Model A

Alibaba

71.79/100

Supported · Public rank #18

90% interval 64.5–79.1

Qwen3.7 Max vs Step 3.7 Flash

Updated August 30, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B

Step 3.7 Flash

StepFun

51.05/100

Estimated · Public rank #126

90% interval 39.5–62.6

Decision reading

Qwen3.7 Max has the higher public score, 71.79 versus 51.05, and the 90% score intervals do not overlap.

6 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

Long documents
Prompts that approach the documented context limit
Qwen3.7 Max
Qwen3.7 Max has the larger documented context window.
Confidence: documented

Show secondary and unsupported calls

Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: rate-fallback
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

30 Qwen3.7 Max only

6 Shared

5 Step 3.7 Flash only

Shared results: 6
Qwen3.7 Max only: 30
Step 3.7 Flash only: 5
Like-for-like categories: 0 / 8

2 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.

Agentic

Directional only

Qwen3.7 Max: 69.7
Step 3.7 Flash: 66.4
Weighted basis: 1 vs 2 rows
Reading: Directional only

Coding

Directional only

Qwen3.7 Max: 77.9
Step 3.7 Flash: 56.3
Weighted basis: 4 vs 1 rows
Reading: Directional only

Reasoning

Not comparable

Qwen3.7 Max: 90.4
Step 3.7 Flash: Not measured
Weighted basis: 1 vs 0 rows
Reading: Not comparable

Knowledge

Not comparable

Qwen3.7 Max: 64.2
Step 3.7 Flash: Not measured
Weighted basis: 4 vs 0 rows
Reading: Not comparable

Math

Not comparable

Qwen3.7 Max: 97.1
Step 3.7 Flash: Not measured
Weighted basis: 1 vs 0 rows
Reading: Not comparable

Multilingual

Not comparable

Qwen3.7 Max: 87.0
Step 3.7 Flash: Not measured
Weighted basis: 1 vs 0 rows
Reading: Not comparable

Multimodal

Not comparable

Qwen3.7 Max: Not measured
Step 3.7 Flash: Not measured
Weighted basis: 0 vs 0 rows
Reading: Not comparable

Instruction following

Not comparable

Qwen3.7 Max: 84.4
Step 3.7 Flash: Not measured
Weighted basis: 2 vs 0 rows
Reading: Not comparable

Category averages with the server-provided evidence basis for Qwen3.7 Max and Step 3.7 Flash
Category	Qwen3.7 Max	Step 3.7 Flash	Weighted basis	Reading
Agentic	69.7	66.4	Directional only1 vs 2 rows	Directional only
Coding	77.9	56.3	Directional only4 vs 1 rows	Directional only
Reasoning	90.4	Not measured	Not comparable1 vs 0 rows	Not comparable
Knowledge	64.2	Not measured	Not comparable4 vs 0 rows	Not comparable
Math	97.1	Not measured	Not comparable1 vs 0 rows	Not comparable
Multilingual	87.0	Not measured	Not comparable1 vs 0 rows	Not comparable
Multimodal	Not measured	Not measured	Not comparable0 vs 0 rows	Not comparable
Instruction following	84.4	Not measured	Not comparable2 vs 0 rows	Not comparable

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

Terminal-Bench 2.0
Agentic
Qwen3.7 Max: 69.7%Step 3.7 Flash: 59.5%Normalized gap 10.2Qwen3.7 Max source Step 3.7 Flash source
SWE-bench Pro
Coding
Qwen3.7 Max: 60.6%Step 3.7 Flash: 56.3%Normalized gap 4.3Qwen3.7 Max source Step 3.7 Flash source

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Qwen3.7 Max: API rate not published; Fits in one request
Step 3.7 Flash: $0.00077; Fits in one request

Qwen3.7 Max has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Qwen3.7 Max: API rate not published; Fits in one request
Step 3.7 Flash: $0.01345; Fits in one request

Qwen3.7 Max has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Qwen3.7 Max: API rate not published; Fits in one request; Cached-input rate unavailable
Step 3.7 Flash: $0.0555; Fits in one request; Cached input priced at the published list-input rate

Step 3.7 Flash has no published cached-input rate, so cached tokens use its listed input rate. Qwen3.7 Max has no comparable published API token rate.

