Model comparison

Step 2 16k Exp 202412 vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 43.8 to 38.6 on the Noometry Index.

Last verified . 0 shared benchmarks.

Step 2 16k Exp 202412 StepFun

38.6

Rank #173 Confirmed

Step 5 Preview StepFun

43.8

Rank #78 Reported

Summary

  • The widest gap is in reasoning, where Step 5 Preview leads 38.0 to 24.8.

Side by side

Step 2 16k Exp 202412 and Step 5 Preview specifications
Step 2 16k Exp 202412Step 5 Preview
ProviderStepFunStepFun
Noometry Index38.643.8
Released—2026-09-16
WeightsProprietaryProprietary
Context window—1.02M
Max output—66K
Input $ / M tokens—$1
Output $ / M tokens—$2.70
Results tracked123

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

Category by category

Coding Step 5 Preview leads

Step 2 16k Exp 202412: 37.9 (#170), Step 5 Preview: 50.6 (#40)

Coding benchmarks
BenchmarkStep 2 16k Exp 202412Step 5 Preview
LMArena WebDev—1569
SciCode—58.9%
LMArena Coding1316—

Reasoning Step 5 Preview leads

Step 2 16k Exp 202412: 24.8 (#140), Step 5 Preview: 38.0 (#58)

Reasoning benchmarks
BenchmarkStep 2 16k Exp 202412Step 5 Preview
CritPt—20.9%
LMArena Hard Prompts1299—

Math Not comparable

Step 2 16k Exp 202412: 33.6 (#171), Step 5 Preview: —

Math benchmarks
BenchmarkStep 2 16k Exp 202412Step 5 Preview
LMArena Math1305—

Knowledge Not comparable

Step 2 16k Exp 202412: 34.6 (#187), Step 5 Preview: —

Knowledge benchmarks
BenchmarkStep 2 16k Exp 202412Step 5 Preview
LMArena Expert1279—

Multilingual Not comparable

Step 2 16k Exp 202412: 43.9 (#176), Step 5 Preview: —

Multilingual benchmarks
BenchmarkStep 2 16k Exp 202412Step 5 Preview
LMArena Non-English1290—
LMArena Chinese1331—
LMArena Russian1324—

Instruction Following Not comparable

Step 2 16k Exp 202412: 68.1 (#187), Step 5 Preview: —

Instruction Following benchmarks
BenchmarkStep 2 16k Exp 202412Step 5 Preview
LMArena Instruction Following1287—

Long Context Not comparable

Step 2 16k Exp 202412: 39.7 (#165), Step 5 Preview: —

Long Context benchmarks
BenchmarkStep 2 16k Exp 202412Step 5 Preview
LMArena Longer Query1307—

Writing & Preference Not comparable

Step 2 16k Exp 202412: 52.5 (#168), Step 5 Preview: —

Writing & Preference benchmarks
BenchmarkStep 2 16k Exp 202412Step 5 Preview
LMArena Text1321—
LMArena Creative Writing1328—
LMArena Multi-Turn1292—

Frequently asked questions

Is Step 2 16k Exp 202412 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 43.8 to 38.6 on the Noometry Index.

Is Step 2 16k Exp 202412 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 50.6 versus 37.9 in the Noometry coding category.

How many benchmarks do Step 2 16k Exp 202412 and Step 5 Preview share?

0 benchmarks have published results for both models. Step 2 16k Exp 202412 has 12 scored results on Noometry and Step 5 Preview has 3.

Related comparisons

Go deeper