@jiayuan_jy: A few objective clarifications: 1) This post has nothing to do with MiniMax (I never take sponsored posts). 2) 'Subjective feel' is not the same as actual performance; it's not quantitative data. After more extensive experience, overall coding ability is a qualitative improvement compared to m2.7. A current shortcoming is that 1-shot results compared with...
Summary
Jiayuan Zhang shared his initial experience with the M3 model's coding ability, stating that it is a qualitative improvement compared to m2.7, but the 1-shot results are not as comprehensive as Opus 4.6/4.7 and GPT5.5.
View Cached Full Text
Cached at: 06/01/26, 05:32 PM
A few objective clarifications:
- This has nothing to do with MiniMax (I never take sponsored posts)
- “Feel” is not the same as actual benchmark — it’s not quantitative data
After extended use, the overall coding capability is a generational improvement over m2.7. The only shortcoming I’ve found so far is that 1-shot results aren’t as comprehensive as Opus 4.6/4.7/gpt5.5 — there are cases where not all aspects are fully considered. https://t.co/Kd3stECxSM
Jiayuan (JY) Zhang (@jiayuan_jy): Been testing all morning. First impression is it’s close to Opus 4.7 (needs more testing).
Using M3 to write code, then Opus 4.8 + GPT5.5 for adversarial code review — works quite well.
One PR already completed.
Similar Articles
@sdrzn: MiniMax's new m3 model scores the same as opus 4.7 on terminal-bench 2.1 at 1/20th the compute/cost of their previous m…
MiniMax's new m3 model achieves the same score as Opus 4.7 on terminal-bench 2.1 while using 1/20th the compute and cost, attributed to their novel MiniMax Sparse Attention architecture.
Minimax M3 vs M2.7
Discussion comparing the new Minimax M3 model to its predecessor M2.7, seeking user feedback after two weeks of release.
Testing MiniMax M2.7 via API on three real ML and coding workflows
A developer tests the MiniMax M2.7 model via its API on three practical machine learning and coding workflows, evaluating its performance.
@PrajwalTomar_: wait. I already tested this model and didn't even know it Last month a stealth model called Space Bunny rebuilt a whole…
MiniMax 宣布此前以 "Space Bunny" 匿名现身的模型其实是 M3.1 Flash 的早期版本，其在 DeepSWE 编码上得 74%、BabyVision 视觉推理上得 91%，速度是 M3 的 3 倍而成本仅三分之一，适合长时间运行的智能体任务。
after a month with 5 Chinese coding LLMs, is M3 actually going to take the top spot?
A user shares a month-long comparison of five Chinese coding LLMs (Kimi K2.6, GLM-5.1, MiMo V2.5 Pro, MiniMax 2.7, DeepSeek V4 Pro) on a TypeScript/Next.js codebase, rating each in categories like frontend, backend, code review, all-rounder, and reasoning. They note MiniMax 2.7 achieves ~90% of Opus 4.6 quality at ~7% cost and speculate whether the upcoming MiniMax 3.0 will close gaps in planning and test coverage to become the top spot.