Model comparison

MiMo-V2.5 vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 43.4 on the Noometry Index. MiMo-V2.5 costs 8.1× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Last verified October 11, 2026. 18 shared benchmarks.

MiMo-V2.5 Xiaomi

43.4

Rank #93 Confirmed

Step 5 Preview

StepFun

47.9

Rank #58 Confirmed

Summary

They share 18 benchmarks with published results for both. MiMo-V2.5 scores higher in 0 categories and Step 5 Preview in 9 categories; 6 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 28.6.
The biggest single-benchmark swing is ProofBench: 16% for MiMo-V2.5 and 42% for Step 5 Preview.
MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
MiMo-V2.5 accepts more context: 1.05M tokens versus 1.02M.
MiMo-V2.5 has downloadable open weights; the other is API-only.

Side by side

MiMo-V2.5 and Step 5 Preview specifications
	MiMo-V2.5	Step 5 Preview
Provider	Xiaomi	StepFun
Noometry Index	43.4	47.9
Released	2026-04-22	2026-09-16
Weights	Open	Proprietary
Context window	1.05M	1.02M
Max output	131K	66K
Input $ / M tokens	$0.14	$1
Output $ / M tokens	$0.28	$2.70
Results tracked	23	18

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

Category by category

Coding Step 5 Preview leads

MiMo-V2.5: 43.9 (#81), Step 5 Preview: 51.8 (#36)

Coding benchmarks
Benchmark	MiMo-V2.5	Step 5 Preview
LMArena WebDev	1438	1564
SciCode	43.1%	58.9%
LMArena Coding	1469	1480
ALE-Bench	513.95	—

Reasoning Step 5 Preview leads

MiMo-V2.5: 28.6 (#101), Step 5 Preview: 40.0 (#57)

Reasoning benchmarks
Benchmark	MiMo-V2.5	Step 5 Preview
CritPt	3.7%	20.9%
LMArena Hard Prompts	1450	1465

Math Step 5 Preview leads

MiMo-V2.5: 36.8 (#163), Step 5 Preview: 46.1 (#72)

Math benchmarks
Benchmark	MiMo-V2.5	Step 5 Preview
ProofBench	16%	42%
LMArena Math	1436	1470

Knowledge Too close to call

MiMo-V2.5: 40.8 (#115), Step 5 Preview: 41.2 (#112)

Knowledge benchmarks
Benchmark	MiMo-V2.5	Step 5 Preview
LMArena Expert	1460	1470

Multimodal Step 5 Preview leads

MiMo-V2.5: 39.8 (#54), Step 5 Preview: 41.0 (#41)

Multimodal benchmarks
Benchmark	MiMo-V2.5	Step 5 Preview
LMArena Vision	1247	1267

Multilingual Step 5 Preview leads

MiMo-V2.5: 51.9 (#99), Step 5 Preview: 53.8 (#54)

Multilingual benchmarks
Benchmark	MiMo-V2.5	Step 5 Preview
LMArena Non-English	1404	1432
LMArena Chinese	1468	1519
LMArena Russian	1395	1436
LMArena Spanish	1416	1439
LMArena French	1447	—
LMArena German	1421	—
LMArena Japanese	1306	—
LMArena Korean	1363	—

Instruction Following Too close to call

MiMo-V2.5: 75.5 (#60), Step 5 Preview: 76.0 (#50)

Instruction Following benchmarks
Benchmark	MiMo-V2.5	Step 5 Preview
LMArena Instruction Following	1434	1444

Long Context Too close to call

MiMo-V2.5: 44.2 (#73), Step 5 Preview: 44.5 (#64)

Long Context benchmarks
Benchmark	MiMo-V2.5	Step 5 Preview
LMArena Longer Query	1445	1455

Writing & Preference Step 5 Preview leads

MiMo-V2.5: 61.6 (#86), Step 5 Preview: 62.8 (#71)

Writing & Preference benchmarks
Benchmark	MiMo-V2.5	Step 5 Preview
LMArena Text	1428	1442
LMArena Creative Writing	1393	1410
LMArena Multi-Turn	1445	1447

Frequently asked questions

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

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

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Step 5 Preview lists at $1 and $2.70.

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

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 43.9 in the Noometry coding category.

Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 1.02M.

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

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