Skip navigation
1/ muse spark 1.2 is a very strong multimodal model—it can do visual coding, robotics planning, and…
0:00 / 0:19

1/ muse spark 1.2 is a very strong multimodal model—it can do visual coding, robotics planning, and…

Alexandr Wang

@alexandr_wang855K followers

Visit on X

187,092 views

1/ muse spark 1.2 is a very strong multimodal model—it can do visual coding, robotics planning, and audio-visual understanding that all come together through agentic tools.

31 Comments

Comments from the original post on X (Twitter)

  • Alexandr Wang's profile picture

    @alexandr_wang

    2/ muse spark 1.2 performs quite strongly across a wide variety of multimodal capabilities and evals.

    135 likes

  • Alexandr Wang's profile picture

    @alexandr_wang

    3/ you can get a deeper look at all this in the research blog published today.

    105 likes

  • elie's profile picture

    @eliebakouch

    i thought this was the oss release of muse spark :( but cool to see more focus on the multimodality!

    12 likes

  • Diligent Plane's profile picture

    @DiligentPlane

    Reading now. When can we expect watermelon Alex? And how are evals stacking up

    6 likes

  • Emily's profile picture

    @IamEmily2050

    Hopefully, Muse Video will be SOTA not on Arena benchmarks but in real use cases.

    5 likes

  • 🍉's profile picture

    @plumberbutt97

    Alexandr I thought this was gonna be watermelon 🍉 and blow my mind

    5 likes

  • Zengyi Qin's profile picture

    @qinzytech

    awesome! honered to have led the multimodal agent eval / wild artifact bench efforts

    4 likes

  • Greg's profile picture

    @CousinGraig

    This is an incredible product. Science fiction stuff, stood up in < 18 months, absolutely incredible. So this ? Isn’t meant to patronize or belittle the achievement. aside from productizing BI tools across platforms, how will $META go to mkt to drive adoption among developers as coding and developer mkt highly saturated by OAI & Anthropic?

    4 likes

  • Max's profile picture

    @selzer25

    Alex, 1. When will muse code be open sourced? 2. Do you have an eta for spark 1.2? when that will be open sourced

    4 likes

  • Vladimir Arustamov's profile picture

    @v_arustamov

    Alexandr, you should check this out: I hope if you will collaborate with @humynlabs, that could bring times more accurate robotics planning ^^

    3 likes

  • Aesther's profile picture

    @AestherML

    Definitely one of the best for visual tasks

    3 likes

  • Divyanshu's profile picture

    @Oldnoob007

    Ok the multimodal capabilities benchmark looks pretty good ngl! Also check out TTFT

    3 likes

  • Yi Zhong 🍊's profile picture

    @yiz_be_building

    when will muse spark support audio as input?

    2 likes

  • Matt Boardman's profile picture

    @MattEBoardman

    Muse RBD vibe coding app when?

    2 likes

  • decipherx's profile picture

    @stacktrace01

    honestly for coding.. deepseek v4 flash >>>> muse spark 1.2

    2 likes

  • rehen's profile picture

    @justrehen

    one model to code them all 💀

    2 likes

  • Russell Caten's profile picture

    @RussellCaten

    Is anyone interested in a company that lies to society!?

    1 like

  • PHICHAI's profile picture

    @numetn_

    My Facebook account was asked to verify its identity. After scanning my face, my account was permanently closed. What happened?

    1 like

  • The AI Therapist's profile picture

    @TheAIShrink

    "visual coding, robotics planning, audio-visual understanding." three new adjectives for the same gpu tax

    1 like

  • AI Apps API's profile picture

    @AIAppsAPI

    Visual coding is the piece that changes workflows fastest. Once a screenshot reliably becomes working code, the bottleneck moves from writing the UI to specifying what correct actually looks like. The part I want to see stress tested is the audio-visual side on long video. That is where most multimodal models still drift.

    1 like