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 Extra High vs. Kimi K3 Swarm - ECHO Start Menu Both models received the exact same prompt. I’m shocked at the quality Kimi K3 was able to output here. Its overall visual quality is above GPT-6’s and even above the menu from the actual game. However, it took... significantly longer - around 3.5 hours versus GPT-6’s 42 minutes. Roughly 5× longer. GPT-6’s demo felt more realistic and stayed a lot closer to how the original menu looks. Kimi added something that GPT-6 missed, which was the interactive eye tracking. Kimi’s eyeball follows (albeit blurry and in a slightly weird way) where you click on the start screen. GPT-6’s doesn’t. • GPT-6 Extra High: approximately 46,000 generated output tokens - $2.30 in API-equivalent output cost. • Kimi K3 Swarm: estimated 250,000 generated output tokens - $3.75 in API-equivalent output cost.show more

Chris

65,941 subscribers

119,119 views • 5 days ago •via X (Twitter)

Science & Technology Gaming

Anya Rossi• Live Now

Private livecam show

36 Comments

Axi5 days ago

I think Astra def wins. it looks almost identical to the original

Chris5 days ago

I agree, Kimi quality though is the best I’ve seen

Axi5 days ago

If the precedent is about photorealism, Astra will give you a very photorealistic result. I think goal-setting played a pivotal role in deciding the outcome.

Chris5 days ago

I agree, Astra could’ve done better if realism was the goal

Hakm5 days ago

KIMI K3 max & Swarms is not fair tho

Jonas5 days ago

Kimi just appears to be distorting a 2D image in order to give the illusion of the eyeball tracking the menu. Did you give them assets, or did they have to find them? And was 3D on the table, or were they stuck with 2D?

Curline Zephirin5 days ago

Kimi's output is highly realistic, but for a game menu, that level of realism is actually a drawback

Daniel Monge5 days ago

Kimi is not better, though. the skin job is very bad. everything deforms together like it's one mesh and not a mesh for the eyball separate from the mesh of the skin. The texture seems less blurry and higher quality, though. It also cheated the blinking motion by making a picture of the closed eyes appear with a vertical swipe transition instead of animating the mesh.

Christopher Malili5 days ago

No mention of the dilating pupil? Astra's eye is realistically reaching to brightness. That's huge

Jared Smith5 days ago

kimi is absolute fire at front end shit

Nagi5 days ago

In terms of actual quality and movement, Astra wins 100% if you look at Kimi the blink is just a PNG swipe down and up, and the eye movement is only around the iris itself not the rest of the eye, looks uncanny because the rest of the eye is dead. Whereas Astra's is more alive.

silent5 days ago

Astra absolutely blows that one away; the other one might look like it has higher resolution, but Astra completely crushes it when it comes to dynamic eyewear movement and pupil contraction.

LLMnonymous (Pro-AI ❇️⏫)5 days ago

Unfair comparison ngl, it should gpt 6 astra max swarm vs Kimi k3 swarm, don’t try to save your usage

Han5 days ago

Kimi is literally morphed 2d texture slop lol wtf, also the GUI is slop too

Bilal Bakr5 days ago

Man GPT 6 made sure to nail the smallest details Look at how the ye pupils get bigger/smaller

Vlad Oreshkov5 days ago

42 minutes vs 3.5 hours is the part I’d pick. Kimi looking nicer doesn’t matter if it takes 5x longer. For Remie I need the one that finishes in a session I can actually afford.

Hussain Hashim | Building SundayBack5 days ago

@ChrisGPT sometimes it's wild how lesser-known models outperform the big names. I've seen it too, their training focus must be spot on. Wonder what datasets they're using!

KURO4 days ago

No one mentioning how the eye tries to focus on Astra?! Easy winner for me

𝕱𝖚𝖑𝖑 𝕶𝖊𝖑𝖑𝖞5 days ago

more detail/resolution doesn’t necessarily mean that the output is better

Franz Vorenkamp4 days ago

GPT’s is way better

snaps💀🔺4 days ago

Astra's output is better here.

Apollon Foivos Bakis5 days ago

The quality gap versus runtime is interesting.

Stats Wire5 days ago

Kimi won

Endling5 days ago

The longer time for k3 seems worth it. It looks great.

AI Mastery Guide4 days ago

Kimi K3 beating GPT-6 here??

Jason Zhang5 days ago

The first-pass visual quality is impressive. I’d really like to see which one holds up better after 5–10 iterations.

Saint Jacques5 days ago

How are u even doing this? How do u prompt it like that

volovuk5 days ago

Solid writeup — actual numbers, actual tradeoffs, no fake urgency. Two things worth flagging though: this is a sample size of one prompt, and “3.5 hours” for Kimi is wall-clock time that likely includes retries/iteration, not raw generation time — worth knowing if that gap holds on a second, unrelated task before calling it a general 5x speed difference.

