Skip to main content

MiniMax M2 vs MiniMax M2.7

SpecMiniMax M2MiniMax M2.7
Respan Index17.4 (#147)26.9 (#101)
Blended price per 1M$0.446$0.032
Context window205K205K
Input / output per 1M$0.255 / $1.02$0.018 / $0.072
Max output128K-
Inputtexttext
Released2025-10-272026-03-18

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryMiniMax M2MiniMax M2.7
Coding4.6 MiniMax M24.4 MiniMax M2.7
Agents12.1 MiniMax M239.6 MiniMax M2.7
Reasoning19.7 MiniMax M225.0* MiniMax M2.7
Knowledge & language11.1* MiniMax M220.0* MiniMax M2.7
Human preference47.9 MiniMax M250.9 MiniMax M2.7

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

MiniMax M2.7 leads on 2 of the 2 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkMiniMax M2MiniMax M2.7
LMArena Elo13441415
LMArena WebDev (LMArena)12991398

FAQ

Is MiniMax M2 better than MiniMax M2.7?

MiniMax M2.7 scores 26.9 on the Respan Index (#101), ahead of MiniMax M2 at 17.4 (#147). MiniMax M2.7 leads on 2 of the 2 benchmarks both report.

Which is cheaper, MiniMax M2 or MiniMax M2.7?

MiniMax M2 lists at $0.255 input and $1.02 output per 1M tokens; MiniMax M2.7 at $0.018 and $0.072. MiniMax M2.7 is 14x cheaper per token at list price.

Which has the larger context window?

Both accept 205K tokens of context.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.