whatmodel.sh / MiniMax-M2

MiniMax-M2

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

MiniMax-M2 is an open-weights language model from MiniMax, released October 2025. Its published size is 230B parameters (10B active per token) and a 205k-token context window. Licence: modified-mit.

64.6±1.2#149 of 719 LLMsfrom 7 benchmark results across 5 sources

$ how it compares

The LLMs ranked either side of MiniMax-M2, out of 828 with a score, then more from MiniMax.

#modelscorewhereRAMreleased
169GLM-4.5 Z.ai65±1api $1.00/M +local~58GB2025-07
170Solar Pro 4 Upstage65±2api $0.53/M2026-08
171MiniMax-M2 MiniMax65±1api $0.53/M +local~75GB2025-10
172Laguna XS.2 Poolside65±2local~21GB2026-04
173Qwen3 235B-A22B Instruct 2507 Alibaba65±1api $0.20/M +local~76GB2025-07
more from MiniMax
84MiniMax-M3 MiniMax70±1api $0.48/M +local~137GB2026-06
120MiniMax-M2.7 MiniMax68±1api $0.53/M +local~75GB2026-03
150MiniMax-M2.5 MiniMax66±1api $0.53/M +local~75GB2026-02

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #104 of 300 · 34% of its score · 3 tests

Beats Grok 4.20 (0309 reasoning), Grok 4.3, o3-pro here, though they rank higher overall. Trails SmolLM3 3B, Nova 2 Pro (Preview), Mistral Medium 3.5 (128B) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
ContractBench success rate (33 observation-contract tool tasks)53.5% ✎▆··▆▄▂▄▂▆▆█▄ beats 14/23very hard · avg 14%▇▇▇▇▇ 12%sharp · at its level
τ²-bench Telecom lab87.0% ✎▁·▅█▆▅▂▃▃▂▃▁ beats 64/89medium · avg 35%▇▇▇▇▇ 12%sharp · small run
Terminal-Bench 2.0 with Terminus 2 agent (benchmark authors' runs)30.0% ✎▃··▃·▃▃██▅▃▅ beats 8/14very hard · avg 5.8%▇▇▇▇ 11%sharp
coding▁▁▁▃▆██▇▆▄▃▁ #133 of 458 * · 23% of its score · 1 test

Beats Qwen3.5 Plus, Gemini 2.5 Pro, Gemini 3.1 Flash-Lite here, though they rank higher overall. Trails Devstral Small 2 24B, Llama 3.1 Nemotron Ultra 253B v1, Nemotron 3.5 Lightning 30B-A3B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
Arena WebDev (Code Arena)1296.6 ✎▁▂▄▃▅█▄▇▆▄▁▁ beats 20/119avg 981▇▇▇▇▇▇▇▇▇ 23%sharp
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #166 of 393 * · 13% of its score · 1 test

Trails LFM2.5 1.2B Instruct, LFM2.5 1.2B Thinking, LFM2.5 8B-A1B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena (text)1343.4 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 184/379avg 1268▇▇▇▇▇ 13%blunt
other tests2 not in a task · 29% of its score
testresultvs the others in its rundifficultycountswhy
Medmarks-V mean win rate (19 verifiable medical benchmarks, 71 configurations)0.5708 ✎▁▄▃▃▇▄█▃▅▁▁▁ beats 26/30avg 0.423▇▇▇▇▇▇▇▇ 20%sharp
Medmarks-V weighted mean win rate (61 models, 71 configurations)57.1% ✎▂▃▅▂▆▃█▅█▅▃▆ beats 27/34medium · avg 42%▇▇▇▇ 9.5%blunt · at its level

$ where to run it

Through an API

api · Amazon Bedrock · $0.52/M · $0.3 in / $1.2 out per 1M tokens · 205k context · docs.aws.amazon.com ↗ · price sourceStandard base token rate from models.dev. Provider-specific tiers, long-context surcharges, caching and promotions may differ.

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run MiniMax-M2 · needs ~138.5 GB · from huggingface.co/unsloth
    chat in the terminal
    llama cli -hf unsloth/MiniMax-M2-GGUF:UD-Q4_K_XL
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf unsloth/MiniMax-M2-GGUF:UD-Q4_K_XL

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run MiniMax-M2 · needs ~138.5 GB · from huggingface.co/unsloth

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/unsloth/MiniMax-M2-GGUF@UD-Q4_K_XL -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Official weights and documentation: huggingface.co/MiniMaxAI ↗

$ how the score was worked out · LMArena leaderboard dataset 36%, Medmarks: A Comprehensive Ope… 29%, ContractBench: Can LLM Agents… 12% and 2 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
LMArena leaderboard dataset2▇▇▇▇▇▇▇▇▇▇▇ 36%CC BY 4.0
Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks — authors' own runs of 61 models2▇▇▇▇▇▇▇▇▇ 29%CC BY 4.0
ContractBench: Can LLM Agents Preserve Observation Contracts? (arXiv:2605.17281v2)1▇▇▇▇ 12%CC BY 4.0
MiniMax vendor-reported benchmark scores for its own models (Hugging Face model cards) · lab-reported1▇▇▇ 12%Factual vendor-reported score (not licensed content)
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces — benchmark authors' own agent-model trials1▇▇▇ 11%CC BY 4.0
prior · pull toward the middle▇ 1%
weighted average= 64.6

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json