Model comparison

Qwen2.5 Plus 1127 vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 43.8 to 38.1 on the Noometry Index.

Last verified . 0 shared benchmarks.

Qwen2.5 Plus 1127 Alibaba (Qwen)

38.1

Rank #179 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

Qwen2.5 Plus 1127 and Step 5 Preview specifications
Qwen2.5 Plus 1127Step 5 Preview
ProviderAlibaba (Qwen)StepFun
Noometry Index38.143.8
Released—2026-09-16
WeightsProprietaryProprietary
Context window—1.02M
Max output—66K
Input $ / M tokens—$1
Output $ / M tokens—$2.70
Results tracked143

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

Category by category

Coding Step 5 Preview leads

Qwen2.5 Plus 1127: 37.9 (#171), Step 5 Preview: 50.6 (#40)

Coding benchmarks
BenchmarkQwen2.5 Plus 1127Step 5 Preview
LMArena WebDev—1569
SciCode—58.9%
LMArena Coding1314—

Reasoning Step 5 Preview leads

Qwen2.5 Plus 1127: 24.8 (#139), Step 5 Preview: 38.0 (#58)

Reasoning benchmarks
BenchmarkQwen2.5 Plus 1127Step 5 Preview
CritPt—20.9%
LMArena Hard Prompts1299—

Math Not comparable

Qwen2.5 Plus 1127: 33.5 (#175), Step 5 Preview: —

Math benchmarks
BenchmarkQwen2.5 Plus 1127Step 5 Preview
LMArena Math1298—

Knowledge Not comparable

Qwen2.5 Plus 1127: 34.9 (#179), Step 5 Preview: —

Knowledge benchmarks
BenchmarkQwen2.5 Plus 1127Step 5 Preview
LMArena Expert1289—

Multilingual Not comparable

Qwen2.5 Plus 1127: 42.1 (#196), Step 5 Preview: —

Multilingual benchmarks
BenchmarkQwen2.5 Plus 1127Step 5 Preview
LMArena Non-English1265—
LMArena Chinese1314—
LMArena German1231—
LMArena Japanese1207—
LMArena Russian1271—

Instruction Following Not comparable

Qwen2.5 Plus 1127: 67.4 (#194), Step 5 Preview: —

Instruction Following benchmarks
BenchmarkQwen2.5 Plus 1127Step 5 Preview
LMArena Instruction Following1275—

Long Context Not comparable

Qwen2.5 Plus 1127: 39.2 (#180), Step 5 Preview: —

Long Context benchmarks
BenchmarkQwen2.5 Plus 1127Step 5 Preview
LMArena Longer Query1292—

Writing & Preference Not comparable

Qwen2.5 Plus 1127: 49.5 (#186), Step 5 Preview: —

Writing & Preference benchmarks
BenchmarkQwen2.5 Plus 1127Step 5 Preview
LMArena Text1299—
LMArena Creative Writing1262—
LMArena Multi-Turn1299—

Frequently asked questions

Is Qwen2.5 Plus 1127 better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 43.8 to 38.1 on the Noometry Index.

Is Qwen2.5 Plus 1127 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 Qwen2.5 Plus 1127 and Step 5 Preview share?

0 benchmarks have published results for both models. Qwen2.5 Plus 1127 has 14 scored results on Noometry and Step 5 Preview has 3.

Related comparisons

Go deeper