Best Coding Model
MiniMaxProvisional

MiniMax M2.7

MiniMax M / MiniMax M2.7 · MiniMaxAI/MiniMax-M2.7

Open-weight Chinese agent model for complex software engineering and productivity workflows.

Objective score

37.8

Confidence

86%

Price evidence

Pricing evidence pending

Other primary tiers in this family

MiniMax M2.7MiniMax M3

Evidence state

Signal coverage

Benchmarks
3
Rank points
7
Usage
2
Agent
0
Sources
4

Objective evidence

Benchmarks and public signals

Swebench
56.2
Livecodebench
Aider
Artificial Analysis
52.6
Openrouter Usage
0.5
Kilo Usage

Persistent history

Recent ranking points

Aug 1#37 · 36
Aug 1#37 · 36
Jul 31#36 · 36
Jul 31#36 · 36
Jul 31#36 · 36
Jul 31#36 · 36

Usage signals

OpenRouter0.5%
Overall0.3%

Agent and tool signals

Evidence is being collected. Missing data is not treated as zero.