max Blade

129,044 views • 2 months ago

fable 5.5 is about to cook everyone some users are getting routed to newer fable 5.5 and outputs are just too good been testing model for the last few days and it's a huge step up from fable 5.1 but still expensive just look at details in this tests, super crazy and even better than opus 5.5 model is expected to drop in this month, most likely first 2 weeks but let's see when do you think we will see model out?

fable 5.5 is about to cook everyone some users are getting routed to newer fable 5.5 and outputs are just too good been testing model for the last few days and it's a huge step up from fable 5.1 but still expensive just look at details in this tests, super crazy and even better than opus 5.5 model is expected to drop in this month, most likely first 2 weeks but let's see when do you think we will see model out?

J A Z I I

38,604 views • 4 days ago

Fable 5 is coming back! (not official, but all signs point to 'SOON'') Sakana AI released "Fugu" and it's REALLY good on Andrej Karpathy's AutoResearch (better than GPT-5.5 and Opus 4.8) also, Sam Altman unveils "Jalapeno", the AI inference chip designed in part by... openAI models:

Fable 5 is coming back! (not official, but all signs point to 'SOON'') Sakana AI released "Fugu" and it's REALLY good on Andrej Karpathy's AutoResearch (better than GPT-5.5 and Opus 4.8) also, Sam Altman unveils "Jalapeno", the AI inference chip designed in part by... openAI models:

Wes Roth

11,712 views • 3 months ago

Rockstar spent 7 years, 2,000+ developers, and $500 million to build Red Dead Redemption 2. Kimi K3 rebuilt the same scene in 10 hours. One prompt. 4 million tokens. It's open source. 2.8 trillion parameters. A 1 million token context window. It beats Claude Opus 4.8 and GPT-5.6. It sits on par with Fable 5. Fable 5 results, at Sonnet pricing. The wall between you and a AAA game used to be a studio. Now it's a prompt.

Rockstar spent 7 years, 2,000+ developers, and $500 million to build Red Dead Redemption 2. Kimi K3 rebuilt the same scene in 10 hours. One prompt. 4 million tokens. It's open source. 2.8 trillion parameters. A 1 million token context window. It beats Claude Opus 4.8 and GPT-5.6. It sits on par with Fable 5. Fable 5 results, at Sonnet pricing. The wall between you and a AAA game used to be a studio. Now it's a prompt.

Dep

99,354 views • 2 months ago

I couldn't believe the results of this benchmarking test. I blind-tested 6 frontier models — Sonnet 5, Opus 4.8, Fable 5, GPT 5.5, GLM 5.2, and Kimi 2.5 — on knowledge work, not engineering. Writing. Analysis. Design. Vibe coding. Subagent simulations. The stuff we actually do all day. Same prompts, each model running its own subagent, every output graded blind before the labels were revealed. The results: → GLM 5.2 (the dirt-cheap open-source model from China) took first → Sonnet 5 took second, beating Fable 5 for knowledge work → Opus 4.8 got whooped Then I had Composer 2.5 judge every output independently — and it picked Fable 5 almost across the board. My blind picks and the AI judge completely disagreed. Full breakdown, method, and prompts in the video below. Which model are you running as your daily driver right now?

I couldn't believe the results of this benchmarking test. I blind-tested 6 frontier models — Sonnet 5, Opus 4.8, Fable 5, GPT 5.5, GLM 5.2, and Kimi 2.5 — on knowledge work, not engineering. Writing. Analysis. Design. Vibe coding. Subagent simulations. The stuff we actually do all day. Same prompts, each model running its own subagent, every output graded blind before the labels were revealed. The results: → GLM 5.2 (the dirt-cheap open-source model from China) took first → Sonnet 5 took second, beating Fable 5 for knowledge work → Opus 4.8 got whooped Then I had Composer 2.5 judge every output independently — and it picked Fable 5 almost across the board. My blind picks and the AI judge completely disagreed. Full breakdown, method, and prompts in the video below. Which model are you running as your daily driver right now?

