Board/MiniMax/MiniMax-M2
mM

MiniMax-M2

MiniMax·Oct 27, 2025N/A

Open weights

Lean MoE with interleaved thinking built for coding/dev workflows — 230B total but only 10B active per token, which makes self-hosting realistic on modest clusters at unheard-of hosted prices.

Status
Generally available
License
Open weights · MIT
Context window
205K
Max output
66K
Input · $/M
$0.3
Output · $/M
$1.20
Cached input · $/M
—
Blended · $/M
$0.52
Parameters
230B MoE · 10B active
Inputs
Text only

Benchmarks

This model has no published scores on the benchmarks we track yet. Specs and pricing below the fold are still fully sourced.

Reasoning & knowledge

  • GPQA Diamond

    no public score

  • MMLU-Pro

    no public score

  • Humanity's Last Exam

    no public score

  • ARC-AGI-2

    no public score

Coding

  • SWE-bench Verified

    no public score

  • SWE-bench Pro

    no public score

  • LiveCodeBench

    no public score

Agents & computer use

  • Terminal-Bench 2

    no public score

  • OSWorld 2.0

    no public score

  • BrowseComp

    no public score

Math

  • AIME 2026

    no public score

Known strengths

  • 10B-active footprint self-hosts cheaply
  • Interleaved-thinking agent design

Primary sources

  • MiniMax platform
Compare this model →