Tencent Hunyuan 2.0 Instruct

Open weights Tencent · 2025-12-05 · Tencent Hunyuan Community License

Tencent's next-generation foundation model, released December 5 2025 as 406B total / 32B active MoE with a 256K context. Ships in HY 2.0 Think and HY 2.0 Instruct variants, integrated into Yuanbao and ima, and exposed via Tencent Cloud API. Reported sharp gains in math (IMO-AnswerBench) and coding (SWE-bench Verified) over predecessors.

Architecture

Schema-generated from data/models.yaml. Every label is auditable against the model's sources.

Specs

Architecture: moe
Total params: 406B
Active params: 32B
Context window: 256K tokens
Attention: unknown
Position encoding: unknown
Post-training: sft, rlhf
OSI-approved: no
Data released: no
Training code: not released

Benchmarks

Each score carries the date it was published; we never infer or interpolate missing scores.

Available quantizations

— not catalogued

Notable innovations

· Think and Instruct dual variants
· 256K context
· Native integration with Yuanbao and ima products

Lineage

Tencent's next-gen Hunyuan; 406B MoE first appearing in the catalog.