Model comparison

Qwen3.5-9B vs Step 3.5 Flash

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 33.3 on the Noometry Index.

Last verified . 1 shared benchmarks.

Qwen3.5-9B Alibaba (Qwen)

33.3

Rank #235 Confirmed

Step 3.5 Flash StepFun

41.7

Rank #116 Confirmed

Summary

  • They share 1 benchmark with published results for both. Qwen3.5-9B scores higher in 2 categories and Step 3.5 Flash in 2 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where Step 3.5 Flash leads 40.6 to 33.5.
  • The biggest single-benchmark swing is MathArena Final-Answer Competitions: 48.5% for Qwen3.5-9B and 66.8% for Step 3.5 Flash.
  • Qwen3.5-9B is cheaper at $0.10 / $0.15 per million input/output tokens, against $0.10 / $0.30 for Step 3.5 Flash.
  • Qwen3.5-9B accepts more context: 262K tokens versus 256K.

Side by side

Qwen3.5-9B and Step 3.5 Flash specifications
Qwen3.5-9BStep 3.5 Flash
ProviderAlibaba (Qwen)StepFun
Noometry Index33.341.7
Released2026-02-232026-01-29
WeightsOpenOpen
Context window262K256K
Max output66K256K
Input $ / M tokens$0.10$0.10
Output $ / M tokens$0.15$0.30
Results tracked1019

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

Category by category

Coding Step 3.5 Flash leads

Qwen3.5-9B: 35.3 (#213), Step 3.5 Flash: 41.7 (#106)

Coding benchmarks
BenchmarkQwen3.5-9BStep 3.5 Flash
SciCode27.5%—
LMArena Coding—1436

Agentic & Tool Use Not comparable

Qwen3.5-9B: 14.4 (#143), Step 3.5 Flash: —

Agentic & Tool Use benchmarks
BenchmarkQwen3.5-9BStep 3.5 Flash
Terminal-Bench9.2%—

Reasoning Qwen3.5-9B leads

Qwen3.5-9B: 22.5 (#178), Step 3.5 Flash: 21.2 (#202)

Reasoning benchmarks
BenchmarkQwen3.5-9BStep 3.5 Flash
NYT Connections (extended)—28.4%
CritPt0.3%—
Chess Puzzles12%—
LMArena Hard Prompts—1411
DTBench71.2%—
LMCA24.5%—
Epoch Capabilities Index139.45—

Math Step 3.5 Flash leads

Qwen3.5-9B: 33.5 (#174), Step 3.5 Flash: 40.6 (#77)

Math benchmarks
BenchmarkQwen3.5-9BStep 3.5 Flash
MathArena Final-Answer Competitions48.5%66.8%
OTIS Mock AIME 2024-202561.7%—
LMArena Math—1408

Knowledge Qwen3.5-9B leads

Qwen3.5-9B: 46.0 (#77), Step 3.5 Flash: 39.0 (#127)

Knowledge benchmarks
BenchmarkQwen3.5-9BStep 3.5 Flash
GPQA Diamond79%—
LMArena Expert—1422

Multilingual Not comparable

Qwen3.5-9B: —, Step 3.5 Flash: 50.7 (#115)

Multilingual benchmarks
BenchmarkQwen3.5-9BStep 3.5 Flash
LMArena Non-English—1386
LMArena Chinese—1448
LMArena French—1421
LMArena German—1404
LMArena Japanese—1353
LMArena Korean—1350
LMArena Russian—1385
LMArena Spanish—1419

Instruction Following Not comparable

Qwen3.5-9B: —, Step 3.5 Flash: 73.3 (#119)

Instruction Following benchmarks
BenchmarkQwen3.5-9BStep 3.5 Flash
LMArena Instruction Following—1385

Long Context Not comparable

Qwen3.5-9B: —, Step 3.5 Flash: 42.8 (#112)

Long Context benchmarks
BenchmarkQwen3.5-9BStep 3.5 Flash
LMArena Longer Query—1402

Writing & Preference Not comparable

Qwen3.5-9B: —, Step 3.5 Flash: 59.0 (#108)

Writing & Preference benchmarks
BenchmarkQwen3.5-9BStep 3.5 Flash
LMArena Text—1403
LMArena Creative Writing—1357
LMArena Multi-Turn—1405

Frequently asked questions

Is Qwen3.5-9B better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 33.3 on the Noometry Index.

Which is cheaper, Qwen3.5-9B or Step 3.5 Flash?

Qwen3.5-9B is cheaper. It lists at $0.10 per million input tokens and $0.15 per million output tokens; Step 3.5 Flash lists at $0.10 and $0.30.

Is Qwen3.5-9B or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 35.3 in the Noometry coding category.

Which has the bigger context window?

Qwen3.5-9B does, with 262K tokens against 256K.

How many benchmarks do Qwen3.5-9B and Step 3.5 Flash share?

1 benchmark has published results for both models. Qwen3.5-9B has 10 scored results on Noometry and Step 3.5 Flash has 19.

Related comparisons

Go deeper