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

SpecificationQwen3.7 MaxStep 3.7 Flash

Context window

Maximum documented context; output-token limits may be lower.

Qwen3.7 Max

Step 3.7 Flash

256K

API model ID

Qwen3.7 Max

Not sourced

Step 3.7 Flash

Not sourced

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Qwen3.7 Max

No comparable hosted API rate

Step 3.7 Flash

Not published

Documented inputs

Qwen3.7 Max

Not sourced

Step 3.7 Flash

Not sourced

Documented outputs

Qwen3.7 Max

Not sourced

Step 3.7 Flash

Not sourced

Provider availability

Qwen3.7 Max

Not sourced

Step 3.7 Flash

Not sourced

Reasoning profile

Qwen3.7 Max

Reasoning

Step 3.7 Flash

Reasoning

Weight access

Qwen3.7 Max

Proprietary

Step 3.7 Flash

Open Weight

License

Qwen3.7 Max

Proprietary

Step 3.7 Flash

Open Weight

Release date

Qwen3.7 Max

2026-05-16

Step 3.7 Flash

2026-05-29

If you already use one of these models

Deployment change: The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal: Qwen3.7 Max has the higher public score, 71.79 versus 51.05, and the 90% score intervals do not overlap.
Workload cost: A complete comparable API-rate estimate is not available for both models.
Context tradeoff: Qwen3.7 Max has the larger documented window (1M).

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence41 rows

Agentic

Terminal-Bench 2.0
Qwen3.7 Max69.7%
Source
Step 3.7 Flash59.5%
Source
Qwen3.7 Max leads this result
QwenClawBench
Qwen3.7 Max64.3%
Source
Step 3.7 Flash—
Not directly comparable
Claw-Eval
Qwen3.7 Max65.2%
Source
Step 3.7 Flash67.1%
Source
Step 3.7 Flash leads this result
BFCL v4
Qwen3.7 Max75.0%
Source
Step 3.7 Flash—
Not directly comparable
MCP Atlas
Qwen3.7 Max76.4%
Source
Step 3.7 Flash—
Not directly comparable
VITA-Bench
Qwen3.7 Max47.9%
Source
Step 3.7 Flash—
Not directly comparable
HLE w/ tools
Qwen3.7 Max53.5%
Source
Step 3.7 Flash47.2%
Source
Qwen3.7 Max leads this result
Gert Labs
Shared source
Qwen3.7 Max64.27%
Step 3.7 Flash51.57%
Qwen3.7 Max leads this result
ResearchClawBench
Qwen3.7 Max18.7%
Source
Step 3.7 Flash—
Not directly comparable
BrowseComp
Qwen3.7 Max—
Step 3.7 Flash75.8%
Source
Not directly comparable
DeepSearchQA
Qwen3.7 Max—
Step 3.7 Flash92.8%
Source
Not directly comparable
Toolathlon
Qwen3.7 Max—
Step 3.7 Flash49.5%
Source
Not directly comparable

Coding

SWE-bench Verified
Qwen3.7 Max80.4%
Source
Step 3.7 Flash—
Not directly comparable
SWE-bench Pro
Qwen3.7 Max60.6%
Source
Step 3.7 Flash56.3%
Source
Qwen3.7 Max leads this result
SWE Multilingual
Qwen3.7 Max78.3%
Source
Step 3.7 Flash—
Not directly comparable
NL2Repo
Qwen3.7 Max47.2%
Source
Step 3.7 Flash—
Not directly comparable
SciCode
Qwen3.7 Max53.5%
Source
Step 3.7 Flash—
Not directly comparable
LiveCodeBench
Qwen3.7 Max91.6%
Source
Step 3.7 Flash—
Not directly comparable
Terminal-Bench 2.0
Qwen3.7 Max69.7%
Source
Step 3.7 Flash59.5%
Source
Qwen3.7 Max leads this result
OpenHarmony Bench
Qwen3.7 Max53.4%
Source
Step 3.7 Flash—
Not directly comparable