Carlo Taleon5 days ago

How does Kimi K3 cost $3.75 yet their $19 Moderato sub lasts me 30 minutes till it's exhausted for the 5 hr limit.

Webster | JARVIS5 days ago

kimi taking 5x longer but only costing ~60% more is honestly the wildest part of these benchmarks. token pricing is gonna get weird real fast.

Meet Pandya5 days ago

This looks like three separate scores: visual preference, fidelity to the original, and working interactions. For a recreation task, I’d keep those separate. A prettier redesign can still miss the brief, while an accurate screenshot can miss the behavior.

UX Mostofa ✦4 days ago

Stylish and modern design!

The Matrix OS4 days ago

Bruh this might take time if human dose it like Kimi k3 lol

rain0x5 days ago

any way you could share the kimi k3 files? it looks beautiful lol

Outdated Often5 days ago

You found a cool fringe case that k3 beat astra in something on graphics lol, cool!

Guilty Geek5 days ago

Kimi >>> astra

Related Videos

Kimi K3 just 3 shotted a whole walkable voxel town with drivable cars — Voxelville, around $3.24 in API usage. The same token cost would be $10.80 with Fable 5 and $6 with GPT 5.6 Sol. Fable 5 built its own Maplewood, GPT 5.6 Sol built Willowwick, but on price/quality Kimi K3 just cooked both of them. The era of free indie game development is closer than you think!

Kimi K3 just 3 shotted a whole walkable voxel town with drivable cars — Voxelville, around $3.24 in API usage. The same token cost would be $10.80 with Fable 5 and $6 with GPT 5.6 Sol. Fable 5 built its own Maplewood, GPT 5.6 Sol built Willowwick, but on price/quality Kimi K3 just cooked both of them. The era of free indie game development is closer than you think!

Kirill

65,087 views • 1 month 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 • 1 month ago

MY FIRST GAME OUTPUT WITH GPT-6 ASTRA IT ONE-SHOTTED THIS CALL OF DUTY GAME IN 30 MINUTES!!! GPT-6 ASTRA IS THE FASTEST MODEL ON THE MARKET. THE SAME PROMPT TOOK FABLE 5.1 ALMOST 5 HRS AND IT CONSUMED A FRACTION OF THE TOKENS FABLE 5.1 DID.

MY FIRST GAME OUTPUT WITH GPT-6 ASTRA IT ONE-SHOTTED THIS CALL OF DUTY GAME IN 30 MINUTES!!! GPT-6 ASTRA IS THE FASTEST MODEL ON THE MARKET. THE SAME PROMPT TOOK FABLE 5.1 ALMOST 5 HRS AND IT CONSUMED A FRACTION OF THE TOKENS FABLE 5.1 DID.

hiraeth

36,888 views • 7 days ago

Just tested Kimi.ai K3 against GPT-5.6 and Grok 4.5 on the same task: build a Subway Surfers game. Kimi K3 was my favorite. Better UI, smoother gameplay, and the overall experience felt more polished. GPT-5.6 was solid too, while Grok 4.5 fell behind on the UI. The interesting part is that all three needed at least one follow-up prompt. Kimi also took a bit longer to generate, but the extra time paid off. Ran Kimi K3 through Nebius Token Factory. Low inference cost + a really capable open source model is a great combo.

Just tested Kimi.ai K3 against GPT-5.6 and Grok 4.5 on the same task: build a Subway Surfers game. Kimi K3 was my favorite. Better UI, smoother gameplay, and the overall experience felt more polished. GPT-5.6 was solid too, while Grok 4.5 fell behind on the UI. The interesting part is that all three needed at least one follow-up prompt. Kimi also took a bit longer to generate, but the extra time paid off. Ran Kimi K3 through Nebius Token Factory. Low inference cost + a really capable open source model is a great combo.

Arindam Majumder 𝕏

46,107 views • 1 month ago

GPT-6 Astra lost to Kimi K3 in chess, LOL I built a chess game where they play against each other via API. Thought Astra would win easily since it’s the best model right now. But Kimi K3 played surprisingly well and beat it. Is Astra nerfed or what?

GPT-6 Astra lost to Kimi K3 in chess, LOL I built a chess game where they play against each other via API. Thought Astra would win easily since it’s the best model right now. But Kimi K3 played surprisingly well and beat it. Is Astra nerfed or what?

Bhavy☄️

30,058 views • 2 days 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 • 2 months ago

Kimi K3 vs GPT 5.6 Sol (extra high) Voxel Death Star trench run I do want to point out that this was supposed to be a static world, but when I gave this prompt to Kimi K3, it said: “Since I can't output raster images, I've done something better: a real-time, fully animated voxel rendering of the assault in a single HTML file. —” So this ended up being an animated competition The way I would subjectively score it is that GPT 5.6 had a better lighting/effects but K3s was much smoother. You can definitely tell open source is getting really good.

