Passer au contenu principal
AITier

MiniMax-M2.1

MiniMaxMiniMaxOpen WeightMIT · Usage Commercial

Description

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.

Date de sortie
2025-12-23
Paramètres
230.0B
Longueur du contexte
205K
Modalités
text

Radar de capacités

41
general
81
coding
83
reasoning
65
science
70
agents
0
multimodal

Classements

Domaine#RangScoreSource
Capacité agentique74
43.0
LS
Classement codage185
69.0
AA
Classement général111
66.0
AA
Science182
61.0
AA

Scores de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

Toolathlon43.5%Aut.

Code

VIBE Web91.5%Aut.
VIBE Android89.7%Aut.
VIBE88.6%Aut.
VIBE iOS88.0%Aut.
VIBE Simulation87.1%Aut.
VIBE Backend86.7%Aut.
SWT-Bench69.3%Aut.
OctoCodingBench26.1%Aut.
SWE-Review8.9%Aut.
SWE-Perf3.1%Aut.

Communication

Tau2 Telecom87.0%Aut.

Instruction Following

IFBench70.0%Aut.

Language

MMLU-Pro88.0%Aut.

Math

AIME 202581.0%Aut.

Reasoning

GPQANYU + Cohere + Anthropic (2023)81.0%Aut.
LiveCodeBench78.0%Aut.
SWE-bench Multilingual72.5%Aut.
SWE-Bench Verified67.0%Aut.
AA-LCR62.0%Aut.
BrowseCompOpenAI (2025)62.0%Aut.
Multi-SWE-Bench49.4%Aut.
Terminal-Bench47.9%Aut.
SciCode39.0%Aut.
Humanity's Last Exam22.0%Aut.

Indices d'évaluation AA

(Artificial Analysis)
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
87.5
Tau2(Sierra + U Toronto + Vector Institute (2025))
85.4
Gpqa(NYU + Cohere + Anthropic (2023))
83.0
Math Index(Artificial Analysis)
82.7
Aime 25(MAA (Mathematical Association of America))
82.7
Livecodebench(UC Berkeley + MIT + Cornell (2024))
81.0
Ifbench(Google Research (2023))
69.9
Lcr(Artificial Analysis)
67.7
Terminalbench Hard(Stanford × Laude Institute (2026))
28.8
Hle(Center for AI Safety + Scale AI (2025))
23.2
Intelligence Index(Artificial Analysis)
20.9

Scores par catégorie LLM Stats

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

Tarification

Prix d'entrée$0.3 / 1M tokens
Prix de sortie$1.2 / 1M tokens
Prix mixte (3:1)$0.525 / 1M tokens
Prix de lecture cache$0.03 / 1M tokens
Prix d'écriture cache$0.375 / 1M tokens

Vitesse

Tokens/sec0.0
Délai du premier token0.00s
Temps de réponse0.00s

Classement des Prix par Fournisseur

Classement des Prix par Fournisseur

15 fournisseurs

Moins cher: MiniMaxPlus cher: Moark
FournisseurEntréeSortie
1MiniMaxMoins cher
$0
$0
2LLM Gateway
$0.27
$1.1
3302.AI
$0.3
$1.2
4OpenRouter
$0.3
$1.2
5Jiekou.AI
$0.3
$1.2
6ZenMux
$0.3
$1.2
7NovitaAI
$0.3
$1.2
8Kilo Gateway
$0.3
$1.2
9Vercel AI Gateway
$0.3
$1.2
10MiniMax (minimax.io)
$0.3
$1.2
11MiniMax (minimax.cn)
$0.3
$1.2
12Merge Gateway
$0.3
$1.2
13Ofox
$0.3
$1.2
14NanoGPT
$0.33
$1.32
15Moark
$2.1
$8.4

Comparer les prix entre différents fournisseurs API pour ce modèle.

Sources externes

LLM StatsArtificial Analysis