Hacker News · item history
GLM-5.2 is the new leading open weights model on Artificial Analysis
13
first seen points
907
peak points
907
latest points
10
observations
Posted on X
- GLM-5.2 topped the open-weights leaderboard this week. The interesting bit: it's from Zhipu AI, not the usual Meta/Mistral suspects, and the benchmark shows it closing the gap on closed models for reasoning tasks. Worth a look if you're spec'ing local inference.