Model comparison

MiniMax-M2 vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 43.8 to 36.9 on the Noometry Index. MiniMax-M2 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 MiniMax

36.9

Rank #201 Confirmed

Step 5 Preview StepFun

43.8

Rank #78 Reported

Summary

  • They share 1 benchmark with published results for both. MiniMax-M2 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 18.6.
  • MiniMax-M2 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 has downloadable open weights; the other is API-only.

Side by side

MiniMax-M2 and Step 5 Preview specifications
MiniMax-M2Step 5 Preview
ProviderMiniMaxStepFun
Noometry Index36.943.8
Released2025-10-272026-09-16
WeightsOpenProprietary
Context window205K1.02M
Max output131K66K
Input $ / M tokens$0.30$1
Output $ / M tokens$1.20$2.70
Results tracked213

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

Category by category

Coding Step 5 Preview leads

MiniMax-M2: 39.1 (#151), Step 5 Preview: 50.6 (#40)

Coding benchmarks
BenchmarkMiniMax-M2Step 5 Preview
LMArena WebDev12971569
SWE-bench Verified (bash only)61%—
SciCode—58.9%
LMArena Coding1370—

Agentic & Tool Use Not comparable

MiniMax-M2: 24.9 (#102), Step 5 Preview: —

Agentic & Tool Use benchmarks
BenchmarkMiniMax-M2Step 5 Preview
Terminal-Bench30%—
Vending-Bench 2160.6—

Reasoning Step 5 Preview leads

MiniMax-M2: 18.6 (#256), Step 5 Preview: 38.0 (#58)

Reasoning benchmarks
BenchmarkMiniMax-M2Step 5 Preview
Kagi LLM Benchmark57.8%—
NYT Connections (extended)14.8%—
CritPt—20.9%
LMArena Hard Prompts1357—

Math Not comparable

MiniMax-M2: 34.6 (#158), Step 5 Preview: —

Math benchmarks
BenchmarkMiniMax-M2Step 5 Preview
LMArena Math1350—

Knowledge Not comparable

MiniMax-M2: 36.3 (#160), Step 5 Preview: —

Knowledge benchmarks
BenchmarkMiniMax-M2Step 5 Preview
LMArena Expert1336—

Multilingual Not comparable

MiniMax-M2: 45.6 (#165), Step 5 Preview: —

Multilingual benchmarks
BenchmarkMiniMax-M2Step 5 Preview
LMArena Non-English1314—
LMArena Chinese1367—
LMArena French1336—
LMArena German1366—
LMArena Russian1332—
LMArena Spanish1326—

Instruction Following Not comparable

MiniMax-M2: 70.4 (#160), Step 5 Preview: —

Instruction Following benchmarks
BenchmarkMiniMax-M2Step 5 Preview
LMArena Instruction Following1329—

Long Context Not comparable

MiniMax-M2: 40.5 (#148), Step 5 Preview: —

Long Context benchmarks
BenchmarkMiniMax-M2Step 5 Preview
LMArena Longer Query1332—

Writing & Preference Not comparable

MiniMax-M2: 53.3 (#157), Step 5 Preview: —

Writing & Preference benchmarks
BenchmarkMiniMax-M2Step 5 Preview
LMArena Text1340—
LMArena Creative Writing1288—
LMArena Multi-Turn1362—

Frequently asked questions

Is MiniMax-M2 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 43.8 to 36.9 on the Noometry Index. MiniMax-M2 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 or Step 5 Preview?

MiniMax-M2 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 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 50.6 versus 39.1 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 and Step 5 Preview share?

1 benchmark has published results for both models. MiniMax-M2 has 21 scored results on Noometry and Step 5 Preview has 3.

Related comparisons

Go deeper