Kimi K2首发测评:5轮推理+60%搜索能力,它比GPT还懂人类?-腾讯云开发者社区-腾讯云 KimiK2Thinking开源大模型登顶AI榜单,1T参数+32B激活架构实现高效推理。支持128k上下文,在Agent能力、自主搜索、编程等方面表现卓越,Humanity’s Last Exam测试44 9%创纪录。MoE架构优化成本,256K长文本处理和多轮工具调用能力领先,国内大模型进入自主思考新时代。
Kimi K2 - Open Agentic Intelligence by MoonshotAI Kimi K2 is an advanced AI model by MoonshotAI, featuring 128K context length, superior performance in reasoning, coding, and multilingual tasks Available as open-source models and API