Model comparison

Step 3.7 Flash vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 37.3 on the Noometry Index. Step 3.7 Flash costs 3.4× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Last verified October 10, 2026. 2 shared benchmarks.

Step 3.7 Flash

StepFun

37.3

Rank #207 Reported

Step 5 Preview

StepFun

47.9

Rank #58 Confirmed

Summary

They share 2 benchmarks with published results for both. Step 3.7 Flash scores higher in 0 categories and Step 5 Preview in 3 categories; 3 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 21.6.
The biggest single-benchmark swing is SciCode: 40% for Step 3.7 Flash and 58.9% for Step 5 Preview.
Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
Step 5 Preview accepts more context: 1.02M tokens versus 256K.
Step 3.7 Flash has downloadable open weights; the other is API-only.

Side by side

Step 3.7 Flash and Step 5 Preview specifications
	Step 3.7 Flash	Step 5 Preview
Provider	StepFun	StepFun
Noometry Index	37.3	47.9
Released	2026-05-29	2026-09-16
Weights	Open	Proprietary
Context window	256K	1.02M
Max output	256K	66K
Input $ / M tokens	$0.18	$1
Output $ / M tokens	$1.11	$2.70
Results tracked	5	18

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

Category by category

Coding Step 5 Preview leads

Step 3.7 Flash: 40.0 (#150), Step 5 Preview: 51.8 (#36)

Coding benchmarks
Benchmark	Step 3.7 Flash	Step 5 Preview
SciCode	40%	58.9%
LMArena WebDev	—	1564
LMArena Coding	—	1480
ALE-Bench	694.12	—

Reasoning Step 5 Preview leads

Step 3.7 Flash: 21.6 (#219), Step 5 Preview: 40.0 (#57)

Reasoning benchmarks
Benchmark	Step 3.7 Flash	Step 5 Preview
CritPt	2.3%	20.9%
NYT Connections (extended)	39.7%	—
LMArena Hard Prompts	—	1465

Math Step 5 Preview leads

Step 3.7 Flash: 42.9 (#82), Step 5 Preview: 46.1 (#72)

Math benchmarks
Benchmark	Step 3.7 Flash	Step 5 Preview
MathArena Final-Answer Competitions	68.5%	—
ProofBench	—	42%
LMArena Math	—	1470

Knowledge Not comparable

Step 3.7 Flash: —, Step 5 Preview: 41.2 (#112)

Knowledge benchmarks
Benchmark	Step 3.7 Flash	Step 5 Preview
LMArena Expert	—	1470

Multimodal Not comparable

Step 3.7 Flash: —, Step 5 Preview: 41.0 (#41)

Multimodal benchmarks
Benchmark	Step 3.7 Flash	Step 5 Preview
LMArena Vision	—	1267

Multilingual Not comparable

Step 3.7 Flash: —, Step 5 Preview: 53.8 (#54)

Multilingual benchmarks
Benchmark	Step 3.7 Flash	Step 5 Preview
LMArena Non-English	—	1432
LMArena Chinese	—	1519
LMArena Russian	—	1436
LMArena Spanish	—	1439

Instruction Following Not comparable

Step 3.7 Flash: —, Step 5 Preview: 76.0 (#50)

Instruction Following benchmarks
Benchmark	Step 3.7 Flash	Step 5 Preview
LMArena Instruction Following	—	1444

Long Context Not comparable

Step 3.7 Flash: —, Step 5 Preview: 44.5 (#64)

Long Context benchmarks
Benchmark	Step 3.7 Flash	Step 5 Preview
LMArena Longer Query	—	1455

Writing & Preference Not comparable

Step 3.7 Flash: —, Step 5 Preview: 62.8 (#71)

Writing & Preference benchmarks
Benchmark	Step 3.7 Flash	Step 5 Preview
LMArena Text	—	1442
LMArena Creative Writing	—	1410
LMArena Multi-Turn	—	1447

Frequently asked questions

Is Step 3.7 Flash better than Step 5 Preview?

Which is cheaper, Step 3.7 Flash or Step 5 Preview?

Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; Step 5 Preview lists at $1 and $2.70.

Is Step 3.7 Flash or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 40.0 in the Noometry coding category.

Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 256K.

How many benchmarks do Step 3.7 Flash and Step 5 Preview share?

2 benchmarks have published results for both models. Step 3.7 Flash has 5 scored results on Noometry and Step 5 Preview has 18.