JJ Englert

10,737 views • 3 months ago

$SITUATION EXPLAINED: Kimi K3 just beat Fable on a major coding benchmark, at a fraction of the price. • Kimi K3 beat Fable on Frontend Code Arena • The gap between Kimi and Fable is bigger than the gap between Fable and Sol • It also smashes Opus outright, while being priced the same as Sonnet, $3/$15 per million tokens • Sonnet 5 High currently sits in 10th place on this leaderboard at that same price point • The generational jump is dramatic: Kimi K2.6 ranked 18th on this benchmark, K3 jumped 17 spots to take the top spot • K3 ranked #1 in 6 of 7 tested domains: brand and marketing, reference-based design, data and analytics, consumer products, simulations, and content creation tools, it placed #2, only in gaming, behind Fable • Full model weights are set to release July 27th Theo Jaffee: "Imagine if Anthropic were a public company today, their stock would be down 20%, maybe more, enterprises are probably not gonna be spending $10 and $50 on Fable when they can instead be spending $3 and $15 on Kimi K3."$

SITUATION EXPLAINED: Kimi K3 just beat Fable on a major coding benchmark, at a fraction of the price. • Kimi K3 beat Fable on Frontend Code Arena • The gap between Kimi and Fable is bigger than the gap between Fable and Sol • It also smashes Opus outright, while being priced the same as Sonnet, $3/$15 per million tokens • Sonnet 5 High currently sits in 10th place on this leaderboard at that same price point • The generational jump is dramatic: Kimi K2.6 ranked 18th on this benchmark, K3 jumped 17 spots to take the top spot • K3 ranked #1 in 6 of 7 tested domains: brand and marketing, reference-based design, data and analytics, consumer products, simulations, and content creation tools, it placed #2, only in gaming, behind Fable • Full model weights are set to release July 27th Theo Jaffee: "Imagine if Anthropic were a public company today, their stock would be down 20%, maybe more, enterprises are probably not gonna be spending $10 and $50 on Fable when they can instead be spending $3 and $15 on Kimi K3."

MTS

132,930 views • 2 months ago

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua

Chris

250,919 views • 3 months ago

You can now choose which model builds your app on Caffeine. The latest models are all in there: Opus 5.5 Fable 5.1 GPT-6 Astra GPT-6 Sol Kimi K3 Sonnet 5 DeepSeek V4.1 Flash Plan a whole new app with a frontier model, then switch to a faster, cheaper one for quick questions and small changes. It works on every plan, starting today.

You can now choose which model builds your app on Caffeine. The latest models are all in there: Opus 5.5 Fable 5.1 GPT-6 Astra GPT-6 Sol Kimi K3 Sonnet 5 DeepSeek V4.1 Flash Plan a whole new app with a frontier model, then switch to a faster, cheaper one for quick questions and small changes. It works on every plan, starting today.

caffeine

15,932 views • 13 days ago

I was wrong about Kimi K3 Just tried it in Claude Code and it is Fable 5 level for sure Far better than GPT-5.6 Sol at least at front-end It is really slow and consumes a lot of tokens but it is so good at completing its task, I like what I see here Kimi.ai

I was wrong about Kimi K3 Just tried it in Claude Code and it is Fable 5 level for sure Far better than GPT-5.6 Sol at least at front-end It is really slow and consumes a lot of tokens but it is so good at completing its task, I like what I see here Kimi.ai

Hamza

258,763 views • 2 months ago

Qwen 3.8 will be benchmaxxed slop second to fable 5 is such a hype statement , its not even close to kimi k3 and GPT-5.6 sol you can test it yourself on the qwen chat website currently available > token hungry > not that good as advertised , will test more The best part of kimi was that in blog they themselves wrote its not comparable to fable 5 and sol 5.6 in bunch of user experience stuff We need more truth like this in our industry , other than that i will run my vision test

Qwen 3.8 will be benchmaxxed slop second to fable 5 is such a hype statement , its not even close to kimi k3 and GPT-5.6 sol you can test it yourself on the qwen chat website currently available > token hungry > not that good as advertised , will test more The best part of kimi was that in blog they themselves wrote its not comparable to fable 5 and sol 5.6 in bunch of user experience stuff We need more truth like this in our industry , other than that i will run my vision test

Chetaslua

127,047 views • 2 months ago

Grok should be praised a lot , this is one of the biggest launch > priced way less than even kimi k2.7 , glm 5.2 > on artificial code analysis only behind fable 5 and gpt 5.5 xhigh > this is well rounded launch i will showcase a 3d test that will blow everyone mind

Grok should be praised a lot , this is one of the biggest launch > priced way less than even kimi k2.7 , glm 5.2 > on artificial code analysis only behind fable 5 and gpt 5.5 xhigh > this is well rounded launch i will showcase a 3d test that will blow everyone mind

