Model comparison

MiniMax-M2 vs Step 3.5 Flash

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 37.4 on the Noometry Index.

Last verified October 10, 2026. 16 shared benchmarks.

MiniMax-M2

MiniMax

37.4

Rank #204 Confirmed

Step 3.5 Flash

StepFun

42.3

Rank #116 Confirmed

Summary

They share 16 benchmarks with published results for both. MiniMax-M2 scores higher in 0 categories and Step 3.5 Flash in 8 categories; 8 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Step 3.5 Flash leads 58.8 to 53.0.
The biggest single-benchmark swing is NYT Connections (extended): 14.8% for MiniMax-M2 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.
Step 3.5 Flash accepts more context: 256K tokens versus 205K.

Side by side

MiniMax-M2 and Step 3.5 Flash specifications
	MiniMax-M2	Step 3.5 Flash
Provider	MiniMax	StepFun
Noometry Index	37.4	42.3
Released	2025-10-27	2026-01-29
Weights	Open	Open
Context window	205K	256K
Max output	131K	256K
Input $ / M tokens	$0.30	$0.10
Output $ / M tokens	$1.20	$0.30
Results tracked	21	19

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

Category by category

Coding Step 3.5 Flash leads

MiniMax-M2: 39.3 (#159), Step 3.5 Flash: 42.4 (#105)

Coding benchmarks
Benchmark	MiniMax-M2	Step 3.5 Flash
LMArena Coding	1370	1436
SWE-bench Verified (bash only)	61%	—
LMArena WebDev	1297	—

Agentic & Tool Use Not comparable

MiniMax-M2: 25.1 (#109), Step 3.5 Flash: —

Agentic & Tool Use benchmarks
Benchmark	MiniMax-M2	Step 3.5 Flash
Terminal-Bench	30%	—
Vending-Bench 2	160.6	—

Reasoning Step 3.5 Flash leads

MiniMax-M2: 19.4 (#258), Step 3.5 Flash: 22.2 (#202)

Reasoning benchmarks
Benchmark	MiniMax-M2	Step 3.5 Flash
NYT Connections (extended)	14.8%	28.4%
LMArena Hard Prompts	1357	1411
Kagi LLM Benchmark	57.8%	—

Math Step 3.5 Flash leads

MiniMax-M2: 37.3 (#160), Step 3.5 Flash: 42.6 (#84)

Math benchmarks
Benchmark	MiniMax-M2	Step 3.5 Flash
LMArena Math	1352	1408
MathArena Final-Answer Competitions	—	66.8%

Knowledge Step 3.5 Flash leads

MiniMax-M2: 37.0 (#163), Step 3.5 Flash: 39.6 (#132)

Knowledge benchmarks
Benchmark	MiniMax-M2	Step 3.5 Flash
LMArena Expert	1337	1421

Multilingual Step 3.5 Flash leads

MiniMax-M2: 45.3 (#171), Step 3.5 Flash: 50.5 (#119)

Multilingual benchmarks
Benchmark	MiniMax-M2	Step 3.5 Flash
LMArena Non-English	1313	1385
LMArena Chinese	1366	1447
LMArena French	1335	1421
LMArena German	1355	1405
LMArena Russian	1331	1385
LMArena Spanish	1326	1419
LMArena Japanese	—	1354
LMArena Korean	—	1352

Instruction Following Step 3.5 Flash leads

MiniMax-M2: 70.2 (#166), Step 3.5 Flash: 73.1 (#124)

Instruction Following benchmarks
Benchmark	MiniMax-M2	Step 3.5 Flash
LMArena Instruction Following	1328	1385

Long Context Step 3.5 Flash leads

MiniMax-M2: 40.5 (#153), Step 3.5 Flash: 42.8 (#117)

Long Context benchmarks
Benchmark	MiniMax-M2	Step 3.5 Flash
LMArena Longer Query	1331	1402

Writing & Preference Step 3.5 Flash leads

MiniMax-M2: 53.0 (#162), Step 3.5 Flash: 58.8 (#113)

Writing & Preference benchmarks
Benchmark	MiniMax-M2	Step 3.5 Flash
LMArena Text	1340	1403
LMArena Creative Writing	1286	1357
LMArena Multi-Turn	1361	1405

Frequently asked questions

Is MiniMax-M2 better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 37.4 on the Noometry Index.

Which is cheaper, MiniMax-M2 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 lists at $0.30 and $1.20.

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

Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 39.3 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 and Step 3.5 Flash share?

16 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Step 3.5 Flash has 19.