Microsoft Corp. has developed a small language model that can solve certain math problems better than algorithms several times its size. The company revealed the model, Phi-4, on Thursday. The ...

Companies like OpenAI continue to push the boundaries with large language (LLM) models in its pursuit of the holy grail of artificial general intelligence (AGI). Meanwhile, Microsoft is taking a ...

微软下一代14B小模型Phi-4出世了！仅用了40%合成数据，在数学性能上击败了GPT-4o，最新36页技术报告出炉。 最近，微软下一代小模型Phi-4正式亮相。在GPQA和MATH基准上，其数学性能直接碾压GPT-4o、Gemini Pro 1.5 ...