MiniMax benchmarks.
A lab-level profile for MiniMax, covering tracked models, category leaders, open/proprietary mix, speed, value, source coverage, and portfolio depth.
Lab rank
#3
By available Arena average
Models tracked
5
4 open-weight models
Portfolio coverage
56%
Average matched benchmark signals
Fastest model
1.02s
Minimax M2.1 Preview
Lab profile
Portfolio shape, leaders, and model coverage.
The lab page now starts with the portfolio read, then drills into category leaders, value rankings, and model-level coverage rather than repeating source panels.
Portfolio read
MiniMax has 5 tracked benchmark profiles.
The portfolio combines 1 proprietary models and 4 open-weight models. Its average available Arena rank is 47.1, with a best category rank of #20. Average profile coverage is 56%, so model-level gaps remain visible in the cards below.
Best Arena model
Minimax M3
Best category rank #20
Highest coverage
Minimax M3
78% matched signals
Fastest response
Minimax M2.1 Preview
1.02s first token
Category leaders
Best model by benchmark lens.
Each card shows the highest-ranked model from this lab in a composite benchmark suite, with the global rank and index left intact.
Value
Quality, price, latency, and speed
Minimax M2.7
value index
Coding
Code Arena, SWE-bench, and output speed
Minimax M2.5
coding index
Agents
Search, document, code, and latency
Minimax M2.7
agent proxy
Reasoning
Text, document, vision, and mode signals
Minimax M3
reasoning proxy
Context
Document, search, and text proxy
Minimax M3
context proxy
MiniMax value ranking table
Models from this lab with both quality and commercial price matches.
Top 5 of 5
| Rank | Model | Index | Price | Latency | Speed | Quality | Sources |
|---|---|---|---|---|---|---|---|
| #27 | 65value index | $0.525blended / 1M tokens | 1.14stime to first token | 50 tok/soutput speed | 52quality signal | ArenaArtificial Analysis | |
| #28 | 64value index | $0.525blended / 1M tokens | 1.02stime to first token | 72 tok/soutput speed | 51quality signal | ArenaArtificial Analysis | |
| #33 | 64value index | $0.525blended / 1M tokens | 1.09stime to first token | 72 tok/soutput speed | 49quality signal | ArenaArtificial Analysis | |
| #39 | 62value index | $0.525blended / 1M tokens | 1.39stime to first token | 92 tok/soutput speed | 47quality signal | ArenaArtificial Analysis | |
| #53 | 57value index | $0.525blended / 1M tokens | 1.08stime to first token | 73 tok/soutput speed | 36quality signal | ArenaArtificial Analysis |
Model portfolio
MiniMax model coverage map.
Every tracked model keeps its best Arena rank, coverage score, commercial metrics, and suite placement visible in one scannable grid.
Minimax M3
minimax-m3
Coverage
78%
Best Arena
#20
Code
Value
#39
value index
Coding
#37
coding index
Latency
1.39s
92 tok/s
Minimax M2.7
minimax-m2.7
Coverage
44%
Best Arena
#48
Code
Value
#27
value index
Coding
#67
coding index
Latency
1.14s
50 tok/s
Minimax M2.1 Preview
minimax-m2.1-preview
Coverage
44%
Best Arena
#51
Code
Value
#28
value index
Coding
#68
coding index
Latency
1.02s
72 tok/s
Minimax M2.5
minimax-m2.5
Coverage
56%
Best Arena
#58
Code
Value
#33
value index
Coding
#21
coding index
Latency
1.09s
72 tok/s
Minimax M2
minimax-m2
Coverage
56%
Best Arena
#77
Code
Value
#53
value index
Coding
#59
coding index
Latency
1.08s
73 tok/s
