Alibaba DAMO Academy, in collaboration with the ModelScope community, recently announced the open sourcing of a new multilingual benchmark testing set, P-MMEval, aimed at comprehensively evaluating the multilingual capabilities of Large Language Models (LLMs) and conducting comparative analysis of cross-language transfer abilities. This testing set covers efficient datasets for both basic and specialized capabilities, ensuring consistency in multilingual coverage across all selected datasets, and provides parallel samples across multiple languages, supporting up to 10 languages from 8 different language families, including English, Chinese, and Arabic.

Moonshot AI's Kimi Chat is now fully open for service and no longer requires beta testing qualifications. Kimi Chat possesses strong multilingual capabilities, supporting context of approximately 200,000 Chinese characters. It achieves lossless long-range attention mechanisms through innovative network structures and engineering optimizations. Kimi Chat has significant advantages in Chinese and represents an innovation among large models trained primarily in English on the market. The open service of Kimi Chat will provide users with