Noometry

Model comparison

Qwen3.5 Plus vs Step 3.5 Flash

Qwen3.5 Plus and Step 3.5 Flash score almost the same on the Noometry Index (42.9 vs 42.3), so choose on price, context window or the category you care about most.

Last verified . 0 shared benchmarks.

Qwen3.5 Plus Alibaba (Qwen)

42.9

Rank #106 Confirmed

Step 3.5 Flash StepFun

42.3

Rank #116 Confirmed

Summary

  • The widest gap is in reasoning, where Qwen3.5 Plus leads 32.8 to 22.2.
  • Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.40 / $2.40 for Qwen3.5 Plus.
  • Qwen3.5 Plus accepts more context: 1M tokens versus 256K.
  • Step 3.5 Flash has downloadable open weights; the other is API-only.

Side by side

Qwen3.5 PlusStep 3.5 Flash
ProviderAlibaba (Qwen)StepFun
Noometry Index42.942.3
Released2026-02-162026-01-29
WeightsProprietaryOpen
Context window1M256K
Max output66K256K
Input $ / M tokens$0.40$0.10
Output $ / M tokens$2.40$0.30
Results tracked1519

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

Category by category

Coding Not comparable

Qwen3.5 Plus: —, Step 3.5 Flash: 42.4 (#105)

BenchmarkQwen3.5 PlusStep 3.5 Flash
LMArena Coding—1436
ALE-Bench621.92—

Agentic & Tool Use Not comparable

Qwen3.5 Plus: —, Step 3.5 Flash: —

BenchmarkQwen3.5 PlusStep 3.5 Flash
Vending-Bench 20.54—

Reasoning Qwen3.5 Plus leads

Qwen3.5 Plus: 32.8 (#74), Step 3.5 Flash: 22.2 (#202)

BenchmarkQwen3.5 PlusStep 3.5 Flash
NYT Connections (extended)—28.4%
Chess Puzzles22%—
LMArena Hard Prompts—1411
Mystery Game Puzzles17%—
DTBench80.5%—
LMCA36.4%—
Epoch Capabilities Index146.78—

Math Qwen3.5 Plus leads

Qwen3.5 Plus: 49.6 (#61), Step 3.5 Flash: 42.6 (#84)

BenchmarkQwen3.5 PlusStep 3.5 Flash
MathArena Final-Answer Competitions—66.8%
OTIS Mock AIME 2024-202586.7%—
LMArena Math—1408
FrontierMath (Feb 2025 set)21%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Qwen3.5 Plus leads

Qwen3.5 Plus: 46.0 (#83), Step 3.5 Flash: 39.6 (#132)

BenchmarkQwen3.5 PlusStep 3.5 Flash
GPQA Diamond84.8%—
SimpleQA Verified25.4%—
Vectara Hallucination Rate10.7%—
LMArena Expert—1421

Multilingual Not comparable

Qwen3.5 Plus: —, Step 3.5 Flash: 50.5 (#119)

BenchmarkQwen3.5 PlusStep 3.5 Flash
LMArena Non-English—1385
LMArena Chinese—1447
LMArena French—1421
LMArena German—1405
LMArena Japanese—1354
LMArena Korean—1352
LMArena Russian—1385
LMArena Spanish—1419

Instruction Following Not comparable

Qwen3.5 Plus: —, Step 3.5 Flash: 73.1 (#124)

BenchmarkQwen3.5 PlusStep 3.5 Flash
LMArena Instruction Following—1385

Long Context Too close to call

Qwen3.5 Plus: 43.0 (#113), Step 3.5 Flash: 42.8 (#117)

BenchmarkQwen3.5 PlusStep 3.5 Flash
CL-bench19.8%—
CL-bench Life12.4%—
LMArena Longer Query—1402

Writing & Preference Not comparable

Qwen3.5 Plus: —, Step 3.5 Flash: 58.8 (#113)

BenchmarkQwen3.5 PlusStep 3.5 Flash
LMArena Text—1403
LMArena Creative Writing—1357
LMArena Multi-Turn—1405

Frequently asked questions

Is Qwen3.5 Plus better than Step 3.5 Flash?

Qwen3.5 Plus and Step 3.5 Flash score almost the same on the Noometry Index (42.9 vs 42.3), so choose on price, context window or the category you care about most.

Which is cheaper, Qwen3.5 Plus or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen3.5 Plus lists at $0.40 and $2.40.

Which has the bigger context window?

Qwen3.5 Plus does, with 1M tokens against 256K.

How many benchmarks do Qwen3.5 Plus and Step 3.5 Flash share?

0 benchmarks have published results for both models. Qwen3.5 Plus has 15 scored results on Noometry and Step 3.5 Flash has 19.

Related comparisons

Go deeper