# 韩国Upstage发布Solar Pro 3：韩实验室第二强模型

- 来源：Artificial Analysis (@ArtificialAnlys)
- 发布时间：2026-04-08 13:14
- AIHOT 链接：https://aihot.virxact.com/items/cmnw1ypbx00o5slc3wmgqf1v2
- 原文链接：https://x.com/ArtificialAnlys/status/2041746467543732522

## AI 摘要

韩国AI实验室Upstage发布Solar Pro 3，AI Index得分26，为韩国实验室第二强模型。采用MoE架构（102B总参数/12B激活参数），支持128k上下文。核心优势在于agentic工具调用与指令遵循，IFBench得分71%与GLM-5、Kimi K2.5相当，τ²-Bench Telecom达86%。但token消耗较高（约100M），可靠性不足（AA-Omniscience得分-54），准确性18%优于其他韩国模型。可通过Upstage API访问。

## 正文

🇰🇷 South Korean AI lab Upstage has launched Solar Pro 3！ Solar Pro 3 scores 26 on the Artificial Analysis Intelligence Index， a significant improvement over Solar Pro 2 and is currently the second strongest model released by a Korean lab

Key benchmarking takeaways：

➤ Strength in agentic tool use and instruction following： @upstageai's Solar Pro 3 scores 71% on IFBench， which signals strong instruction following capabilities. Solar Pro 3 ranks near the frontier models in this category， scoring similarly to GLM-5 （71%） and Kimi K2.5 （70%） and is the leader among Korean models. Solar Pro 3 scores also 86% on τ2-Bench Telecom， demonstrating strong performance on agentic tool-use， making it a strong candidate for incorporation into agentic workflows.

➤ Relatively high token usage： Solar Pro 3 demonstrates relatively high token usage compared to other models in the same intelligence tier， using ~100M reasoning tokens across the Artificial Analysis Intelligence suite. This is comparable to LG's K-EXAONE （100M reasoning tokens）， another Korean model.

➤ Modest accuracy and reliability： Solar Pro 3 scores -54 on AA-Omniscience， our evaluation of knowledge reliability and hallucination， where scores range from -100 to 100 （higher is better） and a negative score indicates more incorrect than correct answers. However， with an 18% on accuracy component score， Solar Pro 3 does outperform Korean competitors in this metric.

➤ First-party and third-party API access： Solar Pro 3 is a proprietary model and is currently available through Upstage's first-party API

Other Relevant Model Details：

➤ Model type： Mixture of Experts （MoE）
➤ Size： 102B total parameters （12B active parameters）
➤ Context length： 128k
➤ Training data cut-off： July 2025

See below for further analysis