Artificial Analysis@ArtificialAnlys

2026-05-27 07:09·37天前

AI 摘要

OpenBMB发布了MiniCPM5-1B（Non-reasoning），一款1B参数的稠密大语言模型。该模型在Artificial Analysis Intelligence Index上获得17.9分，成为1B及以下开源模型中得分最高者。其得分领先同规模模型Qwen3.5 0.8B（10.5分）和Qwen3.5 2B（16.3分），性能超越前代模型MiniCPM-V 4.6 1.3B（12.7分）。MiniCPM5-1B为纯文本模型，上下文窗口128K，采用Apache 2.0许可证。在AA-Omniscience测试中，其通过选择“拒绝回答”而非猜测，避免了模型幻觉惩罚，获得了同尺寸类别的最高分。

OpenBMB has released MiniCPM5-1B （Non-reasoning）， the leading 1B open weights model， scoring 17.9 on the Artificial Analysis Intelligence Index

@OpenBMB is a China-based lab jointly founded in 2022 by Tsinghua University's NLP Lab and ModelBest Inc. This release extends the open weights Pareto frontier for Intelligence vs. Parameters at the sub-2B scale. It sits almost 2 points ahead of the best-performing 2B open weights model， @Alibaba's Qwen3.5 2B （Reasoning， 16.3）， and 7 points ahead of Qwen3.5 0.8B （Reasoning， 10.5）.

Unlike the recently released MiniCPM-V 4.6 1.3B Instruct， MiniCPM5-1B （Non-reasoning） does not support native multimodal input， and is text input and output only.

Key results：

➤ MiniCPM5-1B scores 17.9 on the Artificial Analysis Intelligence Index， the highest of any open weights model at 1B parameters or below by 7.4 points. The next-most-intelligent open weights model at this scale is Qwen3.5 0.8B （Reasoning， 10.5）. No other open weights model under 2B parameters has exceeded 15 on the Intelligence Index； its predecessor MiniCPM-V 4.6 1.3B sits at 12.7.

➤ MiniCPM5-1B extends the open weights Pareto frontier on both Intelligence vs. Total Parameters and Intelligence vs. Active Parameters at the sub-2B scale. It surpasses its predecessor MiniCPM-V 4.6 1.3B （12.7） by 5.3 points at ~23% fewer parameters， and beats Qwen3.5 2B （Reasoning， 16.3） by 1.6 points at less than half the parameter count.

➤ MiniCPM5-1B is more token-efficient than the larger reasoning peers it surpasses， but uses more output tokens than its （also non-reasoning） predecessor MiniCPM-V 4.6 1.3B. It used 12.6M output tokens to run the Intelligence Index， ~31x fewer than Qwen3.5 2B （Reasoning， 389M） and ~8x fewer than Qwen3.5 2B （Non-reasoning， 100M）， but ~2.3x more than MiniCPM-V 4.6 1.3B's 5.4M.

➤ AA-Omniscience score of -1 is the highest in its size class， earned by abstaining rather than hallucinating. MiniCPM5-1B declines to answer the vast majority of AA-Omniscience questions， avoiding the hallucination penalty that pulls sub-2B peers down to the -70 to -89 range （Qwen3.5 0.8B Non-reasoning at -89， MiniCPM-V 4.6 1.3B at -85， Exaone 4.0 1.2B Non-reasoning at -83）. Choosing to abstain rather than guess is the more honest posture， and AA-Omniscience credits it positively.

Artificial Analysis@ArtificialAnlys · X

67导出 Markdown

2026-05-27 07:09·37天前

在 X 看原推· x.com

AI 摘要

OpenBMB has released MiniCPM5-1B （Non-reasoning）， the leading 1B open weights model， scoring 17.9 on the Artificial Analysis Intelligence Index