Noometry

Model comparison

Step 3.5 Flash vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 42.3 on the Noometry Index. Step 3.5 Flash costs 9.5× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Last verified . 13 shared benchmarks.

Step 3.5 Flash StepFun

42.3

Rank #116 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Step 3.5 Flash scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 22.2.
  • Step 3.5 Flash is cheaper at $0.10 / $0.30 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 3.5 Flash has downloadable open weights; the other is API-only.

Side by side

Step 3.5 FlashStep 5 Preview
ProviderStepFunStepFun
Noometry Index42.347.9
Released2026-01-292026-09-16
WeightsOpenProprietary
Context window256K1.02M
Max output256K66K
Input $ / M tokens$0.10$1
Output $ / M tokens$0.30$2.70
Results tracked1918

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

Category by category

Coding Step 5 Preview leads

Step 3.5 Flash: 42.4 (#105), Step 5 Preview: 51.8 (#36)

BenchmarkStep 3.5 FlashStep 5 Preview
LMArena Coding14361480
LMArena WebDev—1564
SciCode—58.9%

Reasoning Step 5 Preview leads

Step 3.5 Flash: 22.2 (#202), Step 5 Preview: 40.0 (#57)

BenchmarkStep 3.5 FlashStep 5 Preview
LMArena Hard Prompts14111465
NYT Connections (extended)28.4%—
CritPt—20.9%

Math Step 5 Preview leads

Step 3.5 Flash: 42.6 (#84), Step 5 Preview: 46.1 (#72)

BenchmarkStep 3.5 FlashStep 5 Preview
LMArena Math14081470
MathArena Final-Answer Competitions66.8%—
ProofBench—42%

Knowledge Step 5 Preview leads

Step 3.5 Flash: 39.6 (#132), Step 5 Preview: 41.2 (#112)

BenchmarkStep 3.5 FlashStep 5 Preview
LMArena Expert14211470

Multimodal Not comparable

Step 3.5 Flash: —, Step 5 Preview: 41.0 (#41)

BenchmarkStep 3.5 FlashStep 5 Preview
LMArena Vision—1267

Multilingual Step 5 Preview leads

Step 3.5 Flash: 50.5 (#119), Step 5 Preview: 53.8 (#54)

BenchmarkStep 3.5 FlashStep 5 Preview
LMArena Non-English13851432
LMArena Chinese14471519
LMArena Russian13851436
LMArena Spanish14191439
LMArena French1421—
LMArena German1405—
LMArena Japanese1354—
LMArena Korean1352—

Instruction Following Step 5 Preview leads

Step 3.5 Flash: 73.1 (#124), Step 5 Preview: 76.0 (#50)

BenchmarkStep 3.5 FlashStep 5 Preview
LMArena Instruction Following13851444

Long Context Step 5 Preview leads

Step 3.5 Flash: 42.8 (#117), Step 5 Preview: 44.5 (#64)

BenchmarkStep 3.5 FlashStep 5 Preview
LMArena Longer Query14021455

Writing & Preference Step 5 Preview leads

Step 3.5 Flash: 58.8 (#113), Step 5 Preview: 62.8 (#71)

BenchmarkStep 3.5 FlashStep 5 Preview
LMArena Text14031442
LMArena Creative Writing13571410
LMArena Multi-Turn14051447

Frequently asked questions

Is Step 3.5 Flash better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 42.3 on the Noometry Index. Step 3.5 Flash costs 9.5× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

Which is cheaper, Step 3.5 Flash or Step 5 Preview?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Step 5 Preview lists at $1 and $2.70.

Is Step 3.5 Flash or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 42.4 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 3.5 Flash and Step 5 Preview share?

13 benchmarks have published results for both models. Step 3.5 Flash has 19 scored results on Noometry and Step 5 Preview has 18.

Related comparisons

Go deeper