Hy3 Officially Released With 256K Context
alifcoder · x · 2026-07-11
Hunyuan's Hy3 has been officially released, focusing on a "practical-first" approach.
Key highlights:
- 295B MoE with 21B activated parameters
- 256K context length
- Outperforms GLM-5.1 in blind expert evaluations
- Hallucination rate reduced from 12.5% to 5.4%
- Open-sourced under Apache 2.0, available for free trial on OpenRouter
The post stresses its competitiveness even against models 2–5 times its size.
More from Models
- OpenAI ships GPT-6.1 Terra; Brockman says its computer use now beats his own speed — gdb · 2026-10-27
- Kimi K3.1 Pro regresses on Debate Benchmark while DeepSeek 1017 gains at lower cost — teortaxesTex · 2026-10-27
- 4 Hours of LLM Startup Research Produced a Convincing but Nonsense Product Thesis — annetgriffin · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- MiniMax matches Claude Opus 4.5 in non-benchmaxxed evals, users report — teortaxesTex · 2026-10-27
- Real-world math: GPT-6.1 Terra's half price is offset by 2-3x token usage, costing more than Sol — lordpuddingcup · 2026-10-27