Zhipu founder Tang Jie: After GLM-5.2 was open-sourced, multiple evaluations ranked among the top, and the gap with models such as OpenAI and Anthropic continues to narrow

robot
Abstract generation in progress

Deep Tide TechFlow News, on June 19th, Zhipu AI founder Tang Jie stated on the X platform that since the open-source release of GLM-5.2, it has achieved top results in multiple international evaluations and rankings. Among them, in the Artificial Analysis Intelligence Index comprehensive assessment, GLM-5.2 scored 51 points, placing it in a similar performance range to Anthropic Claude Opus 4.8; in the Code Arena front-end code generation test, it ranked second globally with an Elo of 1595; in the DesignArena scene combining design and code, it ranked first with 1360 points.

Tang Jie said that GLM-5.2 continues to perform at the forefront in real-world scenario evaluations such as front-end development, design generation, and software engineering, with the performance gap compared to cutting-edge models like OpenAI and Anthropic gradually narrowing.

Previously, Elon Musk said that China's AI reaching Fable level might happen in "Q1," to which Zhipu AI founder Tang Jie responded that "it won't take that long."

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
  • Pinned