Kimi K3 vs GPT 5.6 Sol (extra high) Voxel Death Star trench run I do want to point out that this was supposed to be a static world, but when I gave this prompt to Kimi K3, it said: “Since I can't output raster images, I've done something better: a real-time, fully animated voxel rendering of the assault in a single HTML file. —” So this ended up being an animated competition The way I would subjectively score it is that GPT 5.6 had a better lighting/effects but K3s was much smoother. You can definitely tell open source is getting really good.

Chris

50,121 views • 1 month ago

GPT-6 Astra smokes Claude Fable 5.1 in Blender 💨 We compared GPT-6 Astra and Fable 5.1 on a Porsche 911 GT3 RS build and the difference is visible from the very first shot Output: Astra: $132.03 • 2.58 hours Fable: $114.41 • 2.56 hours Astra's model is not only more detailed in every aspect, but also far closer to the original car, costing almost the same as Fable's blocky funny looking model, the difference is astonishing

GPT-6 Astra smokes Claude Fable 5.1 in Blender 💨 We compared GPT-6 Astra and Fable 5.1 on a Porsche 911 GT3 RS build and the difference is visible from the very first shot Output: Astra: $132.03 • 2.58 hours Fable: $114.41 • 2.56 hours Astra's model is not only more detailed in every aspect, but also far closer to the original car, costing almost the same as Fable's blocky funny looking model, the difference is astonishing

atomic.chat

129,995 views • 4 days 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

1,482,214 views • 1 month 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 • 8 days ago

⚡️ JUST IN: MUSK LAUNCHES GROK 4.5, CALLING IT "OPUS-CLASS" AI MODEL Musk just released Grok 4.5 on Grok Build, Cursor, and the SpaceXAI Console, calling it an "Opus-class" AI model. He says it is faster, more token-efficient and lower cost, with EU access expected by mid-July. Built on a 1.5 TRILLION parameter foundation model, it drops the same day as OpenAI's GPT-5.6. API pricing is $2 per million input tokens and $6 per million output tokens.

⚡️ JUST IN: MUSK LAUNCHES GROK 4.5, CALLING IT "OPUS-CLASS" AI MODEL Musk just released Grok 4.5 on Grok Build, Cursor, and the SpaceXAI Console, calling it an "Opus-class" AI model. He says it is faster, more token-efficient and lower cost, with EU access expected by mid-July. Built on a 1.5 TRILLION parameter foundation model, it drops the same day as OpenAI's GPT-5.6. API pricing is $2 per million input tokens and $6 per million output tokens.

Coin Bureau

50,488 views • 2 months ago

Found a way to run Kimi K3 for FREE with daily credits on 😳 it's a 2.8T parameter model. 1M context. beats Fable 5 on coding benchmarks. what you get for $0: -2.8 trillion parameters -1M context window -beats Fable 5 on SWE Marathon (42 vs 35) -beats Fable 5 on Program Bench (77.8) -topped BrowseComp (91.2) -native vision understanding What this replaces: -Paid frontier API costs for coding agents -Fable 5 at $30/M output tokens -GPT-5.6 Sol at $25/M output tokens how to use it (2 min): 1. Go to 2. Sign up with email 3. Start using K3 — it's the default model Also available on desktop app, CLI, and mobile. Important: Free daily credits reset. Full open weights dropping July 27. Rate limits apply on free tier. use this before the free tier gets crowded

Found a way to run Kimi K3 for FREE with daily credits on 😳 it's a 2.8T parameter model. 1M context. beats Fable 5 on coding benchmarks. what you get for $0: -2.8 trillion parameters -1M context window -beats Fable 5 on SWE Marathon (42 vs 35) -beats Fable 5 on Program Bench (77.8) -topped BrowseComp (91.2) -native vision understanding What this replaces: -Paid frontier API costs for coding agents -Fable 5 at $30/M output tokens -GPT-5.6 Sol at $25/M output tokens how to use it (2 min): 1. Go to 2. Sign up with email 3. Start using K3 — it's the default model Also available on desktop app, CLI, and mobile. Important: Free daily credits reset. Full open weights dropping July 27. Rate limits apply on free tier. use this before the free tier gets crowded

painn

256,645 views • 1 month ago

Opus 4.6 vs GPT-5.4 (High) (6/9) Testing out how well these models to with cloth physics simulation, and honestly both where pretty close here but my god I am shocked how good GPT 5.4 is with optimizing this scene whilst opus 4.6 felt quite janky and lower fps. GPT 5.4 also got the cutting working properly whilst Opus was just floating about. I do want to heavily stress the fact that making this prompt, Opus 4.6 cost the whole 100% of the session ($20 pro plan) + $3 in credits whilst GPT 5.4 only cost 10% of the usage. prompt: Build a premium Vite + React interactive cloth simulation of a cozy room curtain using real particle/constraint physics, with structural + shear springs, damping, collisions, and stable real-time deformation. Users should be able to drag the curtain, add wind, and cut constraints, while the experience stays polished, visually elegant, and numerically stable.

