跳转到主要内容

MiniMax-M2.1

MiniMaxMiniMax开源权重MIT · 商用许可

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
205K
支持模态
text

能力雷达图

47
general
72
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
智能体能力模型榜85
51.0
LS
代码能力榜76
71.0
AA
通用能力榜58
74.0
AA
数学推理70
84.0
AA
科学能力74
65.0
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
31.4
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

Language
90
Legal
90
Finance
90
Healthcare
90
Communication
90
General
80
Instruction Following
70
Frontend Development
70
Tool Calling
70
Long Context
60
Math
60
Physics
60
Reasoning
60
Search
60
Biology
60
Chemistry
60
Code
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228.5
首Token延迟8.19s
首回答延迟16.94s

供应商价格排行

供应商价格排行

21 个供应商

最便宜: MiniMax最贵: Moark
供应商输入输出
1MiniMax最便宜
$0
$0
2Kilo Gateway
$0.27
$0.95
3Meganova
$0.28
$1.2
4OpenRouter
$0.29
$0.95
5302.AI
$0.3
$1.2
6SiliconFlow (China)
$0.3
$1.2
7Jiekou.AI
$0.3
$1.2
8Hugging Face
$0.3
$1.2
9ZenMux
$0.3
$1.2
10NovitaAI
$0.3
$1.2
11OpenCode Zen
$0.3
$1.2
12Amazon Bedrock
$0.3
$1.2
13Vercel AI Gateway
$0.3
$1.2
14MiniMax (minimax.io)
$0.3
$1.2
15LLM Gateway
$0.3
$1.2
16MiniMax (minimaxi.com)
$0.3
$1.2
17Merge Gateway
$0.3
$1.2
18NanoGPT
$0.33
$1.32
19Cortecs
$0.34
$1.34
20Synthetic
$0.55
$2.19
21Moark
$2.1
$8.4

比较该模型在不同 API 供应商之间的定价。

外部链接