Noometry

Model comparison

Qwen3.5 122B-A10B vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 42.1 on the Noometry Index.

Last verified . 17 shared benchmarks.

Qwen3.5 122B-A10B Alibaba (Qwen)

42.1

Rank #119 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Qwen3.5 122B-A10B scores higher in 0 categories and Step 5 Preview in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 27.2.
  • The biggest single-benchmark swing is SciCode: 35.6% for Qwen3.5 122B-A10B and 58.9% for Step 5 Preview.
  • Qwen3.5 122B-A10B is cheaper at $0.40 / $3.20 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
  • Step 5 Preview accepts more context: 1.02M tokens versus 262K.
  • Qwen3.5 122B-A10B has downloadable open weights; the other is API-only.

Side by side

Qwen3.5 122B-A10BStep 5 Preview
ProviderAlibaba (Qwen)StepFun
Noometry Index42.147.9
Released2026-02-232026-09-16
WeightsOpenProprietary
Context window262K1.02M
Max output66K66K
Input $ / M tokens$0.40$1
Output $ / M tokens$3.20$2.70
Results tracked2718

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

Category by category

Coding Step 5 Preview leads

Qwen3.5 122B-A10B: 39.1 (#162), Step 5 Preview: 51.8 (#36)

BenchmarkQwen3.5 122B-A10BStep 5 Preview
LMArena WebDev13601564
SciCode35.6%58.9%
LMArena Coding14361480

Reasoning Step 5 Preview leads

Qwen3.5 122B-A10B: 27.2 (#123), Step 5 Preview: 40.0 (#57)

BenchmarkQwen3.5 122B-A10BStep 5 Preview
CritPt0.9%20.9%
LMArena Hard Prompts14211465
NYT Connections (extended)51.7%—
Thematic Generalization51.2%—
Mystery Game Puzzles17%—
DTBench84.3%—
LMCA32.2%—

Math Step 5 Preview leads

Qwen3.5 122B-A10B: 39.1 (#112), Step 5 Preview: 46.1 (#72)

BenchmarkQwen3.5 122B-A10BStep 5 Preview
LMArena Math14321470
ProofBench—42%

Knowledge Step 5 Preview leads

Qwen3.5 122B-A10B: 38.8 (#142), Step 5 Preview: 41.2 (#112)

BenchmarkQwen3.5 122B-A10BStep 5 Preview
LMArena Expert14321470
Vectara Hallucination Rate11.2%—

Multimodal Step 5 Preview leads

Qwen3.5 122B-A10B: 39.6 (#57), Step 5 Preview: 41.0 (#41)

BenchmarkQwen3.5 122B-A10BStep 5 Preview
LMArena Vision12451267

Multilingual Step 5 Preview leads

Qwen3.5 122B-A10B: 51.6 (#107), Step 5 Preview: 53.8 (#54)

BenchmarkQwen3.5 122B-A10BStep 5 Preview
LMArena Non-English14001432
LMArena Chinese14621519
LMArena Russian14001436
LMArena Spanish14241439
LMArena French1442—
LMArena German1426—
LMArena Japanese1367—
LMArena Korean1352—

Instruction Following Step 5 Preview leads

Qwen3.5 122B-A10B: 73.8 (#115), Step 5 Preview: 76.0 (#50)

BenchmarkQwen3.5 122B-A10BStep 5 Preview
LMArena Instruction Following13991444

Long Context Step 5 Preview leads

Qwen3.5 122B-A10B: 43.0 (#109), Step 5 Preview: 44.5 (#64)

BenchmarkQwen3.5 122B-A10BStep 5 Preview
LMArena Longer Query14101455

Writing & Preference Step 5 Preview leads

Qwen3.5 122B-A10B: 60.0 (#105), Step 5 Preview: 62.8 (#71)

BenchmarkQwen3.5 122B-A10BStep 5 Preview
LMArena Text14171442
LMArena Creative Writing13681410
LMArena Multi-Turn14161447

Frequently asked questions

Is Qwen3.5 122B-A10B better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 42.1 on the Noometry Index.

Which is cheaper, Qwen3.5 122B-A10B or Step 5 Preview?

Qwen3.5 122B-A10B is cheaper. It lists at $0.40 per million input tokens and $3.20 per million output tokens; Step 5 Preview lists at $1 and $2.70.

Is Qwen3.5 122B-A10B or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 39.1 in the Noometry coding category.

Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 262K.

How many benchmarks do Qwen3.5 122B-A10B and Step 5 Preview share?

17 benchmarks have published results for both models. Qwen3.5 122B-A10B has 27 scored results on Noometry and Step 5 Preview has 18.

Related comparisons

Go deeper