Opus 4.6 vs GPT-5.4 (High) (6/9) Testing out how well these models to with cloth physics simulation, and honestly both where pretty close here but my god I am shocked how good GPT 5.4 is with optimizing this scene whilst opus 4.6 felt quite janky and lower fps. GPT 5.4 also got the cutting working properly whilst Opus was just floating about. I do want to heavily stress the fact that making this prompt, Opus 4.6 cost the whole 100% of the session ($20 pro plan) + $3 in credits whilst GPT 5.4 only cost 10% of the usage. prompt: Build a premium Vite + React interactive cloth simulation of a cozy room curtain using real particle/constraint physics, with structural + shear springs, damping, collisions, and stable real-time deformation. Users should be able to drag the curtain, add wind, and cut constraints, while the experience stays polished, visually elegant, and numerically stable.

Dev Ed

414,465 views • 6 months ago

KIMI K3 USED MY ENTIRE MONTH'S USAGE AND BUILT ME GHOST OF TSUSHIMA ENTIRELY IN JAVASCRIPT. Using OS Red Sands + Matt Schumer's gauntlet loop, I made an explorable Ghost of Tsushima entirely playable on browser Kimi K3 REALLLLYYY earned its stripes here (other models soon dw) How I Made The Samurai + The Horse: 1. Higgsfield CLI (GPT Image 2) 2. Meshy API (multi-image-to-3D) — the turnaround → 30k-poly PBR rigged GLB 3. Blender CLI -- animating the GLB 3D assets for running, sitting, walking, riding, etc How I Made the Rest: 1. Kimi K3 High, running a few different /goals and loops (NOT one shotted) 2. Loading Screen was Minimax H3 Video Gen (768p not even 2k) 3. Suno for the background song I won't lie, this took me a few weeks to understand how to do, and then I had to throw away all of my work because I discovered the gauntlet loop and the red sands open source repo Building on top of red sand was a game changer, and the gauntlet loop also helped a lot even if it wasn't on Claude Code Full video on this soon + how GPT 5.6 SOL, Grok 4.6, Qwen 3.8 27B, Opus 5 did with this test as well!

KIMI K3 USED MY ENTIRE MONTH'S USAGE AND BUILT ME GHOST OF TSUSHIMA ENTIRELY IN JAVASCRIPT. Using OS Red Sands + Matt Schumer's gauntlet loop, I made an explorable Ghost of Tsushima entirely playable on browser Kimi K3 REALLLLYYY earned its stripes here (other models soon dw) How I Made The Samurai + The Horse: 1. Higgsfield CLI (GPT Image 2) 2. Meshy API (multi-image-to-3D) — the turnaround → 30k-poly PBR rigged GLB 3. Blender CLI -- animating the GLB 3D assets for running, sitting, walking, riding, etc How I Made the Rest: 1. Kimi K3 High, running a few different /goals and loops (NOT one shotted) 2. Loading Screen was Minimax H3 Video Gen (768p not even 2k) 3. Suno for the background song I won't lie, this took me a few weeks to understand how to do, and then I had to throw away all of my work because I discovered the gauntlet loop and the red sands open source repo Building on top of red sand was a game changer, and the gauntlet loop also helped a lot even if it wasn't on Claude Code Full video on this soon + how GPT 5.6 SOL, Grok 4.6, Qwen 3.8 27B, Opus 5 did with this test as well!

ashen

46,725 views • 14 days ago

.OpenAI's GPT-5.1 is live in Cline. After testing the last several weeks, here's what we've found makes GPT-5.1 an exceptional model in Cline: GPT-5.1 is an obsessive researcher. It reads everything before writing anything. Where other models grab context and go, GPT-5.1 investigates thoroughly first, even for one-line changes. We found this overkill for simple tasks, and modified GPT-5.1's prompting resultantly, but a superpower when channeled right. Here's what you should expect from GPT-5.1 in Cline: > deep, systematic investigation before any edits > follows constraints religiously (specs, todo lists, your requirements) > maintains coherent reasoning with large contexts > delivers complete features with fewer corrections How we optimized Cline for GPT-5.1: 1. redesigned prompts for execution focus and stricter Plan/Act transitions 2. tightened tool specs, GPT-5.1 internalizes rules with just single examples 3. split /deep-planning investigation into two phases (read first, then search) Result: GPT-5.1 is a model that finishes what it starts, even across dozens of files and thousands of lines. Both GPT-5.1 (272K context) and GPT-5.1-codex (400K context) available now in Cline. $1.25/M input, $10/M output. Enable native tool calling in settings for best results. Use /deep-planning to see GPT-5.1 at its best. Full technical breakdown linked below.

