AI News

Meituan Open-Sources LongCat-2.5: 1.6 Trillion Parameters, Trained Entirely on Ascend, Surpassing GPT-5.6 on 20 Benchmarks

Meituan released the weights of LongCat-2.5 on November 15, 2026, a 1.6-trillion-parameter MoE model trained entirely on Huawei Ascend chips without touching Nvidia GPUs, outperforming GPT-5.6-Sol on 20 of 27 tests. The report examines the evaluation data, analyzes how domestic chips affect the ceiling of model capability, and discusses the industrial significance under export controls.

美团 LongCat-2.5 昇腾芯片
88