The tech giant’s latest offering leverages large-scale reinforcement learning, rivalling DeepSeek in top benchmark tests
Tencent Holdings has unveiled a new artificial intelligence (AI) reasoning model, Hunyuan T1, that rivals DeepSeek’s R1 in both performance and pricing.
The Chinese technology giant’s latest offering, launched on Friday, leverages large-scale reinforcement learning, a technique also employed by DeepSeek in its R1 reasoning model, which launched in January.
The release is an official version of the model after a beta run of T1-preview on its chatbot Yuanbao. It scored 87.2 points on the Massive Multitask Language Understanding (MMLU) Pro benchmark, a test that gauges a model’s knowledge. That bested DeepSeek-R1’s 84 points but trailed the 89.3 points achieved by OpenAI’s o1, the reasoning model that the ChatGPT maker launched in December.
- Deep Dive: How These Top deepseek Optimization Companies Dominate the Industry
- From Closed to Open: Baidu Open-Sources ERNIE 4.5 Family, Outperforming Deepseek on Multiple Benchmarks
- China Set to Produce Over 100 DeepSeek-Level AI Breakthroughs, Says Former Central Bank Official
- Exclusive: DeepSeek Accused of Aiding Chinese Military and Circumventing U.S. Chip Bans
- Editorial: Financial Empowerment for Tech Innovation – Cultivating More “DeepSeek Moments”