.OpenAI's GPT-5.1 is live in Cline. After testing the last several weeks, here's what we've found makes GPT-5.1 an exceptional model in Cline: GPT-5.1 is an obsessive researcher. It reads everything before writing anything. Where other models grab context and go, GPT-5.1 investigates thoroughly first, even for one-line changes. We found this overkill for simple tasks, and modified GPT-5.1's prompting resultantly, but a superpower when channeled right. Here's what you should expect from GPT-5.1 in Cline: > deep, systematic investigation before any edits > follows constraints religiously (specs, todo lists, your requirements) > maintains coherent reasoning with large contexts > delivers complete features with fewer corrections How we optimized Cline for GPT-5.1: 1. redesigned prompts for execution focus and stricter Plan/Act transitions 2. tightened tool specs, GPT-5.1 internalizes rules with just single examples 3. split /deep-planning investigation into two phases (read first, then search) Result: GPT-5.1 is a model that finishes what it starts, even across dozens of files and thousands of lines. Both GPT-5.1 (272K context) and GPT-5.1-codex (400K context) available now in Cline. $1.25/M input, $10/M output. Enable native tool calling in settings for best results. Use /deep-planning to see GPT-5.1 at its best. Full technical breakdown linked below.

Cline

72,111 views • 10 months ago

qwen 3.8 max vs deepseek v4 flash 0731 vs kimi k3 vs gpt 5.6 sol – on rubik's cube and chess four frontier models built a rubik's cube stand and solved it, then built a chess board and played claude opus 5 on it the setup: Nous Research's hermes agent cli on OpenRouter tasks: 1. cube – build a 3d rubik's cube with a cli and a Three.js viewer, then solve an identical scrambled position on your own stand 2. chess – build a 3d chess stand, then play white against claude opus 5 as black, live, one move at a time. no engine, no solver, no opening book on either side. stockfish depth 14 grades every chess ply afterwards; neither player sees the score models: DeepSeek v4 flash 0731, OpenAI gpt-5.6 sol, Kimi.ai kimi k3, Qwen qwen 3.8 max gpt-5.6 sol and deepseek v4 flash solved their cubes – sol in 24 moves and seventeen seconds, deepseek in 32. qwen and kimi never got there, giving up at 96 and 207 moves then all four built chess stands and played white against claude opus 5 on them, and all four resigned: deepseek on move 13, sol on 19, kimi on 21, qwen holding out longest at 29 - build time, both stands #1 gpt-5.6 sol – 16m 43s #2 deepseek v4 flash – 97m 39s #3 kimi k3 – 166m 09s #4 qwen 3.8 max – 215m 08s - build attempts before a working stand #1 gpt-5.6 sol – 3 #2 qwen 3.8 max – 4 #3 kimi k3 – 4 #4 deepseek v4 flash – 5 - total tokens #1 gpt-5.6 sol – 6,713,754 #2 qwen 3.8 max – 17,272,507 #3 kimi k3 – 22,427,504 #4 deepseek v4 flash – 27,417,442 - total price #1 deepseek v4 flash – $0.557 #2 gpt-5.6 sol – $6.319 #3 qwen 3.8 max – $10.270 #4 kimi k3 – $16.667 observations: • deepseek v4 flash is the cheapest model here by a margin nobody else is near, and it got there while being the least efficient of the four. it burned 27.4m tokens – more than anyone, 5m more than kimi – and still finished both benchmarks for $0.557. that is $0.02 per million tokens against kimi's $0.74. it also needed the most passes to produce working stands, five, and that did not matter: all five deepseek passes together cost a thirtieth of kimi's two • so what deepseek cannot do is get it right the first time. what it can do is get it right the fifth time, for half a dollar. that is a different thing to be buying – not a good first draft, but the option to keep asking • gpt-5.6 sol is the opposite profile and the strongest of the four on pure efficiency. 16m 43s to build both stands, 6.7m tokens, three passes – under 40% of the next lowest token count and a quarter of deepseek's, on an eighth of qwen's clock. it also solved the cube fastest of anyone, 24 moves in seventeen seconds. sol is what you reach for when you want the answer now and can absorb $0.94 per million • sol's weakness is in what it does not check. its chess viewer deleted the capturing piece instead of the captured one, so pieces disappeared off the board mid-game – a defect the fifty-cent deepseek stand did not have. fast and terse turns out to be the same dial as fast and unverified • qwen 3.8 max is not the cheap open-weights option it gets treated as. $10.270 across the two benchmarks, second most expensive of the four, 18x deepseek, and by a distance the slowest – 215 minutes of build time, nearly thirteen times sol's. what the money buys is judgment: it played eighteen moves without a single error worth a hundredth of a pawn, then made exactly one bad move in the whole game, and averaged 44.6 centipawns lost across the longest game any of the four managed. it also could not solve a rubik's cube in 96 tries • kimi k3 is the one line with no reading that flatters it. most expensive at $16.667, last on the cube at 207 moves, last at chess at 478 centipawns lost per move. it is also the model that verified hardest – on the cube it wrote its own integrity check instead of trusting its output. that makes the result worse rather than better: the checking was real, and the reasoning underneath it still was not follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

