DrstaOne retweeted
Everyone's Benchmarking Pelicans. I Made Mine Into a Film.
>> Hand Drawn Anime Aesthetic, Pure Canvas 2D. No Libraries. No Images. No Audio Files. Just Pure Code.
<< Pure Code by Gemini 4 Carbon High >>
DrstaOne retweeted
Gemini 4 Carbon(Now) VS Gemini 4 Carbon(Arena)
I test same prompt fox running side now and when it was testing arena.
The Carbon model has upgraded more , it's look more natural now.
DrstaOne retweeted
Alibaba is going to launch its new model Soon.... and It's new model were testing on Arena
I also tried to make cell like @DrstaOne
-->I told Qwen 3.8 Max to built an Animal cell
This turned out pretty cool ,Personally loved this output
But i need public review ,How much will rate out of 10
nitter.gq/DrstaOne/status/211700…
DrstaOne retweeted
Wtf, Agron is beast at World Development
>Made this Clicking water Model using Gemini 4 Argon
And For sure ,This is So good
Btw How much would u rate this outof 10 @DrstaOne
This new model "Kalmia" is Crazy
→Made this Living cell using Kalmia new model of Qwen's
I think this gonna be craziest model of Alibaba Qwen, Truely this feels so illegal to make this kind of outputs
Alibaba's new model is going to compete frontier model like DSv4.1 flash and Opus 5.5
DrstaOne retweeted
Build a Immersive Feudal Japan World in 3D, Inspired by Traditional Architecture, Culture, and Landscapes.
Remarkably, The Entire Scene was Generated From a SINGLE PROMPT.🏯🌸✨
Claude Haiku 5.5 is insane in 3D model World making ,Everyone just talking about haiku 5.5
At this points everyone is just hyping for haiku 5.5 as because it is also an amazing model and i also tried an prompt on this ,I told Haiku to build "Kong Skull island " and output is insane ,this looks so amazing
Haiku 5.5 is also an cheap model launched by Anthropic and really good at Cost efficiency, Well... i don't have taken full clip of the model as because it will felt so large in size
honestly this is one the best model i ever made
DrstaOne retweeted
GPT-6 Astra Ultra
Generated in 26 minutes 🤯
10,460,032 tokens used
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.







