Pangu Pro MoE is an AI model published by Huawei, released on 2025-06-30, for Chat model, with 71.9B parameters, and 32K context length, requiring about 129.39 GB storage, with a 96.80 score on MATH-500.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Model basics
Open source & experience
Official resources
API details
Benchmark Results
Pangu Pro MoE currently shows benchmark results led by DROP (1 / 9, score 91.20), MMLU (15 / 124, score 89.30), MATH-500 (15 / 44, score 96.80). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
Math and Reasoning
3 evaluationsPublisher
Model Overview
Pangu Pro MoE is an AI model published by Huawei, released on 2025-06-30, for Chat model, with 71.9B parameters, and 32K context length, requiring about 129.39 GB storage, with a 96.80 score on MATH-500.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
