Model comparison

MiniMax M1 vs Step 3

MiniMax M1 and Step 3 score almost the same on the Noometry Index (40.3 vs 40.5), so choose on price, context window or the category you care about most.

Last verified . 15 shared benchmarks.

MiniMax M1 MiniMax

40.3

Rank #150 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 15 benchmarks with published results for both. MiniMax M1 scores higher in 1 category and Step 3 in 7 categories; 4 gaps are clear of the uncertainty.

Side by side

MiniMax M1 and Step 3 specifications
MiniMax M1Step 3
ProviderMiniMaxStepFun
Noometry Index40.340.5
Released2025-06-13—
WeightsOpenOpen
Context window1M—
Max output40K—
Input $ / M tokens$0.55—
Output $ / M tokens$2.20—
Results tracked1817

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

Category by category

Coding Too close to call

MiniMax M1: 39.9 (#153), Step 3: 40.1 (#147)

Coding benchmarks
BenchmarkMiniMax M1Step 3
LMArena Coding13591367

Reasoning Step 3 leads

MiniMax M1: 26.9 (#126), Step 3: 28.4 (#105)

Reasoning benchmarks
BenchmarkMiniMax M1Step 3
LMArena Hard Prompts13391355
Kagi LLM Benchmark—62.3%

Math Too close to call

MiniMax M1: 37.5 (#151), Step 3: 37.6 (#148)

Math benchmarks
BenchmarkMiniMax M1Step 3
LMArena Math13611366

Knowledge Too close to call

MiniMax M1: 36.4 (#170), Step 3: 36.8 (#164)

Knowledge benchmarks
BenchmarkMiniMax M1Step 3
LMArena Expert13171333

Multimodal Not comparable

MiniMax M1: —, Step 3: 35.5 (#86)

Multimodal benchmarks
BenchmarkMiniMax M1Step 3
LMArena Vision—1177

Multilingual Too close to call

MiniMax M1: 45.8 (#163), Step 3: 46.3 (#159)

Multilingual benchmarks
BenchmarkMiniMax M1Step 3
LMArena Non-English13191327
LMArena Chinese13601397
LMArena German13501371
LMArena Korean12661269
LMArena Russian13291331
LMArena Spanish13531371
LMArena French1370—
LMArena Japanese1217—

Instruction Following Step 3 leads

MiniMax M1: 69.3 (#174), Step 3: 70.4 (#164)

Instruction Following benchmarks
BenchmarkMiniMax M1Step 3
LMArena Instruction Following13121332

Long Context MiniMax M1 leads

MiniMax M1: 41.4 (#141), Step 3: 40.3 (#157)

Long Context benchmarks
BenchmarkMiniMax M1Step 3
LMArena Longer Query13261326
Fiction.LiveBench69.4%—

Writing & Preference Step 3 leads

MiniMax M1: 53.1 (#161), Step 3: 54.3 (#151)

Writing & Preference benchmarks
BenchmarkMiniMax M1Step 3
LMArena Text13431350
LMArena Creative Writing12981321
LMArena Multi-Turn13351341

Frequently asked questions

Is MiniMax M1 better than Step 3?

MiniMax M1 and Step 3 score almost the same on the Noometry Index (40.3 vs 40.5), so choose on price, context window or the category you care about most.

Is MiniMax M1 or Step 3 better for coding?

They score almost the same on coding (39.9 vs 40.1); test both on your own repository before choosing.

How many benchmarks do MiniMax M1 and Step 3 share?

15 benchmarks have published results for both models. MiniMax M1 has 18 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper