MiniMax-M2.5
READER SUMMARYA low-cost agentic model for coding, search, tools, office work, and sustained operational tasks.
Why this model scores 78.0
Strong agentic breadth, API access, low cost, and reported internal automation support high autonomy and deployment, while dangerous-domain evidence remains limited.
News tied to MiniMax-M2.5
The model score of 78.0 rates this model's risk profile. The overall Doom Index of 62.1 measures the recalibrated complete evidence corpus. These values answer different questions.
Each article's leave-one-out 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 are recalculated from their technical profile and related news, but never feed back into the overall index.
MiniMax-M2.5 automates substantial internal work at low operating cost
MiniMax released M2.5 and M2.5-Lightning for agentic coding, search, tools, and office work. MiniMax reports that M2.5 autonomously completes 30% of its internal tasks and generates 80% of newly committed code.
- Full item contribution
- +0.05
- MiniMax-M2.5 equal share
- +0.03
Model score history
- R2Doom Score 78.0
Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.
11 Aug 2026 - R1Doom Score 78.5
New exact dated public model absent from durable context.
11 Aug 2026