K-EXAONE (Reasoning)
LG AI ResearchProprietary
描述
K-EXAONE is a state-of-the-art large language model developed by LG AI Research with 236 billion parameters. It features advanced reasoning capabilities, strong performance in both Korean and English, and excels at complex tasks including mathematics, coding, and creative writing. The model uses A23B quantization for efficient inference while maintaining high quality outputs. K-EXAONE is designed for enterprise applications with robust instruction following and knowledge integration.
發布日期
2025-12-31
參數規模
236.0B
上下文長度
—
支援模態
text
能力雷達圖
80
general
0
coding
90
reasoning
68
science估算
70
agents
0
multimodal
缺少專門科學評測時,Science 由 LLM Stats 科學得分或推理能力估算。
排行榜排名
| 領域 | #排名 | 分數 | 來源 |
|---|---|---|---|
| 智慧體能力模型榜 | 96 | 43.0 | LS |
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))Agents
t2-bench
73.2%自報
Instruction Following
IFBench
67.3%自報
Language
MMMLU
85.7%自報
MMLU-Pro
83.8%自報
Math
AIME 2025
92.8%自報
Reasoning
LiveCodeBench v6
80.7%自報
AA 評測指數
(Artificial Analysis)暫無 AA 評測資料
LLM Stats 分類評分
(LLM Stats (zeroeval))Math90
Language80
Legal80
Reasoning80
Finance80
General80
Healthcare80
Instruction Following70
Agents70
Tool Calling70
定價
暫無定價資料
速度
暫無速度資料
供應商價格排行
暫無提供商資料