Z.ai GLM 5.2

theanonymousone 15 points 1 comment June 16, 2026
huggingface.co · View on Hacker News

Discussion Highlights (1 comments)

osti

Given that DeepSwe is one of the very few coding benchmarks worth taking a look at, this achieves rather excellent result at it (not far from opus 4.8). From looking at the results and my own impression of 5.1 and other models, I think this is the best Chinese coding model by some non-insignificant margin.

Semantic search powered by Rivestack pgvector
10,715 stories · 100,765 chunks indexed