• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    User reports GPT-6 Astra outscored MolmoAct2 on robotics tasks

    The post puts Astra at 46% versus MolmoAct2’s 12% across 200 trials on five two-handed tasks.

    MB
    YC
    KC
    12 Sources, 19d ago, first seen 19d ago

    TLDR

    A user reports GPT-6 Astra scored 46% compared with 12% for MolmoAct2 across 200 trials on five bimanual, or two-handed, tasks. The post describes MolmoAct2 as a state-of-the-art robotics model and calls Astra’s score “3.9x higher.”

    Combined views

    252.9K

    12 Sources, first seen 19d ago

    1.7K likes

    Combined views

    252.9K

    12 Sources, first seen 19d ago

    1.7K likes
    103 comments
    694 saves
    176 reposts

    Sentiment

    Positive79.6%20.4%Negative

    Based on 68 sentiment-bearing replies from 54 accounts across 2 conversations.

    103 comments
    694 saves
    176 reposts

    Sentiment

    Positive79.6%20.4%Negative

    Based on 68 sentiment-bearing replies from 54 accounts across 2 conversations.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    12 Sources

    @chooi_jeqGPT-6 Astra scores 46% vs 12% for MolmoAct2, a state-of-the-art robotics VLA, across 200 trials on five bimanual tasks. That's 3.9x higher. 🧵
    @ycombinatorRT @chooi_jeq: GPT-6 Astra scores 46% vs 12% for MolmoAct2, a state-of-the-art robotics VLA, across 200 trials on five bimanual tasks. That…
    @_varunnair@robocurve is pushing the entire industry forward with it open source evaluation protocol. phenomenal work @chooi_jeq. Keeps robotics progress real, quantifiable and transparent.
    @chris_j_paxtonIf you are a robot foundation model guy and not a deployment guy this must be really concerning
    @HSlifelearnerI recall @mobav0 calling out how he believes why robotics is solved via digital world first, it seemed unfathomable at the time but true now.
    @kimmaicutlerRT @_varunnair: @robocurve is pushing the entire industry forward with it open source evaluation protocol. phenomenal work @chooi_jeq. Ke…
    @mobav0RT @HSlifelearner: I recall @mobav0 calling out how he believes why robotics is solved via digital world first, it seemed unfathomable at t…
    @zhaoran_wangpick-and-place almost solved by the general LLM?
    @peteskomorochRT @chris_j_paxton: If you are a robot foundation model guy and not a deployment guy this must be really concerning

    12 Sources

    @chooi_jeqGPT-6 Astra scores 46% vs 12% for MolmoAct2, a state-of-the-art robotics VLA, across 200 trials on five bimanual tasks. That's 3.9x higher. 🧵
    @ycombinatorRT @chooi_jeq: GPT-6 Astra scores 46% vs 12% for MolmoAct2, a state-of-the-art robotics VLA, across 200 trials on five bimanual tasks. That…
    @_varunnair@robocurve is pushing the entire industry forward with it open source evaluation protocol. phenomenal work @chooi_jeq. Keeps robotics progress real, quantifiable and transparent.
    @chris_j_paxtonIf you are a robot foundation model guy and not a deployment guy this must be really concerning
    @HSlifelearnerI recall @mobav0 calling out how he believes why robotics is solved via digital world first, it seemed unfathomable at the time but true now.
    @kimmaicutlerRT @_varunnair: @robocurve is pushing the entire industry forward with it open source evaluation protocol. phenomenal work @chooi_jeq. Ke…
    @mobav0RT @HSlifelearner: I recall @mobav0 calling out how he believes why robotics is solved via digital world first, it seemed unfathomable at t…
    @zhaoran_wangpick-and-place almost solved by the general LLM?
    @peteskomorochRT @chris_j_paxton: If you are a robot foundation model guy and not a deployment guy this must be really concerning