Noometry

Model comparison

MiniMax-M2.1 vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 43.8 to 38.4 on the Noometry Index. MiniMax-M2.1 costs 2.7× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Last verified . 1 shared benchmarks.

MiniMax-M2.1 MiniMax

38.4

Rank #177 Confirmed

Step 5 Preview StepFun

43.8

Rank #78 Reported

Summary

  • They share 1 benchmark with published results for both. MiniMax-M2.1 scores higher in 0 categories and Step 5 Preview in 2 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Step 5 Preview leads 38.0 to 15.8.
  • MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
  • Step 5 Preview accepts more context: 1.02M tokens versus 205K.
  • MiniMax-M2.1 has downloadable open weights; the other is API-only.

Side by side

MiniMax-M2.1Step 5 Preview
ProviderMiniMaxStepFun
Noometry Index38.443.8
Released2025-12-232026-09-16
WeightsOpenProprietary
Context window205K1.02M
Max output131K66K
Input $ / M tokens$0.30$1
Output $ / M tokens$1.20$2.70
Results tracked223

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Step 5 Preview leads

MiniMax-M2.1: 40.1 (#132), Step 5 Preview: 50.6 (#40)

BenchmarkMiniMax-M2.1Step 5 Preview
LMArena WebDev13841569
SciCode—58.9%
LMArena Coding1421—
ALE-Bench623.83—

Agentic & Tool Use Not comparable

MiniMax-M2.1: 27.7 (#91), Step 5 Preview: —

BenchmarkMiniMax-M2.1Step 5 Preview
Terminal-Bench36.6%—

Reasoning Step 5 Preview leads

MiniMax-M2.1: 15.8 (#301), Step 5 Preview: 38.0 (#58)

BenchmarkMiniMax-M2.1Step 5 Preview
NYT Connections (extended)11.2%—
CritPt—20.9%
LMArena Hard Prompts1410—

Math Not comparable

MiniMax-M2.1: 35.6 (#142), Step 5 Preview: —

BenchmarkMiniMax-M2.1Step 5 Preview
LMArena Math1396—

Knowledge Not comparable

MiniMax-M2.1: 37.7 (#143), Step 5 Preview: —

BenchmarkMiniMax-M2.1Step 5 Preview
Vectara Hallucination Rate11.8%—
LMArena Expert1432—

Multilingual Not comparable

MiniMax-M2.1: 50.2 (#123), Step 5 Preview: —

BenchmarkMiniMax-M2.1Step 5 Preview
LMArena Non-English1378—
LMArena Chinese1430—
LMArena French1405—
LMArena German1380—
LMArena Japanese1287—
LMArena Korean1297—
LMArena Russian1386—
LMArena Spanish1396—

Instruction Following Not comparable

MiniMax-M2.1: 74.0 (#108), Step 5 Preview: —

BenchmarkMiniMax-M2.1Step 5 Preview
LMArena Instruction Following1399—

Long Context Not comparable

MiniMax-M2.1: 43.2 (#98), Step 5 Preview: —

BenchmarkMiniMax-M2.1Step 5 Preview
LMArena Longer Query1416—

Writing & Preference Not comparable

MiniMax-M2.1: 58.5 (#114), Step 5 Preview: —

BenchmarkMiniMax-M2.1Step 5 Preview
LMArena Text1392—
LMArena Creative Writing1362—
LMArena Multi-Turn1396—

Frequently asked questions

Is MiniMax-M2.1 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 43.8 to 38.4 on the Noometry Index. MiniMax-M2.1 costs 2.7× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Which is cheaper, MiniMax-M2.1 or Step 5 Preview?

MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Step 5 Preview lists at $1 and $2.70.

Is MiniMax-M2.1 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 50.6 versus 40.1 in the Noometry coding category.

Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 205K.

How many benchmarks do MiniMax-M2.1 and Step 5 Preview share?

1 benchmark has published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Step 5 Preview has 3.

Related comparisons

Go deeper