跳转到主要内容

MiniMax-M2.1

MiniMaxMiniMaxOpen WeightMIT · Commercial OK

描述

MiniMax M2.1 is an enhanced large language model focused on multi-language programming and real-world complex tasks. It features exceptional capabilities across Rust, Java, Golang, C++, Kotlin, Objective-C, TypeScript, JavaScript and more, with industry-leading multilingual performance that outperforms Claude Sonnet 4.5 and approaches Claude Opus 4.5. M2.1 significantly strengthens native Android and iOS development, delivers enhanced design comprehension and aesthetic expression for web/app scenarios, and provides more concise responses with improved speed and reduced token consumption. It excels across various coding agent frameworks including Claude Code, Droid (Factory AI), Cline, Kilo Code, Roo Code, and BlackBox.

发布日期
2025-12-23
参数规模
230.0B
上下文长度
197K
支持模态
text

能力雷达图

51
general
50
coding
83
reasoning
56
science估算
70
agents
0
multimodal

Science 在缺少专门科学评测时使用推理能力代理估算。

排行榜排名

领域#排名分数来源
智能体与工具73
51.0
LS
代码能力榜83
65.0
AA
通用能力榜54
78.0
AA
数学推理70
84.0
AA
科学能力62
68.0
AA

基准测试分数 (LLM Stats)

Agents

BrowseComp62.0%自报
Terminal-Bench47.9%自报
Toolathlon43.5%自报

Biology

GPQA81.0%自报
SciCode39.0%自报

Code

VIBE Web91.5%自报
VIBE Android89.7%自报
VIBE88.6%自报
VIBE iOS88.0%自报
VIBE Simulation87.1%自报
VIBE Backend86.7%自报
LiveCodeBench78.0%自报
SWE-bench Multilingual72.5%自报
SWT-Bench69.3%自报
SWE-Bench Verified67.0%自报
Multi-SWE-Bench49.4%自报
OctoCodingBench26.1%自报
SWE-Review8.9%自报
SWE-Perf3.1%自报

Communication

Tau2 Telecom87.0%自报

Finance

MMLU-Pro88.0%自报

General

IFBench70.0%自报

Long Context

AA-LCR62.0%自报

Math

AIME 202581.0%自报
Humanity's Last Exam22.0%自报

AA 评测指数

Math Index
82.7
Intelligence Index
39.4
Coding Index
32.8
Mmlu Pro
0.9
Tau2
0.9
Gpqa
0.8
Aime 25
0.8
Livecodebench
0.8
Ifbench
0.7
Lcr
0.6
Scicode
0.4
Terminalbench Hard
0.3
Hle
0.2

LLM Stats 分类评分

Communication
90
Finance
90
Healthcare
90
Language
90
Legal
90
General
80
Tool Calling
70
Frontend Development
70
Instruction Following
70
Biology
60
Chemistry
60
Code
60
Long Context
60
Math
60
Physics
60
Reasoning
60
Search
60
Agents
50
Vision
20

定价

输入价格$0.3 / 1M tokens
输出价格$1.2 / 1M tokens
混合价格(3:1)$0.525 / 1M tokens

速度

Tokens/秒86.3 tokens/s
首Token延迟1.30s
首回答延迟24.49s

可用提供商

(LS 内部计价单位)
提供商输入价格输出价格
MiniMax300K1.2M

外部链接