Model comparison

Qwen3.7 Flash vs Step 3.5 Flash

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 39.9 on the Noometry Index. Qwen3.7 Flash costs 2.7× less per token, which makes it the better buy when Step 3.5 Flash's lead doesn't matter for your workload.

Last verified October 11, 2026. 1 shared benchmarks.

Qwen3.7 Flash

Alibaba (Qwen)

39.9

Rank #156 Confirmed

Step 3.5 Flash

StepFun

42.3

Rank #116 Confirmed

Summary

They share 1 benchmark with published results for both. Qwen3.7 Flash scores higher in 2 categories and Step 3.5 Flash in 1 category; 3 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Qwen3.7 Flash leads 48.9 to 39.6.
The biggest single-benchmark swing is NYT Connections (extended): 43.8% for Qwen3.7 Flash and 28.4% for Step 3.5 Flash.
Qwen3.7 Flash is cheaper at $0.03 / $0.13 per million input/output tokens, against $0.10 / $0.30 for Step 3.5 Flash.
Qwen3.7 Flash accepts more context: 1M tokens versus 256K.
Step 3.5 Flash has downloadable open weights; the other is API-only.

Side by side

Qwen3.7 Flash and Step 3.5 Flash specifications
	Qwen3.7 Flash	Step 3.5 Flash
Provider	Alibaba (Qwen)	StepFun
Noometry Index	39.9	42.3
Released	2026-07-15	2026-01-29
Weights	Proprietary	Open
Context window	1M	256K
Max output	131K	256K
Input $ / M tokens	$0.03	$0.10
Output $ / M tokens	$0.13	$0.30
Results tracked	7	19

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

Category by category

Coding Not comparable

Qwen3.7 Flash: —, Step 3.5 Flash: 42.4 (#105)

Coding benchmarks
Benchmark	Qwen3.7 Flash	Step 3.5 Flash
LMArena Coding	—	1436

Reasoning Qwen3.7 Flash leads

Qwen3.7 Flash: 28.2 (#108), Step 3.5 Flash: 22.2 (#202)

Reasoning benchmarks
Benchmark	Qwen3.7 Flash	Step 3.5 Flash
NYT Connections (extended)	43.8%	28.4%
Chess Puzzles	23%	—
LMArena Hard Prompts	—	1411
Mystery Game Puzzles	15%	—
Epoch Capabilities Index	144.64	—

Math Step 3.5 Flash leads

Qwen3.7 Flash: 38.3 (#140), Step 3.5 Flash: 42.6 (#84)

Math benchmarks
Benchmark	Qwen3.7 Flash	Step 3.5 Flash
FrontierMath (Tiers 1-3)	19.3%	—
MathArena Final-Answer Competitions	—	66.8%
OTIS Mock AIME 2024-2025	86.7%	—
LMArena Math	—	1408

Knowledge Qwen3.7 Flash leads

Qwen3.7 Flash: 48.9 (#75), Step 3.5 Flash: 39.6 (#132)

Knowledge benchmarks
Benchmark	Qwen3.7 Flash	Step 3.5 Flash
GPQA Diamond	82.3%	—
LMArena Expert	—	1421

Multilingual Not comparable

Qwen3.7 Flash: —, Step 3.5 Flash: 50.5 (#119)

Multilingual benchmarks
Benchmark	Qwen3.7 Flash	Step 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

Qwen3.7 Flash: —, Step 3.5 Flash: 73.1 (#124)

Instruction Following benchmarks
Benchmark	Qwen3.7 Flash	Step 3.5 Flash
LMArena Instruction Following	—	1385

Long Context Not comparable

Qwen3.7 Flash: —, Step 3.5 Flash: 42.8 (#117)

Long Context benchmarks
Benchmark	Qwen3.7 Flash	Step 3.5 Flash
LMArena Longer Query	—	1402

Writing & Preference Not comparable

Qwen3.7 Flash: —, Step 3.5 Flash: 58.8 (#113)

Writing & Preference benchmarks
Benchmark	Qwen3.7 Flash	Step 3.5 Flash
LMArena Text	—	1403
LMArena Creative Writing	—	1357
LMArena Multi-Turn	—	1405

Frequently asked questions

Is Qwen3.7 Flash better than Step 3.5 Flash?

Which is cheaper, Qwen3.7 Flash or Step 3.5 Flash?

Qwen3.7 Flash is cheaper. It lists at $0.03 per million input tokens and $0.13 per million output tokens; Step 3.5 Flash lists at $0.10 and $0.30.

Which has the bigger context window?

Qwen3.7 Flash does, with 1M tokens against 256K.

How many benchmarks do Qwen3.7 Flash and Step 3.5 Flash share?

1 benchmark has published results for both models. Qwen3.7 Flash has 7 scored results on Noometry and Step 3.5 Flash has 19.