AIbase
Home
AI Tools
AI Models
MCP
AI NEWS
EN
Model Selection
Tags
Reward evaluation

# Reward evaluation

Acemath 72B Instruct
AceMath is a series of cutting-edge models designed specifically for mathematical reasoning. It is improved based on Qwen and is good at using chain-of-thought (CoT) reasoning to solve English mathematical problems.
Large Language Model Safetensors English
A
nvidia
3,141
18
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase