Noometry

Model comparison

Qwen3.6 Plus vs Step 5 Preview

Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 43.8 on the Noometry Index.

Last verified . 3 shared benchmarks.

Qwen3.6 Plus Alibaba (Qwen)

47.3

Rank #54 Confirmed

Step 5 Preview StepFun

43.8

Rank #78 Reported

Summary

  • They share 3 benchmarks with published results for both. Qwen3.6 Plus scores higher in 0 categories and Step 5 Preview in 2 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Step 5 Preview leads 50.6 to 40.6.
  • The biggest single-benchmark swing is SciCode: 40.7% for Qwen3.6 Plus and 58.9% for Step 5 Preview.
  • Qwen3.6 Plus is cheaper at $0.50 / $3 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
  • Step 5 Preview accepts more context: 1.02M tokens versus 1M.

Side by side

Qwen3.6 PlusStep 5 Preview
ProviderAlibaba (Qwen)StepFun
Noometry Index47.343.8
Released2026-03-312026-09-16
WeightsProprietaryProprietary
Context window1M1.02M
Max output66K66K
Input $ / M tokens$0.50$1
Output $ / M tokens$3$2.70
Results tracked373

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

Category by category

Coding Step 5 Preview leads

Qwen3.6 Plus: 40.6 (#125), Step 5 Preview: 50.6 (#40)

BenchmarkQwen3.6 PlusStep 5 Preview
LMArena WebDev14611569
SciCode40.7%58.9%
SWE-bench Verified57.9%—
LMArena Coding1467—
ALE-Bench670.15—

Agentic & Tool Use Not comparable

Qwen3.6 Plus: —, Step 5 Preview: —

BenchmarkQwen3.6 PlusStep 5 Preview
Vending-Bench 25,115—

Reasoning Step 5 Preview leads

Qwen3.6 Plus: 28.5 (#89), Step 5 Preview: 38.0 (#58)

BenchmarkQwen3.6 PlusStep 5 Preview
CritPt2.9%20.9%
NYT Connections (extended)60.3%—
Chess Puzzles17%—
Thematic Generalization59.5%—
LMArena Hard Prompts1449—
Mystery Game Puzzles12%—
DTBench81.9%—
LMCA33.1%—
Epoch Capabilities Index147.67—

Math Not comparable

Qwen3.6 Plus: 50.6 (#44), Step 5 Preview: —

BenchmarkQwen3.6 PlusStep 5 Preview
FrontierMath (Tiers 1-3)38.2%—
OTIS Mock AIME 2024-202593.3%—
LMArena Math1450—
FrontierMath (Feb 2025 set)26.2%—
FrontierMath Tier 4 (v1)8.3%—

Knowledge Not comparable

Qwen3.6 Plus: 56.1 (#40), Step 5 Preview: —

BenchmarkQwen3.6 PlusStep 5 Preview
GPQA Diamond88.4%—
SimpleQA Verified44.1%—
LMArena Expert1456—

Multilingual Not comparable

Qwen3.6 Plus: 53.5 (#66), Step 5 Preview: —

BenchmarkQwen3.6 PlusStep 5 Preview
LMArena Non-English1424—
LMArena Chinese1478—
LMArena French1454—
LMArena German1451—
LMArena Japanese1389—
LMArena Korean1381—
LMArena Russian1434—
LMArena Spanish1432—

Instruction Following Not comparable

Qwen3.6 Plus: 75.2 (#70), Step 5 Preview: —

BenchmarkQwen3.6 PlusStep 5 Preview
LMArena Instruction Following1425—

Long Context Not comparable

Qwen3.6 Plus: 45.1 (#48), Step 5 Preview: —

BenchmarkQwen3.6 PlusStep 5 Preview
CL-bench20.3%—
LMArena Longer Query1440—

Writing & Preference Not comparable

Qwen3.6 Plus: 62.4 (#78), Step 5 Preview: —

BenchmarkQwen3.6 PlusStep 5 Preview
LMArena Text1437—
LMArena Creative Writing1405—
LMArena Multi-Turn1438—

Frequently asked questions

Is Qwen3.6 Plus better than Step 5 Preview?

Qwen3.6 Plus is the stronger model overall, scoring 47.3 to 43.8 on the Noometry Index.

Which is cheaper, Qwen3.6 Plus or Step 5 Preview?

Qwen3.6 Plus is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Step 5 Preview lists at $1 and $2.70.

Is Qwen3.6 Plus or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 50.6 versus 40.6 in the Noometry coding category.

Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 1M.

How many benchmarks do Qwen3.6 Plus and Step 5 Preview share?

3 benchmarks have published results for both models. Qwen3.6 Plus has 37 scored results on Noometry and Step 5 Preview has 3.

Related comparisons

Go deeper