GPT-5.6, Grok 4.5, Claude, and Muse Spark build the same 4 apps · TryAI<br>All postsOur last build-off hit the Hacker News front page, and the comments did not hold back. Fair enough, a lot of it was good feedback. So we took it, and with GPT-5.6 landing in three tiers (Sol, Terra, Luna) and Meta surprise-dropping a coding model (Muse Spark 1.1), we ran the whole thing again, bigger: twelve models, four apps, five attempts each.
What we changed based on your feedback:
You wanted open-weights models in the mix. So we added GLM-5.2, Qwen 3.7 Plus, DeepSeek V4 Pro, and Kimi K2.6 as comparison points, all served via Fireworks.
One attempt was weird, you said. Agreed. Every model now gets five attempts per task. Up top you get one sample run per model; each task table then says how many of the five we thought actually succeeded (and how we counted) and links the attempt we liked best; and every attempt is linked at the bottom so you can see how much these models swing run to run.
"This isn't objective." Correct, and we are not pretending it is. We are not handing down a scientific verdict. We generated a big pile of artifacts, we are publishing all of them, and you can form your own opinion. Everything below is just our observations from watching the results.
Want to skip straight to poking at the raw builds? Jump to every attempt and run them yourself.
The lineup, twelve strong: the new GPT-5.6 Sol, GPT-5.6 Terra, and GPT-5.6 Luna; Meta's Muse Spark 1.1; Grok 4.5, GPT-5.5, Claude Opus 4.8, and Claude Fable 5; plus the open-weights crew: Qwen 3.7 Plus, DeepSeek V4 Pro, Kimi K2.6, and GLM-5.2.
Here is each task: our pick of the five attempts playing up top, the cost and time for all five just below, and links to every raw attempt at the bottom of the post so you can judge for yourself.
Task 1: Doom-style raycaster maze
First-person raycaster you walk with WASD, shaded walls with depth, floor and ceiling, collision.
Grok 4.5Claude Opus 4.8GPT-5.5Qwen 3.7 Plus<br>Kimi K2.6Claude Fable 5DeepSeek V4 ProGLM-5.2<br>GPT-5.6 SolGPT-5.6 TerraGPT-5.6 LunaMuse Spark 1.1<br>How we counted "playable": the only question we cared about was whether you could actually walk through the labyrinth, move and turn. If yes, it counted.
ModelPlayableBest buildCost (5 runs)Avg timeOur takeGrok 4.55/5#40.27¢62sGreat for the price.Claude Opus 4.84/5#20.54¢48sConsistent but dry.GPT-5.54/5#11.44¢138sBest overall before GPT-5.6.Qwen 3.7 Plus2/5#40.13¢43s—Kimi K2.62/5#21.37¢88s—Claude Fable 53/5#12.35¢107sGood results, but less consistent.DeepSeek V4 Pro3/5#40.30¢318s—GLM-5.20/5—0.12¢133sRendered good detail, but the character could not move in any attempt.GPT-5.6 Sol5/5#51.35¢120sBest results: consistent, better than GPT-5.5, and with more detail in the game overall.GPT-5.6 Terra3/5#10.44¢39sGood detail, but less consistent, I couldn't always walk.GPT-5.6 Luna5/5#50.15¢23sGreat results, though not as good as GPT-5.5 in my opinion.Muse Spark 1.12/5#10.55¢169sSurprisingly awesome when it worked. Three of five were broken, but the working ones were on par with Fable and Sol, and better than the Grok and Opus ones.<br>Overall, Claude did worse than we expected here. GPT outperformed every other model, Grok was a genuinely usable alternative at its price point, and Muse Spark was a real surprise on the runs that actually worked.
Task 2: 3D Rubik's Cube (scramble + solve)
Build a colorful, 3D-looking Rubik's Cube with Scramble and Solve buttons that visibly animate the rotations.
Grok 4.5Claude Opus 4.8GPT-5.5Qwen 3.7 Plus<br>Kimi K2.6Claude Fable 5DeepSeek V4 ProGLM-5.2<br>GPT-5.6 SolGPT-5.6 TerraGPT-5.6 LunaMuse Spark 1.1<br>How we counted a "clean solve": we scrambled and solved the cube and only counted an attempt if both animations ran smooth, no glitches, no color changes.
ModelClean solveBest buildCost (5 runs)Avg timeOur takeGrok 4.53/5#40.65¢191sGood, simple results.Claude Opus 4.80/5#10.56¢44sNo perfect example, everything had a small issue and the cube's colors would change, though some were close.GPT-5.54/5#41.36¢136sGood results, with small nits like flickering colors or not-quite-smooth rotation animations.Qwen 3.7 Plus1/5#50.07¢24sWhen it worked, it looked great!Kimi K2.61/5#41.05¢59sNot great.Claude Fable 55/5#22.03¢92sNo notes, really nice results.DeepSeek V4 Pro1/5#30.35¢380s—GLM-5.20/5—0.08¢89sSurprisingly, no working results.GPT-5.6 Sol4/5#51.06¢72sGreat results. One had weird animations and one rendered an all-black cube (interesting choice), but it did great on the ones that worked.GPT-5.6 Terra4/5#40.42¢38sFine, with weird scramble animations, felt like a small step up from GPT-5.5.GPT-5.6 Luna0/5—0.14¢24sUsually rendered correctly at first, but scrambling immediately broke it.Muse Spark 1.12/5#10.54¢182sA step above the OSS models, but not something I'd use over Grok for the price.<br>Overall, we were surprised GPT underperformed here given its clear 3D lead in the raycaster. Claude did an amazing job again, though it was Fable carrying...