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.
发布日期
2025-12-31
参数规模
236.0B
上下文长度
—
支持模态
text
能力雷达图
80
general
0
coding
90
reasoning
68
science估算
70
agents
0
multimodal
缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。
排行榜排名
| 领域 | #排名 | 分数 | 来源 |
|---|---|---|---|
| 智能体能力模型榜 | 96 | 43.0 | LS |
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
t2-bench
73.2%自报
Instruction Following
IFBench
67.3%自报
Language
MMMLU
85.7%自报
MMLU-Pro
83.8%自报
Math
AIME 2025
92.8%自报
Reasoning
LiveCodeBench v6
80.7%自报
AA 评测指数
(Artificial Analysis)暂无 AA 评测数据
LLM Stats 分类评分
(LLM Stats (zeroeval))Math90
Language80
Legal80
Reasoning80
Finance80
General80
Healthcare80
Instruction Following70
Agents70
Tool Calling70
定价
暂无定价数据
速度
暂无速度数据
供应商价格排行
暂无提供商数据