Reasoning

MRCRv2
Qwen3.7 Max90.4%
Source
Step 3.7 Flash—
Not directly comparable
CritPt
Qwen3.7 Max13.4%
Source
Step 3.7 Flash—
Not directly comparable

Knowledge

GPQA
Qwen3.7 Max92.4%
Source
Step 3.7 Flash—
Not directly comparable
GPQA-D
Qwen3.7 Max92.4%
Source
Step 3.7 Flash—
Not directly comparable
HLE
Qwen3.7 Max41.4%
Source
Step 3.7 Flash—
Not directly comparable
MMLU-Pro
Qwen3.7 Max89.6%
Source
Step 3.7 Flash—
Not directly comparable
MMLU-Redux
Qwen3.7 Max95%
Source
Step 3.7 Flash—
Not directly comparable
SuperGPQA
Qwen3.7 Max73.6%
Source
Step 3.7 Flash—
Not directly comparable
MMMLU
Qwen3.7 Max90.3%
Source
Step 3.7 Flash—
Not directly comparable

Math

HMMT Feb 2026
Qwen3.7 Max97.1%
Source
Step 3.7 Flash—
Not directly comparable
IMOAnswerBench
Qwen3.7 Max90.0%
Source
Step 3.7 Flash—
Not directly comparable
Apex
Qwen3.7 Max44.5%
Source
Step 3.7 Flash—
Not directly comparable

Multilingual

MMLU-ProX
Qwen3.7 Max87%
Source
Step 3.7 Flash—
Not directly comparable
NOVA-63
Qwen3.7 Max59.0%
Source
Step 3.7 Flash—
Not directly comparable
INCLUDE
Qwen3.7 Max86.2%
Source
Step 3.7 Flash—
Not directly comparable
MAXIFE
Qwen3.7 Max89.2%
Source
Step 3.7 Flash—
Not directly comparable
PolyMath
Qwen3.7 Max86.5%
Source
Step 3.7 Flash—
Not directly comparable

Multimodal

SimpleVQA
Qwen3.7 Max—
Step 3.7 Flash79.2%
Source
Not directly comparable
V*
Qwen3.7 Max—
Step 3.7 Flash95.3%
Source
Not directly comparable

Instruction following

IFEval
Qwen3.7 Max94.3%
Source
Step 3.7 Flash—
Not directly comparable
IFBench
Qwen3.7 Max79.1%
Source
Step 3.7 Flash—
Not directly comparable

Frequently asked questions

Which is better, Qwen3.7 Max or Step 3.7 Flash?

Qwen3.7 Max has the higher public score, 71.79 versus 51.05, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.

Which is better for coding, Qwen3.7 Max or Step 3.7 Flash?

The current coding averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Qwen3.7 Max or Step 3.7 Flash?

The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.

Which costs less, Qwen3.7 Max or Step 3.7 Flash?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, Qwen3.7 Max or Step 3.7 Flash?

Qwen3.7 Max has the larger documented context window: 1M, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 30, 2026

Watch Qwen3.7 Max vs Step 3.7 Flash

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.

Qwen3.7 Max vs Step 3.7 Flash

Which one for your work

Long documents

Coding work

Agentic work

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

What is actually comparable

Category results, on a stated basis

Agentic

Coding

Reasoning

Knowledge

Math

Multilingual

Multimodal

Instruction following

Shape of the matched evidence

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

Benchmark evidence

Agentic

Coding

Reasoning

Knowledge

Math

Multilingual

Multimodal

Instruction following

Frequently asked questions

Which is better, Qwen3.7 Max or Step 3.7 Flash?

Which is better for coding, Qwen3.7 Max or Step 3.7 Flash?

Which is better for agentic tasks, Qwen3.7 Max or Step 3.7 Flash?

Which costs less, Qwen3.7 Max or Step 3.7 Flash?

Which has the larger context window, Qwen3.7 Max or Step 3.7 Flash?

Related comparisons

Watch Qwen3.7 Max vs Step 3.7 Flash