MiniMax M3

weights

open(on HF

data

closed

code

partial(inference only

license

minimax-community(custom, see HF LICENSE)

MiniMax distributes MiniMax-M3's weights under a custom minimax-community license over a closed training corpus, with inference-only code and no training pipeline released. That combination of open weights with closed data and code makes MiniMax an open-weights release rather than a fully open model.

• https://huggingface.co/api/models/MiniMaxAI/MiniMax-M3 recorded 2026-08-13

  Public ungated weights repo (safetensors/MoE), `license: other` with `license_name: minimax-community`, `gated: false`, created 2026-06-02, 169,325 downloads.

• https://huggingface.co/MiniMaxAI/MiniMax-M3 recorded 2026-08-13

  M3 model card with a bundled LICENSE and vLLM / SGLang deployment guides; no training corpus named and no training pipeline linked, which is what holds data at closed and code at partial.

• https://venturebeat.com/technology/minimax-m3-debuts-eclipsing-gpt-5-5-and-gemini-3-1-pro-on-key-benchmark-performance-for-just-5-10-of-the-cost recorded 2026-06-04

  VentureBeat piece on the MiniMax M3 debut; the host answers HTTP 429.

Adoption is measured as Hugging Face downloads for the single declared checkpoint, MiniMax-M3, the release the product records as currently governing. MiniMax is also served through OpenRouter and offered free inside coding tools such as Kilo Code, channels a download count does not capture.

• https://huggingface.co/api/models/MiniMaxAI/MiniMax-M3 recorded 2026-08-13

  169,325 downloads in the trailing 30 days for MiniMaxAI/MiniMax-M3, the single declared artifact

• https://huggingface.co/MiniMaxAI/MiniMax-M2.5 recorded 2026-06-04

  ~693,331 downloads last month on the official HF model page

MiniMax-M3 reports 80.5% on SWE-bench Verified and 59.0% on SWE-bench Pro, alongside multimodal and agentic results, which puts it among the leading open-weight agentic models. The figures are self-reported, run on MiniMax's own infrastructure, and not independently audited.

• https://huggingface.co/MiniMaxAI/MiniMax-M3/raw/main/.eval_results/minimax-m3.yaml recorded 2026-09-29

  MiniMax's evaluation file in the M3 repo, "Extracted from the model card benchmark graph", records "SWE-Bench Verified - 80.5", "SWE-Bench Pro - 59.0", "MMMU-Pro - 78.1" and "Claw-Eval - 74.5", run "using Claude Code as the scaffolding".