Andriy Buday

Muse Code at @Meta
Prev: @Google, @Amazon, @iaeaorg & more.
Software Engineer. Opinions are mine.

[Alexandr Wang @alexandr_wang]

many people still sleeping on Muse Wonder Full

all good, we have better models on the way 🔜 👿

[Andriy Buday @andriybuday]

@thesosana Thanks for sharing the feedback. The more feedback we have the better we understand where the main pain points are and where our focus should be.

[Andriy Buday @andriybuday]

Keep hearing over and over that Muse Wonder Full is great model to talk to. It definitely has a different feel to models people are used to.

[Theo - t3.gg @theo]

I still think you guys are severely underrating Muse Wonder Full.

Been using it a ton for orchestration and drafting rewrites of docs, skills, mcp descriptions and more.

It's so much more pleasant to talk to AND it's great at steering models (as such, decent at skill writing!)

[Meta for Developers @MetaforDevs]

Muse Wonder is now available on @Cline, @Cloudflare, @Cognition, @Cursor_AI, @OpenRouter, @Oracle and @Vercel - with more partners coming soon.

We look forward to seeing what the community builds with Muse Wonder!

Start building 👉 https://t.co/QJT3aIZNd1

[Andriy Buday @andriybuday]

https://t.co/Sk4ewyivh8

[Andriy Buday @andriybuday]

@Muse saved me 50$ on new climbing shoes by finding them on sale on some Italian website, it figured that shipping and US import tax still saves me money, and no other retailer in US would beat the price. I got my shoes delivered in 6 days, I haven't even seen that website or typed any of my details. Just told my Muse what I need, and confirmed purchase once it done full research. I love agents in my personal life. I also keep hearing from friends how happy they are with @Muse. My Metamates who made this possible, you rock!

[Andriy Buday @andriybuday]

@cobeyluke @theo @ImLunaHey @mjdouglas Thanks for flagging. Yeah, I think it is a good idea to be proactive.

[Morgan @morganlinton]

Okay so I managed to squeeze in getting model cards out today for my Muse Wonder Full benchmark with @VulcanBench - enjoy!

This, plus all the data from every run will be on the VulcanBench site soon(ish), and all of the traces will be on Github as well.

Everything I do with VulcanBench is free and open source. As a truly independent benchmark (it's just me!) I share it all, every single trace from every run, plus the source code for VulcanBench so you can even re-rerun specific tests, or the entire benchmark if you want to.

What stands out looking at this is that Astra is fast, but you pay for it. GPT-6.1 Sol is fast and cheap. Opus wins in accuracy, and Muse Wonder is accurate, but expensive and slow.

Right now, with the data I have, I don't think I would use Muse Wonder for coding, and I'm not sure that's the market they're going after, yet.

That being said, looking at the accuracy numbers, it's clear the Muse team has built a very intelligent model. If they can figure out how to wrangle the time/cost per task, they could very easily become a model usable for daily coding tasks.

Live long and benchmark 🖖

[Andriy Buday @andriybuday]

@ZryMiller Thanks for sharing! Good to know that Wonder Full is nice to talk to!

[Andriy Buday @andriybuday]

@morganlinton @VulcanBench Thanks for sharing!

[Andriy Buday @andriybuday]

@Signal_65 @AIatMeta Nice!

[Andriy Buday @andriybuday]

@alexandr_wang btw, "no deadlines" doesn't mean chilling out, lol. MSL, is by far the fastest moving work environment for me. Insanely fast, and stimulating! Absolutely bonkers. Also thanks for all the shitposting, boss! Love it.

[Andriy Buday @andriybuday]

@ZryMiller 👀 interested to learn more... "keep hearing" is a very interesting part, as I didn't hear this before at all 😅

[Andriy Buday @andriybuday]

@morganlinton @VulcanBench @morganlinton thank you so much for running these benchmarks. The team released a new 1.4.8 version of Muse Code that is more token efficient and we also hit reset button:

[Michael Douglas @mjdouglas]

1.4.8 made Muse Code a lot more token-efficient, so we wanted you to feel it right away.

🎉 Everyone's usage is reset, effective now. Have fun.

[Michael Douglas @mjdouglas]

1.4.8 made Muse Code a lot more token-efficient, so we wanted you to feel it right away.

🎉 Everyone's usage is reset, effective now. Have fun.

[Andriy Buday @andriybuday]

@AdamBLevine @QuixiAI @AIatMeta @Muse The team is working on improving efficiency in Muse Code so your subscriptions can get you further.

[Andriy Buday @andriybuday]

Someone is making a programming language from scratch with help of Muse Wonder Full and says the model is Fable level and twice the speed 💪🚀

[Eric Hartford @QuixiAI]

@AIatMeta is humbly downplaying @Muse muse-wonder-full-1.0's coding ability in favor of its agentic assistant strengths.

Muse Code is Fable-level. Twice as fast. And significantly more generous usage limits.

I have been using it nonstop since its release and it has completely replaced Fable for my most challenging tasks. If there's one thing I'm good at, it's burdening agents with the most challenging of tasks.

[Andriy Buday @andriybuday]

Those are impressive real work results of Muse Wonder Full. The team has been using it internally to develop Muse Code, chase and fix bugs. It's really good.

[Paweł Huryn @PawelHuryn]

So, I tested Muse Wonder Full 1.0 on real work. 2 repos. 105 bugs frontier models missed in Q1 2026. Find and fix what you can.

I'm so surprised we need a new thread.
The results:

GPT-6 Astra (max): 45
Muse Wonder Full 1.0 (max): 44
Fable 5.1 (max): 43
Opus 5.5 (max): 41.7
Muse Spark 1.3 (max): 32.2
Grok 4.7 (xhigh): 29

@AIatMeta has just matched Anthropic and OpenAI. Huge congrats!

Next in this thread, more effort levels and more runs for Muse Wonder Full 1.0. All dropping tonight 🧵

[Meta for Developers @MetaforDevs]

Developers can start building with Muse Wonder in Muse Code and on Meta Model API at $4/$20 per million tokens.

Muse Wonder Full is available on both the Power Usage plan and new Maximum Usage plan, which brings an 80x limit over the Everyday Usage plan and the same five-hour and weekly resets. (2/3)

[Andriy Buday @andriybuday]

You can now write your code with Muse Wonder in the latest Muse Code!

curl https://t.co/rDaQsgyj6Z | bash

[Alexandr Wang @alexandr_wang]

MUSE WONDER 🍉

muse wonder is the best model in the world for personal agents and professional agents.

we evaluated our model against the best models in the world across agentic and coding tasks, and we think you all will like it.