跳转到主要内容

EXAONE 4.5 33B

LG AI ResearchProprietary

描述

EXAONE 4.5 is the first open-weight vision-language model from LG AI Research. It is a dense 33B multimodal model (31.7B language + 1.29B vision encoder) built by adding a dedicated visual encoder to the EXAONE 4.0 framework. It supports a 262,144-token context window, hybrid reasoning (thinking on by default), and strong performance on document understanding and Korean contextual reasoning while retaining EXAONE language capabilities. License: EXAONE AI Model License Agreement 1.2 - NC. Knowledge cutoff: December 2024.

发布日期
2026-04-09
参数规模
33.0B
上下文长度
—
支持模态
—

能力雷达图

13
general
24
coding
79
reasoning
59
science
70
agents
80
multimodal

排行榜排名

领域#排名分数来源
代码能力榜374
38.0
AA
通用能力榜282
45.0
AA
多模态榜71
53.0
LS
科学能力271
50.0
AA

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Chat

IFEvalGoogle Research (2023)89.6%自报
Tau2 Airline56.5%自报

Communication

Tau2 Retail77.9%自报
Tau2 Telecom73.0%自报

Language

MMLU-Pro83.3%自报

Math

AIME 202592.9%自报
AIME 202692.6%自报
MathVista-Mini85.0%自报

Multimodal

MMMU78.7%自报

Reasoning

LiveCodeBench v681.4%自报
GPQANYU + Cohere + Anthropic (2023)80.5%自报
AA-LCR50.6%自报

Vision

AI2D89.0%自报
MMStar74.9%自报
MMMU-Pro68.6%自报

AA 评测指数

(Artificial Analysis)
Gpqa(NYU + Cohere + Anthropic (2023))
79.4
Tau2(Sierra + U Toronto + Vector Institute (2025))
78.1
Ifbench(Google Research (2023))
58.0
Lcr(Artificial Analysis)
54.7
Coding Index(Artificial Analysis)
23.6
Terminalbench V2 1
21.3
Terminalbench Hard(Stanford × Laude Institute (2026))
20.5
Intelligence Index(Artificial Analysis)
13.2
Hle(Center for AI Safety + Scale AI (2025))
12.9

LLM Stats 分类评分

(LLM Stats (zeroeval))
Instruction Following
90
Math
90
Structured Output
90
Language
80
Legal
80
Multimodal
80
Physics
80
Reasoning
80
Finance
80
General
80
Healthcare
80
Biology
80
Chemistry
80
Vision
80
Chat
70
Communication
70
Tool Calling
70
Long Context
50

定价

输入价格免费
输出价格免费
混合价格(3:1)免费

速度

Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s

供应商价格排行

暂无提供商数据

外部链接