Skip to main content
BenchLM
Data

Qwen3.7 Plus vs Step 5 Preview

Updated November 5, 2026. Rank says Step 5 Preview is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Step 5 Preview has the higher public point estimate, 56.81 versus 53.91. Their conditional score ranges overlap. These ranges do not establish rank confidence. 6 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Alibaba logo
Qwen3.7 Plus

Alibaba

53.91/100

Estimated · Public rank #78

Conditional range 44.2–63.6

Model B
StepFun logo
Step 5 Preview

StepFun

56.81/100

Estimated · Public rank #60

Conditional range 47.1–66.5

Shared results
6
Qwen3.7 Plus only
47
Step 5 Preview only
18
Like-for-like categories
0 / 8
Estimated: Qwen3.7 Plus and Step 5 Preview. Conditional ranges do not establish rank confidence.How the comparison works

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.

No workload recommendation clears the current evidence threshold.

Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.

Show secondary and unsupported calls

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Qwen3.7 Plus and Step 5 Preview are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    Step 5 Preview is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

  • 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: listed-rates

  • 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

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

40.7Qwen3.7 Plus48.8Step 5 Preview

Directional only · BenchAlign v5.8

Step 5 Preview has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboardShortlist models for this job
Same basis rules as the category table below

What is actually comparable

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

4 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

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.

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Directional only
Qwen3.7 Plus
36.9
Supported · #83/135
Step 5 Preview
55.3
Estimated · #42/135
Basis
BenchAlign v5.8 lane · 11 vs 13 public rows
Reading
Directional only

Coding

Directional only
Qwen3.7 Plus
40.7
Estimated · #67/156
Step 5 Preview
48.8
Estimated · #47/156
Basis
BenchAlign v5.8 lane · 7 vs 6 public rows
Reading
Directional only

Multimodal

Directional only
Qwen3.7 Plus
81.3
#17/58
Step 5 Preview
73.3
#32/58
Basis
Provisional lane · 2 vs 2 weighted rows
Reading
Directional only

Knowledge

Directional only
Qwen3.7 Plus
53.6
Estimated · #64/177
Step 5 Preview
61.0
Supported · #44/177
Basis
BenchAlign v5.8 lane · 7 vs 2 public rows
Reading
Directional only

Reasoning

Not comparable
Qwen3.7 Plus
80.0
Unranked · 3 rankable rows
Step 5 Preview
82.5
Unranked · 2 rankable rows
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Qwen3.7 Plus
95.7
#3/17
Step 5 Preview
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Qwen3.7 Plus
92.8
#18/157
Step 5 Preview
Not ranked
Basis
Provisional lane · 1 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Qwen3.7 Plus
64.3
Unranked · 4 rankable rows
Step 5 Preview
Not ranked
Basis
Provisional lane · 2 vs 0 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

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 Plus
API rate not published
Fits in one request
Step 5 Preview
$0.00235
Fits in one request

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

Repository review

50K fresh input + 3K output tokens

Qwen3.7 Plus
API rate not published
Fits in one request
Step 5 Preview
$0.0581
Fits in one request

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

Cache-heavy agent loop

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

Qwen3.7 Plus
API rate not published
Fits in one request
Cached-input rate unavailable
Step 5 Preview
$0.057
Fits in one request

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

Cached input falls back to the list input rate only where a cached rate is unpublished

Specification differences

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

Cached-input rate

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

Qwen3.7 Plus

No comparable hosted API rate

Step 5 Preview

$0.05 per 1M cached input tokens

StepFun pricing and rate limits

Reasoning profile

Qwen3.7 Plus

Reasoning

Step 5 Preview

Reasoning

Weight access

Qwen3.7 Plus

Proprietary

Step 5 Preview

Open Weight

License

Qwen3.7 Plus

Proprietary

Step 5 Preview

Open Weight

Release date

Qwen3.7 Plus

2026-06-03

Step 5 Preview

2026-09-20

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
Step 5 Preview has the higher public point estimate, 56.81 versus 53.91. Their conditional score ranges overlap. These ranges do not establish rank confidence.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Qwen3.7 Plus or Step 5 Preview?

Step 5 Preview has the higher public point estimate, 56.81 versus 53.91. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Qwen3.7 Plus or Step 5 Preview?

Step 5 Preview scores higher for coding on the public lane, 48.8 to 40.7. Qwen3.7 Plus and Step 5 Preview are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Qwen3.7 Plus or Step 5 Preview?

Step 5 Preview scores higher for agentic tasks on the public lane, 55.3 to 36.9. Step 5 Preview is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which costs less, Qwen3.7 Plus or Step 5 Preview?

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 Plus or Step 5 Preview?

Both models list the same context window, 1M.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Qwen3.7 Plus
API / mo$0
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
Step 5 Preview
API / mo$2,775
Self-host / mo$27,962
Break-even617M/day
Model the full break-even

Benchmark evidence

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

Browse raw public benchmark evidence71 rows

Agentic

  • Terminal-Bench 2.0

    Qwen3.7 Plus70.3%
    Source
    Step 5 Preview—

    Not directly comparable

  • QwenClawBench

    Qwen3.7 Plus61.8%
    Source
    Step 5 Preview—

    Not directly comparable

  • Claw-Eval

    Qwen3.7 Plus62.7%
    Source
    Step 5 Preview—

    Not directly comparable

  • BFCL v4

    Qwen3.7 Plus72.9%
    Source
    Step 5 Preview—

    Not directly comparable

  • MCP Atlas

    Qwen3.7 Plus73.2%
    Source
    Step 5 Preview85.6%
    Source

    Step 5 Preview leads this result

  • VITA-Bench

    Qwen3.7 Plus45.6%
    Source
    Step 5 Preview—

    Not directly comparable

  • DeepPlanning

    Qwen3.7 Plus62.3%
    Source
    Step 5 Preview—

    Not directly comparable

  • OSWorld-Verified

    Qwen3.7 Plus73.3%
    Source
    Step 5 Preview—

    Not directly comparable

  • AndroidWorld

    Qwen3.7 Plus81.0%
    Source
    Step 5 Preview—

    Not directly comparable

  • OSWorld 2.0

    Qwen3.7 Plus2.8%
    Source
    Step 5 Preview—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Qwen3.7 Plus52.8%
    Source
    Step 5 Preview—

