AI 导读
在覆盖编程、数学、指令遵循、通用知识、长上下文理解、工具使用和智能体任务的 34 项基准上,MiniCPM5-2B 取得平均分 53.9,排名第一。 它超越了排名第二的 2B 模型(33.2),以及表现最佳的 4B 级模型 Qwen3.5-4B。
正文
Across 34 benchmarks covering coding, math, instruction following, general knowledge, long-context understanding, tool use, and agentic tasks, MiniCPM5-2B achieves an average score of 53.9, ranking #1.
It outperforms the second-ranked 2B model at 33.2, as well as the top-performing 4B-class model, Qwen3.5-4B.
来源:@OpenBMB · x.com