Chetaslua

25,644 views • 3 months ago

My honest take on Kimi.ai K3 👀 As soon as I got access to Kimi, I put it through the exact same 3D football stadium challenge I had previously given Claude Fable 5. Fable 5 finished in under an hour. Kimi took almost 3 hours 🥵 At first, that was a very bad impression but i decided to see what's taking it this much of time. It was running E2E tests, validating desktop, tablet, and mobile, taking screenshots, finding failures, fixing them, even adapting for low end hardware and low FPS before moving on. All these that Fable 5 never did. None of it because it wasn't able to run this WebGL app on a headless browser. Kimi also shipped a clean React + Three.js codebase with proper components while Fable, as you might have checked codebase, generated one big HTML file with everything stuffed in. With all of this happening, it felt like I was doing more "Vibe Coding" with Fable 5 and more "Vibe Engineering" with Kimi K3. It feels like it's spending more time making sure the code actually works and easily scalable. Really impressed so far. More Kimi K3 experiments coming soon. Code (Kimi): Code (Fable): Live (Kimi hosted):

My honest take on Kimi.ai K3 👀 As soon as I got access to Kimi, I put it through the exact same 3D football stadium challenge I had previously given Claude Fable 5. Fable 5 finished in under an hour. Kimi took almost 3 hours 🥵 At first, that was a very bad impression but i decided to see what's taking it this much of time. It was running E2E tests, validating desktop, tablet, and mobile, taking screenshots, finding failures, fixing them, even adapting for low end hardware and low FPS before moving on. All these that Fable 5 never did. None of it because it wasn't able to run this WebGL app on a headless browser. Kimi also shipped a clean React + Three.js codebase with proper components while Fable, as you might have checked codebase, generated one big HTML file with everything stuffed in. With all of this happening, it felt like I was doing more "Vibe Coding" with Fable 5 and more "Vibe Engineering" with Kimi K3. It feels like it's spending more time making sure the code actually works and easily scalable. Really impressed so far. More Kimi K3 experiments coming soon. Code (Kimi): Code (Fable): Live (Kimi hosted):

The Bugged Dev

579,952 views • 2 months ago

I tested Fable 5.1 vs Kimi K3 vs GPT 5.6 Sol vs Gemini 3.8 Flash I capped Fable, Kimi & Sol at $2 and asked them to generate this beach scene. Fable 5.1: Looks good at first glance, but made many mistakes, like people sitting on the volleyball court. Kimi K3: It did well. There were no major bugs like in Fable 5.1, and everything looks good. Sol: Bad at 3D scenes as usual, but Astra will definitely fix that. Gemini 3.8 Flash: I ran it in a loop for 35+ mins and it cost $0.95. It didn’t understand what it was fixing. The output here is the enhanced version. IMO, not even Terra level. Gemini's benchmarks say Opus 5-level, but maybe not for spatial understanding. Gemini has other use cases. Which one did the best job?

I tested Fable 5.1 vs Kimi K3 vs GPT 5.6 Sol vs Gemini 3.8 Flash I capped Fable, Kimi & Sol at $2 and asked them to generate this beach scene. Fable 5.1: Looks good at first glance, but made many mistakes, like people sitting on the volleyball court. Kimi K3: It did well. There were no major bugs like in Fable 5.1, and everything looks good. Sol: Bad at 3D scenes as usual, but Astra will definitely fix that. Gemini 3.8 Flash: I ran it in a loop for 35+ mins and it cost $0.95. It didn’t understand what it was fixing. The output here is the enhanced version. IMO, not even Terra level. Gemini's benchmarks say Opus 5-level, but maybe not for spatial understanding. Gemini has other use cases. Which one did the best job?

