Epoch AI Research evaluates the performance of Meta's new model Muse Spark on the FrontierMath benchmark

robot
Abstract generation in progress

ME News update: On April 9 (UTC+8), Epoch AI Research recently obtained pre-release access to Meta’s new model, Muse Spark, and evaluated it on the FrontierMath benchmark. The evaluation results show that Muse Spark scored 39% on Tier 1–3 and 15% on Tier 4. According to the article, this performance is competitive compared with several recent cutting-edge models, but it lags behind GPT-5.4. (Source: InFoQ)

View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin