On June 14th, Turing Award winner and Meta's chief AI scientist Yann LeCun joined Abacus.AI, New York University and other institutions to launch a new large model evaluation benchmark LiveBench AI, and released the first evaluation list. The newly open-sourced large model Qwen2-72B of Aliyun Tongyi Qianwen became the top-ranking open source large model and the only Chinese large model among the top ten lists, with better performance than Meta's Llama3-70B model. At present, the download volume of Qwen series open source models has exceeded 16 million.
阿里通义Qwen2拿下美国最新测评榜单开源大模型全球第一
Ali Tongyi Qwen2 tops the latest evaluation list in the USA and ranks first in the global open-source large model.
The translation is provided by third-party software.
The above content is for informational or educational purposes only and does not constitute any investment advice related to Futu. Although we strive to ensure the truthfulness, accuracy, and originality of all such content, we cannot guarantee it.