Cunxiang Wang(@CunxiangWang):Strongly agree that true usefulness matters more than benchmark points. That’s exactly why it is encouraging to see GLM-5.2 improve in real development scenarios, not just on public evals. The interesting contrast is not benchmark vs usefulness, but models that keep moving on both and models that have been oddly quiet on both for a long time. More here: https://t.co/9vJuqX2M80

Cunxiang Wang

@CunxiangWang

Researcher @Zai_org, Postdoc @thukeg, working with @jietang. Core contributor to GLM series. Focusing on real long-horizon agentic tasks, self-evolving LLMs

Joined August 2019

1.3K Following 2K Followers

Cunxiang Wang@CunxiangWang

2026.06.19 04:15

Strongly agree that true usefulness matters more than benchmark points. That’s exactly why it is encouraging to see GLM-5.2 improve in real development scenarios, not just on public evals. The interesting contrast is not benchmark vs usefulness, but models that keep moving on both and models that have been oddly quiet on both for a long time. More here: