On November 27th, Bijie.com reported that, according to Zhitong Finance, DeepSeek has launched a new mathematical reasoning model, DeepSeekMath-V2, which employs a self-verifiable training framework. This model is built on DeepSeek-V3.2-Exp-Base, automatically reviews generated mathematical proofs through an LLM validator, and continuously optimizes performance using high-difficulty samples.