Noometry

Model comparison

MiniMax-M2.1 vs Step 3.5 Flash

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.4 on the Noometry Index.

Last verified . 18 shared benchmarks.

MiniMax-M2.1 MiniMax

38.4

Rank #177 Confirmed

Step 3.5 Flash StepFun

41.7

Rank #116 Confirmed

Summary

  • They share 18 benchmarks with published results for both. MiniMax-M2.1 scores higher in 2 categories and Step 3.5 Flash in 6 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Step 3.5 Flash leads 21.2 to 15.8.
  • The biggest single-benchmark swing is NYT Connections (extended): 11.2% for MiniMax-M2.1 and 28.4% for Step 3.5 Flash.
  • Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
  • Step 3.5 Flash accepts more context: 256K tokens versus 205K.

Side by side

MiniMax-M2.1Step 3.5 Flash
ProviderMiniMaxStepFun
Noometry Index38.441.7
Released2025-12-232026-01-29
WeightsOpenOpen
Context window205K256K
Max output131K256K
Input $ / M tokens$0.30$0.10
Output $ / M tokens$1.20$0.30
Results tracked2219

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

Category by category

Coding Step 3.5 Flash leads

MiniMax-M2.1: 40.1 (#132), Step 3.5 Flash: 41.7 (#106)

BenchmarkMiniMax-M2.1Step 3.5 Flash
LMArena Coding14211436
LMArena WebDev1384—
ALE-Bench623.83—

Agentic & Tool Use Not comparable

MiniMax-M2.1: 27.7 (#91), Step 3.5 Flash: —

BenchmarkMiniMax-M2.1Step 3.5 Flash
Terminal-Bench36.6%—

Reasoning Step 3.5 Flash leads

MiniMax-M2.1: 15.8 (#301), Step 3.5 Flash: 21.2 (#202)

BenchmarkMiniMax-M2.1Step 3.5 Flash
NYT Connections (extended)11.2%28.4%
LMArena Hard Prompts14101411

Math Step 3.5 Flash leads

MiniMax-M2.1: 35.6 (#142), Step 3.5 Flash: 40.6 (#77)

BenchmarkMiniMax-M2.1Step 3.5 Flash
LMArena Math13961408
MathArena Final-Answer Competitions—66.8%

Knowledge Step 3.5 Flash leads

MiniMax-M2.1: 37.7 (#143), Step 3.5 Flash: 39.0 (#127)

BenchmarkMiniMax-M2.1Step 3.5 Flash
LMArena Expert14321422
Vectara Hallucination Rate11.8%—

Multilingual Too close to call

MiniMax-M2.1: 50.2 (#123), Step 3.5 Flash: 50.7 (#115)

BenchmarkMiniMax-M2.1Step 3.5 Flash
LMArena Non-English13781386
LMArena Chinese14301448
LMArena French14051421
LMArena German13801404
LMArena Japanese12871353
LMArena Korean12971350
LMArena Russian13861385
LMArena Spanish13961419

Instruction Following Too close to call

MiniMax-M2.1: 74.0 (#108), Step 3.5 Flash: 73.3 (#119)

BenchmarkMiniMax-M2.1Step 3.5 Flash
LMArena Instruction Following13991385

Long Context Too close to call

MiniMax-M2.1: 43.2 (#98), Step 3.5 Flash: 42.8 (#112)

BenchmarkMiniMax-M2.1Step 3.5 Flash
LMArena Longer Query14161402

Writing & Preference Too close to call

MiniMax-M2.1: 58.5 (#114), Step 3.5 Flash: 59.0 (#108)

BenchmarkMiniMax-M2.1Step 3.5 Flash
LMArena Text13921403
LMArena Creative Writing13621357
LMArena Multi-Turn13961405

Frequently asked questions

Is MiniMax-M2.1 better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.4 on the Noometry Index.

Which is cheaper, MiniMax-M2.1 or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.

Is MiniMax-M2.1 or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 40.1 in the Noometry coding category.

Which has the bigger context window?

Step 3.5 Flash does, with 256K tokens against 205K.

How many benchmarks do MiniMax-M2.1 and Step 3.5 Flash share?

18 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Step 3.5 Flash has 19.

Related comparisons

Go deeper