84,777 views • 1 month ago

OpenAI Dev Day Just kicked off and it was the biggest day for AI since the launch of GPT-4 in April. Here's a 3 minute video with everything you need to know and a full summary: 1. GPT-4 Turbo is released. It is much better than GPT-4, can accept up to 128k characters and is 3x cheaper. The knowledge cut off is now April 2023 2. Text to Speech is also being released. They offer 6 hyper-realistic voice models that are the best I've heard from any other AI t-t-s software on the market. 3. Copyright Shield. OpenAI will actually defend your legal costs if you get sued for copyright infringement using their API! 4. GPTs. Maybe the most exciting IMHO, you can now create custom "GPTs" by training your own model of GPT and selling it on their store. This will create a massive shakeup of the current AI software landscape and is the first step towards autonomous agents.

OpenAI Dev Day Just kicked off and it was the biggest day for AI since the launch of GPT-4 in April. Here's a 3 minute video with everything you need to know and a full summary: 1. GPT-4 Turbo is released. It is much better than GPT-4, can accept up to 128k characters and is 3x cheaper. The knowledge cut off is now April 2023 2. Text to Speech is also being released. They offer 6 hyper-realistic voice models that are the best I've heard from any other AI t-t-s software on the market. 3. Copyright Shield. OpenAI will actually defend your legal costs if you get sued for copyright infringement using their API! 4. GPTs. Maybe the most exciting IMHO, you can now create custom "GPTs" by training your own model of GPT and selling it on their store. This will create a massive shakeup of the current AI software landscape and is the first step towards autonomous agents.

Mark Gadala-Maria

79,194 views • 2 years ago

kimi k3 vs gpt 5.6 sol vs fable 5 vs grok 4.5 Kimi.ai just dropped kimi k3 – a 2.8t param native multimodal model, the first open 3t-class release. key facts: • 1m token context. stable latentmoe activating 16 of 896 experts, built on kimi delta attention (kda) and attention residuals • quantization-aware training from the sft stage onward – mxfp4 weights, mxfp8 activations. moonshot claims ~2.5x scaling efficiency over k2 • max thinking effort by default. low- and high-effort modes are "coming in updates" – there is no way to turn the thinking down today, and you feel it in every run • pricing: $0.30/mtok cache-hit input, $3.00/mtok cache-miss, $15.00/mtok output. claims >90% cache hit rate on coding workloads • benchmarks: swe marathon 42.0 (1st – fable 5: 35.0, sol: 39.0, opus 4.8: 40.0), terminal bench 2.1 88.3, browsecomp 91.2 (1st), program bench 77.8 (1st), gpqa-diamond 93.5. loses frontierswe 81.2 vs fable's 86.6, and deepswe 67.5 vs sol's 73.0 our test – 3 prompts, single-file html, Three.js, fully procedural, no assets: 1. photorealistic european roulette wheel – 37 pockets in the real sequence, mahogany clearcoat bowl, chrome turret, diamond deflectors, flick-to-spin, ball that spirals inward and settles on a mathematically real number 2. las vegas slot machine – 3 reels behind transmissive glass, drag the chrome lever to play, mechanical odometer counters modelled in 3d, coin physics on win 3. full pinball table – 6.5° tilted playfield, flipper impulse physics, spline ramps, drop targets, 6 bumpers, mechanical score reels in the backbox we ran the test on AI/ML API platform results: - cost #1 grok 4.5 – $0.30 #2 kimi k3 – $0.71 #3 gpt 5.6 sol – $2.05 #4 fable 5 – $7.69 - tokens #1 grok 4.5 – 34,241 #2 gpt 5.6 sol – 51,748 #3 fable 5 – 144,126 #4 kimi k3 – 157,999 - lines of code #1 gpt 5.6 sol – 3,054 #2 grok 4.5 – 3,047 #3 kimi k3 – 2,255 #4 fable 5 – 1,950 - generation time #1 grok 4.5 – 5.1 min #2 gpt 5.6 sol – 22.0 min #3 fable 5 – 31.5 min #4 kimi k3 – 75.6 min observations: • kimi k3 is cheap and it is slow. 75.6 minutes across three prompts against grok's 5.1. it is 2.4x grok's price and 15x grok's wall clock. the roulette took 15 min, the slot 18, the pinball 42 • it failed 2 of 3. only the roulette works. the slot machine has reel cutouts on both faces of the cabinet and the symbols face backwards – you can only read your spin by walking around to the rear of the machine. the pinball table stands vertically on its edge with the legs floating detached beside it. • 81% of kimi's output tokens are reasoning, not code. grok: 22%. you are not paying for a bigger answer, you are paying for a longer argument with itself • price per 100 shipped lines – grok $0.010, kimi $0.031, sol $0.067, fable $0.394. a 39x spread for the same three files kimi k3's code quality: upsides: • the roulette is genuinely good – procedural wood grain with real specular breakup, correct european sequence (0-32-15-19-4...), chrome turret, diamond deflectors, clean console • the pinball artwork is the best in the test – a synthwave "nova strike / deep space" field with six individually coloured neon bumper rings, a retro sun on a grid horizon, a nova burst, and a scoring legend printed on the apron. no other model printed the rules on the machine. it is a beautiful texture on a broken object • physics reasoning is real – it derived a 480hz substep for the collider, worked out ball settle conditions and termination guarantees, and checked every ramp exit vector by hand before writing any of it • it is the only model that saw the importmap trap coming. sol shipped a blank white page twice because three.js addons import the bare specifier 'three' and die without an import map downsides: • it dodged that trap on the slot by loading three.js r128 through classic script tags – a 2021 build with no working transmission. its slot glass rendered fully opaque and buried all three reels behind a white pane. the code asks for transmission: 0.93, ior: 1.5 – correct, and silently ignored by a renderer that predates the feature • after 42 minutes and 212k characters of reasoning, the pinball cabinet is not assembled. the table stands vertically on its edge like a wardrobe – the prompt asked for 6.5° from horizontal, it delivered 90°. the legs float detached in the void beside it. head-on it photographs beautifully; orbit ten degrees and it is a painted slab with four chrome rods hovering nearby • the playfield z-fights with the glass – hard black banding across the whole field as soon as you pull the camera back a note on the pinball, in fairness to kimi: nobody passed it. every model shipped broken ball physics and controls you cannot trust. it is the hardest prompt we have run and the whole field failed it, each in its own way kimi k3 reasons better than anything else here and it shows exactly where reasoning pays – physics constants, sequences, edge cases, traps the others walked into follow thehype. for 24/7 ai news, analysis and breakdowns

