PyyanThe AI Index

Pyyan / Compare / Hunyuan 3.0 vs Kimi K3 vs GLM-5.2

Hunyuan 3.0 vs Kimi K3 vs GLM-5.2

3 of 5

Open-Weight Models · verified 13 Aug 2026

×Hunyuan 3.0Tencentcurrent
×Kimi K3Moonshot AIcurrent
×GLM-5.2Zhipu AIcurrent
2 slots left
SpecificationHunyuan 3.0Kimi K3GLM-5.2
Summary295B MoE under Apache 2.0.Largest open-weight model shipped.Strongest open reasoning and mathematics.
Context256K——
LicenceApache-2.0Open weightsOpen weights
Parameters295B MoE2.8T—
Released6 Jul 202617 Jul 2026—
CategoryOpen-Weight ModelsOpen-Weight ModelsOpen-Weight Models
OfficialTencent ↗Moonshot AI ↗Zhipu AI ↗

Highlighted rows are where these differ.

Hunyuan 3.0

  • 21B active parameters
  • EU/UK/Korea usage restrictions removed

Best for permissive MoE.

Full spec sheet →

Kimi K3

  • Tops the Frontend Code Arena
  • 76.8% on SWE-Bench Verified

Best for coding.

Full spec sheet →

GLM-5.2

  • 91.2 on GPQA Diamond
  • Strong agentic tool use

Best for maths and reasoning.

Full spec sheet →