Model comparison

MiMo-V2-Pro vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 2.6× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Last verified . 14 shared benchmarks.

MiMo-V2-Pro Xiaomi

43.0

Rank #103 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • They share 14 benchmarks with published results for both. MiMo-V2-Pro scores higher in 3 categories and Step 5 Preview in 5 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 22.1.
  • MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
  • MiMo-V2-Pro accepts more context: 1.05M tokens versus 1.02M.

Side by side

MiMo-V2-Pro and Step 5 Preview specifications
MiMo-V2-ProStep 5 Preview
ProviderXiaomiStepFun
Noometry Index43.047.9
Released2026-03-182026-09-16
WeightsProprietaryProprietary
Context window1.05M1.02M
Max output131K66K
Input $ / M tokens$0.43$1
Output $ / M tokens$0.87$2.70
Results tracked2318

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

Category by category

Coding Step 5 Preview leads

MiMo-V2-Pro: 43.8 (#83), Step 5 Preview: 51.8 (#36)

Coding benchmarks
BenchmarkMiMo-V2-ProStep 5 Preview
LMArena WebDev14331564
LMArena Coding14761480
SciCode—58.9%
ALE-Bench785.17—

Reasoning Step 5 Preview leads

MiMo-V2-Pro: 22.1 (#206), Step 5 Preview: 40.0 (#57)

Reasoning benchmarks
BenchmarkMiMo-V2-ProStep 5 Preview
LMArena Hard Prompts14571465
NYT Connections (extended)25.8%—
CritPt—20.9%
Thematic Generalization45.9%—

Math Step 5 Preview leads

MiMo-V2-Pro: 39.5 (#102), Step 5 Preview: 46.1 (#72)

Math benchmarks
BenchmarkMiMo-V2-ProStep 5 Preview
LMArena Math14471470
ProofBench—42%

Knowledge Too close to call

MiMo-V2-Pro: 41.4 (#111), Step 5 Preview: 41.2 (#112)

Knowledge benchmarks
BenchmarkMiMo-V2-ProStep 5 Preview
LMArena Expert14781470

Multimodal Not comparable

MiMo-V2-Pro: —, Step 5 Preview: 41.0 (#41)

Multimodal benchmarks
BenchmarkMiMo-V2-ProStep 5 Preview
LMArena Vision—1267

Multilingual Step 5 Preview leads

MiMo-V2-Pro: 52.7 (#81), Step 5 Preview: 53.8 (#54)

Multilingual benchmarks
BenchmarkMiMo-V2-ProStep 5 Preview
LMArena Non-English14161432
LMArena Chinese14561519
LMArena Russian14271436
LMArena Spanish14571439
LMArena French1469—
LMArena German1417—
LMArena Japanese1366—
LMArena Korean1400—

Instruction Following Too close to call

MiMo-V2-Pro: 76.0 (#49), Step 5 Preview: 76.0 (#50)

Instruction Following benchmarks
BenchmarkMiMo-V2-ProStep 5 Preview
LMArena Instruction Following14451444

Long Context Step 5 Preview leads

MiMo-V2-Pro: 41.5 (#138), Step 5 Preview: 44.5 (#64)

Long Context benchmarks
BenchmarkMiMo-V2-ProStep 5 Preview
LMArena Longer Query14551455
CL-bench15.7%—
CL-bench Life6.9%—

Writing & Preference Too close to call

MiMo-V2-Pro: 62.8 (#70), Step 5 Preview: 62.8 (#71)

Writing & Preference benchmarks
BenchmarkMiMo-V2-ProStep 5 Preview
LMArena Text14361442
LMArena Creative Writing14151410
LMArena Multi-Turn14561447

Frequently asked questions

Is MiMo-V2-Pro better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 2.6× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Which is cheaper, MiMo-V2-Pro or Step 5 Preview?

MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Step 5 Preview lists at $1 and $2.70.

Is MiMo-V2-Pro or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 43.8 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2-Pro does, with 1.05M tokens against 1.02M.

How many benchmarks do MiMo-V2-Pro and Step 5 Preview share?

14 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and Step 5 Preview has 18.

Related comparisons

Go deeper