Tencent Hy4 Preview Outperforms GLM-5.3 and Kimi K3 in Internal Blind Test

Tencent's newly released foundational model, Hy4 Preview, boasts a total parameter count of 77 billion and supports a context window of 1 million tokens. In internal blind testing, Hy4 Preview slightly outperformed Zhizhu GLM-5.3 and Kimi K3 from the Dark Side of the Moon. Third-party benchmark tests indicate that its performance differs from domestic models like Alibaba's Qwen 3.8 Max. Tencent has made the Hy4 Preview model weights available, allowing developers to use them through the Tencent Cloud platform and integrate them into products such as WorkBuddy and chatbots. The official demonstration of application scenarios includes game creation, 3D web design, and accounting compliance workflows, with future versions set to enhance capabilities through further pre-training and post-training.

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.