GLM-5.3-Flash Released: 320B Total Params, Cost-Efficiency on Pareto Frontier

ArtificialAnlys · x · 2026-08-27

Zai has released GLM-5.3-Flash, a smaller and more cost-efficient sibling to GLM-5.3. It features 320B total parameters with 18B active parameters and supports low, high, and max reasoning efforts.

In Artificial Analysis benchmarks, GLM-5.3-Flash scores 57 on the Intelligence Index and sits comfortably on the Intelligence vs. Cost per Task Pareto frontier at $0.09 per task. It achieves a GDPval-AA v2 score of 1770, matching the GLM-5.3 Max. The evaluation used 149M output tokens, approximately 11% fewer than the GLM-5.3 model.

Related event: Zhipu Open-Sources GLM-5.3-Flash: 320B MoE, 1M Context, at One-Tenth the Cost(38 posts)→

Original post →

More from Models

Models channel →