MiniMax M2.7
The open-source AI that improves its own training
The Panel's Take
MiniMax M2.7 is a 230B-parameter Mixture-of-Experts model (10B active) that does something no major open-source model has done before: it participates in its own development cycle. During training, M2.7 updated its own memory, built skills for RL experiments, and improved its own learning process — with an internal version autonomously optimizing a programming scaffold over 100+ rounds to achieve a 30% performance improvement. On benchmarks, M2.7 scores 56.22% on SWE-Pro and 57.0% on TerminalBench 2, putting it in the same tier as GPT-5.3 for coding tasks. It achieves an ELO of 1495 on GDPval-AA (highest among open-source models) and 97% skill adherence across 40+ complex, multi-thousand-token skills. For office productivity tasks — generating Word, Excel, and PowerPoint files, running financial analysis — it performs at junior analyst level. Released under MIT license on April 12, 2026, M2.7 is available on Hugging Face and via the MiniMax API. The model is particularly strong at agentic workflows: tool calling, multi-step task execution, and professional productivity use cases that require sustained context and precise instruction following.
Share this verdict
MiniMax M2.7 verdict: SHIP 🚀 3 ships · 1 skip from the expert panel Full review: shiporskip.io/tool/minimax-m27-self-evolving-agentic-model-open-source-2026
Weekly AI Tool Verdicts
Get the next verdict in your inbox
7 critics review a new AI tool every day. Weekly digest — free.
Compare MiniMax M2.7 with Others
Embed this verdict
Tool makers can add a live ShipOrSkip badge to their site. Badge loads track impressions; clicks route back to this review.
<a href="https://shiporskip.io/api/badge-click/minimax-m27-self-evolving-agentic-model-open-source-2026" target="_blank" rel="noopener"><img src="https://shiporskip.io/api/badge/minimax-m27-self-evolving-agentic-model-open-source-2026" alt="MiniMax M2.7 Ship verdict on ShipOrSkip" width="360" height="90" /></a>[](https://shiporskip.io/api/badge-click/minimax-m27-self-evolving-agentic-model-open-source-2026)<iframe src="https://shiporskip.io/embed/minimax-m27-self-evolving-agentic-model-open-source-2026" title="MiniMax M2.7 ShipOrSkip verdict" width="360" height="260" style="border:0;border-radius:16px;max-width:100%;" loading="lazy"></iframe>The reviews
“MIT license, 10B active params, and SWE-Pro scores matching GPT-5.3? This is the open-source agentic backbone I've been waiting for. The self-improvement angle is genuinely unprecedented — watching a model optimize its own scaffold over 100 rounds is the kind of thing that used to be sci-fi.”
“230B total parameters is not something most people can run locally — you need serious cluster access or you're using their API, which means the 'open source' framing is mostly PR. And 'self-evolving' sounds revolutionary but the actual mechanism is AutoML loop, something the field has had for years.”
“A model that improves its own training process is a meaningful step toward recursive self-improvement. Even if the current implementation is narrow, this is the architectural direction that matters. MiniMax just showed a credible open-source path to it.”
“97% skill adherence across 2,000-token skills means M2.7 can actually execute complex creative briefs without drifting. For long-form content workflows that need consistent style and structure, this is a real upgrade over models that forget instructions halfway through.”