kimi k3 vs gpt 5.6 sol vs fable 5 vs grok 4.5 Kimi.ai just dropped kimi k3 – a 2.8t param native multimodal model, the first open 3t-class release. key facts: • 1m token context. stable latentmoe activating 16 of 896 experts, built on kimi delta attention (kda) and attention residuals • quantization-aware training from the sft stage onward – mxfp4 weights, mxfp8 activations. moonshot claims ~2.5x scaling efficiency over k2 • max thinking effort by default. low- and high-effort modes are "coming in updates" – there is no way to turn the thinking down today, and you feel it in every run • pricing: $0.30/mtok cache-hit input, $3.00/mtok cache-miss, $15.00/mtok output. claims >90% cache hit rate on coding workloads • benchmarks: swe marathon 42.0 (1st – fable 5: 35.0, sol: 39.0, opus 4.8: 40.0), terminal bench 2.1 88.3, browsecomp 91.2 (1st), program bench 77.8 (1st), gpqa-diamond 93.5. loses frontierswe 81.2 vs fable's 86.6, and deepswe 67.5 vs sol's 73.0 our test – 3 prompts, single-file html, Three.js, fully procedural, no assets: 1. photorealistic european roulette wheel – 37 pockets in the real sequence, mahogany clearcoat bowl, chrome turret, diamond deflectors, flick-to-spin, ball that spirals inward and settles on a mathematically real number 2. las vegas slot machine – 3 reels behind transmissive glass, drag the chrome lever to play, mechanical odometer counters modelled in 3d, coin physics on win 3. full pinball table – 6.5° tilted playfield, flipper impulse physics, spline ramps, drop targets, 6 bumpers, mechanical score reels in the backbox we ran the test on AI/ML API platform results: - cost #1 grok 4.5 – $0.30 #2 kimi k3 – $0.71 #3 gpt 5.6 sol – $2.05 #4 fable 5 – $7.69 - tokens #1 grok 4.5 – 34,241 #2 gpt 5.6 sol – 51,748 #3 fable 5 – 144,126 #4 kimi k3 – 157,999 - lines of code #1 gpt 5.6 sol – 3,054 #2 grok 4.5 – 3,047 #3 kimi k3 – 2,255 #4 fable 5 – 1,950 - generation time #1 grok 4.5 – 5.1 min #2 gpt 5.6 sol – 22.0 min #3 fable 5 – 31.5 min #4 kimi k3 – 75.6 min observations: • kimi k3 is cheap and it is slow. 75.6 minutes across three prompts against grok's 5.1. it is 2.4x grok's price and 15x grok's wall clock. the roulette took 15 min, the slot 18, the pinball 42 • it failed 2 of 3. only the roulette works. the slot machine has reel cutouts on both faces of the cabinet and the symbols face backwards – you can only read your spin by walking around to the rear of the machine. the pinball table stands vertically on its edge with the legs floating detached beside it. • 81% of kimi's output tokens are reasoning, not code. grok: 22%. you are not paying for a bigger answer, you are paying for a longer argument with itself • price per 100 shipped lines – grok $0.010, kimi $0.031, sol $0.067, fable $0.394. a 39x spread for the same three files kimi k3's code quality: upsides: • the roulette is genuinely good – procedural wood grain with real specular breakup, correct european sequence (0-32-15-19-4...), chrome turret, diamond deflectors, clean console • the pinball artwork is the best in the test – a synthwave "nova strike / deep space" field with six individually coloured neon bumper rings, a retro sun on a grid horizon, a nova burst, and a scoring legend printed on the apron. no other model printed the rules on the machine. it is a beautiful texture on a broken object • physics reasoning is real – it derived a 480hz substep for the collider, worked out ball settle conditions and termination guarantees, and checked every ramp exit vector by hand before writing any of it • it is the only model that saw the importmap trap coming. sol shipped a blank white page twice because three.js addons import the bare specifier 'three' and die without an import map downsides: • it dodged that trap on the slot by loading three.js r128 through classic script tags – a 2021 build with no working transmission. its slot glass rendered fully opaque and buried all three reels behind a white pane. the code asks for transmission: 0.93, ior: 1.5 – correct, and silently ignored by a renderer that predates the feature • after 42 minutes and 212k characters of reasoning, the pinball cabinet is not assembled. the table stands vertically on its edge like a wardrobe – the prompt asked for 6.5° from horizontal, it delivered 90°. the legs float detached in the void beside it. head-on it photographs beautifully; orbit ten degrees and it is a painted slab with four chrome rods hovering nearby • the playfield z-fights with the glass – hard black banding across the whole field as soon as you pull the camera back a note on the pinball, in fairness to kimi: nobody passed it. every model shipped broken ball physics and controls you cannot trust. it is the hardest prompt we have run and the whole field failed it, each in its own way kimi k3 reasons better than anything else here and it shows exactly where reasoning pays – physics constants, sequences, edge cases, traps the others walked into follow thehype. for 24/7 ai news, analysis and breakdowns