Bhavy☄️

33,971 views • 1 month ago

DeepSeek V4 Flash completely failed this test. Compared to Opus 4.8, GPT-5.6 Sol, Kimi K3, and the other current top models, it’s honestly not good. The gap is massive. Against Luna, however, it performs similarly well. Both have different strengths and weaknesses, so I still need to test them more. The weird part: the Pi harness performed worse than OpenCode for DeepSeek. More tests are coming, guys. Don’t worry

DeepSeek V4 Flash completely failed this test. Compared to Opus 4.8, GPT-5.6 Sol, Kimi K3, and the other current top models, it’s honestly not good. The gap is massive. Against Luna, however, it performs similarly well. Both have different strengths and weaknesses, so I still need to test them more. The weird part: the Pi harness performed worse than OpenCode for DeepSeek. More tests are coming, guys. Don’t worry

OmedTheVibeCoder

26,166 views • 2 months ago

I tested GLM 5.2 on three real builds. A horror house game. A 3D stealth game. A Remotion marketing video. The results are exactly what I expect from Chinese open source coding models right now. The horror house has broken game logic. Collect all three keys, complete the objective, and the front door still won't open. The stealth game shipped with lighting so dark you can't see your own character. The Remotion video is rough. GLM 5.2 is faster than 5.1 and 10x cheaper than the frontier. But Opus 4.8 and GPT 5.5 are still in a different league for serious coding work. Chinese models keep missing the attention to detail that matters. I MISS FABLE 5 ALREADY. Full review live now.

I tested GLM 5.2 on three real builds. A horror house game. A 3D stealth game. A Remotion marketing video. The results are exactly what I expect from Chinese open source coding models right now. The horror house has broken game logic. Collect all three keys, complete the objective, and the front door still won't open. The stealth game shipped with lighting so dark you can't see your own character. The Remotion video is rough. GLM 5.2 is faster than 5.1 and 10x cheaper than the frontier. But Opus 4.8 and GPT 5.5 are still in a different league for serious coding work. Chinese models keep missing the attention to detail that matters. I MISS FABLE 5 ALREADY. Full review live now.

BridgeMind

24,681 views • 3 months ago

Grok 4.5 is out!!! here is what you need to know : On cursor bench it matched fable 5 high at 83% cheaper, although the ui generation feels similar to gpt 5.5 in a bad way. Important to note, cursor bench was LEAKED to grok 4.5 and may have skewed the results! My initial thoughts are this could be a insanely cheap opus 4.8 level model that runs insanely fast. Will you be using grok build?

Grok 4.5 is out!!! here is what you need to know : On cursor bench it matched fable 5 high at 83% cheaper, although the ui generation feels similar to gpt 5.5 in a bad way. Important to note, cursor bench was LEAKED to grok 4.5 and may have skewed the results! My initial thoughts are this could be a insanely cheap opus 4.8 level model that runs insanely fast. Will you be using grok build?

Max Blade

19,431 views • 3 months ago

Opus 5 crushed Fable 5 at 3D destruction physics for 2x cheaper! We gave four models the same task: build three self-contained HTML scenes with real physics Prompts: - A tornado that sucks in a whole field - A wrecking ball taking down an apartment block - An overloaded truck collapsing a truss bridge Outputs: - Opus 5: 55.9K tokens, $1.40 - Fable 5: 55.1K tokens, $2.82 - Kimi K3: 35.7K tokens, $0.55 - GPT 5.6: 20.1K tokens, $0.31 Opus got all three right unlike the other models. Houses fly up the funnel and out the top, the wall breaks where the ball hits and the rubble piles up, the bridge drops the truck into the river. Fable had almost nothing on the ground for the tornado to pick up, its building collapsed on its own before the ball even touched it and its bridge blew into sticks all at once. GPT is the cheapest here but its ball never reached the building at all and its bridge fell apart in a way nothing falls apart in real life. Kimi K3, the new Chinese frontier model, ended up in the same place as GPT

Opus 5 crushed Fable 5 at 3D destruction physics for 2x cheaper! We gave four models the same task: build three self-contained HTML scenes with real physics Prompts: - A tornado that sucks in a whole field - A wrecking ball taking down an apartment block - An overloaded truck collapsing a truss bridge Outputs: - Opus 5: 55.9K tokens, $1.40 - Fable 5: 55.1K tokens, $2.82 - Kimi K3: 35.7K tokens, $0.55 - GPT 5.6: 20.1K tokens, $0.31 Opus got all three right unlike the other models. Houses fly up the funnel and out the top, the wall breaks where the ball hits and the rubble piles up, the bridge drops the truck into the river. Fable had almost nothing on the ground for the tornado to pick up, its building collapsed on its own before the ball even touched it and its bridge blew into sticks all at once. GPT is the cheapest here but its ball never reached the building at all and its bridge fell apart in a way nothing falls apart in real life. Kimi K3, the new Chinese frontier model, ended up in the same place as GPT

atomic.chat

1,483,840 views • 2 months ago