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

    Meta AI Details AIRA₃ Ensemble Results

    Official Meta AI account describes its AIRA₃ entry and post-hoc model tests on the Kaggle leaderboard.

    AA
    1 Source, 25d ago, first seen 25d ago

    TLDR

    The official AI at Meta account posted that the team entered the AIRA₃ competition live with an ensemble of models and ran additional assessments afterward. It stated that the eighth-ranked gold medal entry combined GPT 5.5 with OpenCode and Claude 4.8 with ClaudeCode. The post also noted that a later test with Muse Spark 1.2 and MuseCode reached gold-medal performance. The message included an image of the dark-themed Kaggle Private Leaderboard.

    Combined views

    14K

    1 Source, first seen 25d ago

    Combined views

    14K

    1 Source, first seen 25d ago

    101 likes
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    101 likes
    10 comments
    15 saves
    4 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    10 comments
    15 saves
    4 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    1 Source

    @AIatMetaWe entered AIRA₃ with an ensemble of models in the live competition, and also assessed it with several others post-hoc. The 8th ranked gold medal entry ensemble was a combination of GPT 5.5 (w/ OpenCode) + Claude 4.8 (w/ ClaudeCode). Post-hoc we assessed with Muse Spark 1.2 (w/ MuseCode), which also performed at a Gold Medal level, as well as Muse Spark 1.1 (w/ OpenCode) and GLM 5.2 (w/ OpenCode), both of which achieved Silver Medal level performance. The post-hoc submissions were also graded externally on the same private test set as those made during the live competition.

    1 Source

    @AIatMetaWe entered AIRA₃ with an ensemble of models in the live competition, and also assessed it with several others post-hoc. The 8th ranked gold medal entry ensemble was a combination of GPT 5.5 (w/ OpenCode) + Claude 4.8 (w/ ClaudeCode). Post-hoc we assessed with Muse Spark 1.2 (w/ MuseCode), which also performed at a Gold Medal level, as well as Muse Spark 1.1 (w/ OpenCode) and GLM 5.2 (w/ OpenCode), both of which achieved Silver Medal level performance. The post-hoc submissions were also graded externally on the same private test set as those made during the live competition.