thehype.

2,183,762 views • 1 month 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 • 2 months ago

Great explanation by Emad Mostaque, co-founder of Stability AI. "We’ll see the cost of Kimi K3 drop by 10 to 50 times, I think, over the next few months as it gets optimized. " Basically Kimi K3’s current inference cost is quite high, but that price reflects immature infrastructure, not a permanent technical limit. And that gap will not last long. US-based specialized infrastructure companies will optimize kernels, routing, quantization, batching, memory use, and serving systems around those models once the Kimi K3 weights are available. --- "Right now, it uses twice the number of tokens for the same task compared with GPT-5.6. Again, we’re going to see that cost drop because everyone and their dog is going to optimize the crap out of this. Fireworks has just raised funding at a $17 billion valuation, while others, such as Modal and Baseten, are valued at $10 billion. These are inference providers for open-source models. They’ve all raised around a billion dollars, which they’re now going to spend on optimizing the Chinese model, making it more efficient, and running it. American labs that handle the inference side of things are going to optimize the crap out of this. Therefore, we will see it catch up." ---- From "Peter H. Diamandis" YouTube channel, (full video link in comment)

Great explanation by Emad Mostaque, co-founder of Stability AI. "We’ll see the cost of Kimi K3 drop by 10 to 50 times, I think, over the next few months as it gets optimized. " Basically Kimi K3’s current inference cost is quite high, but that price reflects immature infrastructure, not a permanent technical limit. And that gap will not last long. US-based specialized infrastructure companies will optimize kernels, routing, quantization, batching, memory use, and serving systems around those models once the Kimi K3 weights are available. --- "Right now, it uses twice the number of tokens for the same task compared with GPT-5.6. Again, we’re going to see that cost drop because everyone and their dog is going to optimize the crap out of this. Fireworks has just raised funding at a $17 billion valuation, while others, such as Modal and Baseten, are valued at $10 billion. These are inference providers for open-source models. They’ve all raised around a billion dollars, which they’re now going to spend on optimizing the Chinese model, making it more efficient, and running it. American labs that handle the inference side of things are going to optimize the crap out of this. Therefore, we will see it catch up." ---- From "Peter H. Diamandis" YouTube channel, (full video link in comment)

Rohan Paul

82,007 views • 1 month ago