Z.ai's GLM-5.3 with max reasoning scores 60 on the Artificial Analysis Intelligence Index, on par with Kimi K3 but below Opus 5 at 63 and Fable 5 at 62 (@artificialanlys)
GLM-5.3 posted a 60 on Artificial Analysis, putting it level with Kimi K3 and seven points above GLM-5.2.
Artificial Analysis says the score would make GLM-5.3 tied for the leading open-weights model once the weights are released. The note places it below Opus 5 at 63 and Fable 5 at 62. Z.ai says the API is live, with the model aimed at coding, defensive cybersecurity, and long-horizon agentic tasks. Techmeme's note
Artificial Analysis says the score would make GLM-5.3 tied for the leading open-weights model once the weights are released. The note places it below Opus 5 at 63 and Fable 5 at 62. Z.ai says the API is live, with the model aimed at coding, defensive cybersecurity, and long-horizon agentic tasks. Techmeme's note
score 8