MiniMax

MiniMax M2

by MiniMaxtext->text3 endpoints
Neura Intelligence Index
45.5/ 100
Rank
#199
Confidence
medium
Benchmarks
7(18% coverage)

Overview

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...

Capabilities

Text generation
Tool use / Function calling
Structured output
Extended reasoning
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
204.8K tokens
Max Output
131.1K tokens
Tokenizer
Other
Uptime (24h)
10000.0%
Parameters
230000000000B
License
mitOpen Weights
Country
🇨🇳CN
Release Date
October 27, 202510mo

Supported Parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Benchmark Performance

coding

BenchmarkScoreSource
SWE-bench Verified
69.4
verified
TerminalBench
46.3
verified
SciCode
36
verified

math

BenchmarkScoreSource
AIME 2025
78
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
78
verified
Humanity's Last Exam
12.5
verified

agent

BenchmarkScoreSource
BrowseComp
44
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.26
Output$1.02
Added
October 23, 2025
Last synced 9/18/2026