All families

FAMILY / TENCENT HY

Hunyuan / Hy

Tencent’s open reasoning and agent line, evolving from Hunyuan Large to Hy3.

First model
2024
Models
3
Latest
Hy3

01 / LINEAGE MAP

Model lineage

predecessor derived from

02 / GENERATIONS

What changed

01

Hunyuan Large

Tencent’s first large open MoE with 389B total and 52B active parameters.

02

Hy3 Preview

The first Hy3 preview after Tencent rebuilt its training stack, combining fast/slow reasoning with sparse MoE.

03

Hy3

The final Hy3 used product feedback to improve agents, coding, and output reliability.