MiniMax-M2
An open-weight coding and agent model built for long tool chains across browser, shell, Python, and MCP environments.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why this model scores 79.1
Long-chain tool use produces high autonomy, while open weights, APIs, and an agent product create near-maximal deployment and meaningful misuse and control difficulty.
News tied to MiniMax-M2
The model score of 79.1 rates this model's risk profile. The overall Doom Index of 67.9 measures the complete temporally weighted evidence record. These values answer different questions.
Each article's current Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores use a bounded temporal offset around their technical profile, but never feed back into the overall index.
MiniMax-M2 open weights push low-cost long-chain agents into broad access
MiniMax released MiniMax-M2 as an open-weight model for coding, browser, shell, Python, and MCP tool workflows, alongside APIs and an agent product.
- Full item contribution
- +0.20
- MiniMax-M2 equal share
- +0.20
Model score history
-
R3
Doom Score 79.1
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-142416 under temporal-monthly-pressure-v4.
12 Aug 2026 -
R2
Doom Score 78.7
Exact-version evidence chronology replayed after run doombench-hourly-news-20260812-132112 under fixed-sensitivity-v3.
12 Aug 2026 -
R1
Doom Score 77.7
New exact open-weight model absent from the durable catalogue.
11 Aug 2026