The new Qwen2-Math large language models are expected to help solve complex maths problems.

The Chinese start-up has released the Prover-V2 model a day after Alibaba released Qwen3, and ahead of an anticipated release of DeepSeek-R2.

New secret math benchmark stumps AI models and PhDs alike FrontierMath's difficult questions remain unpublished so that AI companies can't train against it.