Hunyuan Hy3-preview

Available

Tencent HunyuanFrontierOpen weights

Tencent's third-generation Hunyuan, rebuilt from scratch in ~90 days and open-sourced as the "Hy3 preview". A 295B-total / 21B-active Transformer MoE (80 layers, 192 experts with top-8 routing, plus a 3.8B multi-token-prediction layer) with a 256K-token context, positioned as a leading open reasoning-and-agent model for its size with strong cost efficiency. Vendor-reported results: 74.4 on SWE-bench Verified, 54.4 on Terminal-Bench 2.0, and 70.2 on WideSearch, with strong STEM-olympiad performance. Open weights on GitHub and Hugging Face under Tencent's community license.

Official page ↗Model card ↗

Specifications

License: Open weights · Tencent License
Weights: Downloadable
Architecture: Mixture-of-Experts
Parameters: 295B · 21B active
Context window: 256K tokens
Max output: —
Knowledge cutoff: —
Price (in / out, $/M): —
Modalities: TextCode

Benchmarks

No benchmark scores recorded yet. Spotted some? Submit a correction.

Vendor-reported figures are claims until independently verified. See methodology.