Skip to main content

MiniMax M2.7 vs MiniMax M3

SpecMiniMax M2.7MiniMax M3
Respan Index26.9 (#101)31.2 (#86)
Blended price per 1M$0.032$0.394
Context window205K1M
Input / output per 1M$0.018 / $0.072$0.225 / $0.9
Max output--
Inputtexttext, vision
Released2026-03-182026-06-01

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 M2.7MiniMax M3
Coding4.4 MiniMax M2.78.3 MiniMax M3
Agents39.6 MiniMax M2.747.8 MiniMax M3
Reasoning25.0* MiniMax M2.723.6 MiniMax M3
Knowledge & language20.0* MiniMax M2.733.4 MiniMax M3
Human preference50.9 MiniMax M2.753.2 MiniMax M3

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

Benchmarks both report

MiniMax M3 leads on 2 of the 2 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkMiniMax M2.7MiniMax M3
LMArena Elo14151435
LMArena WebDev (LMArena)13981484

FAQ

Is MiniMax M2.7 better than MiniMax M3?

MiniMax M3 scores 31.2 on the Respan Index (#86), ahead of MiniMax M2.7 at 26.9 (#101). MiniMax M3 leads on 2 of the 2 benchmarks both report.

Which is cheaper, MiniMax M2.7 or MiniMax M3?

MiniMax M2.7 lists at $0.018 input and $0.072 output per 1M tokens; MiniMax M3 at $0.225 and $0.9. MiniMax M2.7 is 13x cheaper per token at list price.

Which has the larger context window?

MiniMax M2.7 accepts 205K tokens and MiniMax M3 1M tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.