    Not directly comparable

  • Terminal-Bench 2.1

    Qwen3.7 Plus—
    Step 5 Preview85.0%
    Source

    Not directly comparable

  • Terminal-Bench 4.0

    Qwen3.7 Plus—
    Step 5 Preview33.30%
    Source

    Not directly comparable

  • CyberGym

    Qwen3.7 Plus—
    Step 5 Preview84.7%
    Source

    Not directly comparable

  • AutomationBench

    Qwen3.7 Plus—
    Step 5 Preview44.0%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Qwen3.7 Plus—
    Step 5 Preview74.1%
    Source

    Not directly comparable

  • JobBench

    Qwen3.7 Plus—
    Step 5 Preview59.0%
    Source

    Not directly comparable

  • APEX-Agents

    Qwen3.7 Plus—
    Step 5 Preview37.8%
    Source

    Not directly comparable

  • DRACO

    Qwen3.7 Plus—
    Step 5 Preview83.3%
    Source

    Not directly comparable

  • BrowseComp

    Qwen3.7 Plus—
    Step 5 Preview88.7%
    Source

    Not directly comparable

  • Agents' Last Exam

    Qwen3.7 Plus—
    Step 5 Preview29.5%
    Source

    Not directly comparable

  • Hermes Index

    Qwen3.7 Plus—
    Step 5 Preview32.8%
    Source

    Not directly comparable

  • Hermes Bench

    Qwen3.7 Plus—
    Step 5 Preview69.2%
    Source

    Not directly comparable

Coding

  • Terminal-Bench 2.0

    Qwen3.7 Plus70.3%
    Source
    Step 5 Preview—

    Not directly comparable

  • SWE-bench Verified

    Qwen3.7 Plus77.7%
    Source
    Step 5 Preview—

    Not directly comparable

  • SWE-bench Pro

    Qwen3.7 Plus57.6%
    Source
    Step 5 Preview—

    Not directly comparable

  • SWE Multilingual

    Qwen3.7 Plus75.8%
    Source
    Step 5 Preview—

    Not directly comparable

  • NL2Repo

    Qwen3.7 Plus41.1%
    Source
    Step 5 Preview—

    Not directly comparable

  • SciCode

    Qwen3.7 Plus51.3%
    Source
    Step 5 Preview58.9%
    Source

    Step 5 Preview leads this result

  • LiveCodeBench v6

    Qwen3.7 Plus89.6%
    Source
    Step 5 Preview—

    Not directly comparable

  • DeepSWE

    Qwen3.7 Plus—
    Step 5 Preview67.7%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Qwen3.7 Plus—
    Step 5 Preview85.0%
    Source

    Not directly comparable

  • ProgramBench

    Qwen3.7 Plus—
    Step 5 Preview80.5%
    Source

    Not directly comparable

  • sweMarathon

    Qwen3.7 Plus—
    Step 5 Preview72.7%
    Source

    Not directly comparable

  • MLS-Bench Lite

    Qwen3.7 Plus—
    Step 5 Preview40.5%
    Source

    Not directly comparable

Reasoning

  • CritPt

    Qwen3.7 Plus9.1%
    Source
    Step 5 Preview20.9%
    Source

    Step 5 Preview leads this result

  • MRCRv2

    Qwen3.7 Plus91.7%
    Source
    Step 5 Preview—

    Not directly comparable

Multimodal

  • MMMU-Pro

    Qwen3.7 Plus79%
    Source
    Step 5 Preview76%
    Source

    Qwen3.7 Plus leads this result

  • MathVision

    Qwen3.7 Plus90.3%
    Source
    Step 5 Preview—

    Not directly comparable

  • CharXiv

    Qwen3.7 Plus85.9%
    Source
    Step 5 Preview—

    Not directly comparable

  • ERQA

    Qwen3.7 Plus69.8%
    Source
    Step 5 Preview—

    Not directly comparable

  • MedXpertQA (MM)

    Qwen3.7 Plus71.0%
    Source
    Step 5 Preview—

    Not directly comparable

  • ScreenSpot Pro

    Qwen3.7 Plus79.0%
    Source
    Step 5 Preview—

    Not directly comparable

  • SimpleVQA

    Qwen3.7 Plus81.7%
    Source
    Step 5 Preview—

    Not directly comparable

  • MMSearch-Plus

    Qwen3.7 Plus41.4%
    Source
    Step 5 Preview—

    Not directly comparable

  • RealWorldQA

    Qwen3.7 Plus86.9%
    Source
    Step 5 Preview—

    Not directly comparable

  • OmniDocBench 1.5

    Qwen3.7 Plus91.4%
    Source
    Step 5 Preview—

    Not directly comparable

  • OCRBench V2

    Qwen3.7 Plus70.7%
    Source
    Step 5 Preview—

    Not directly comparable

  • ODINW13

    Qwen3.7 Plus51.1%
    Source
    Step 5 Preview—

    Not directly comparable

  • Video-MME (with subtitle)

    Qwen3.7 Plus88.0%
    Source
    Step 5 Preview—

    Not directly comparable

  • VideoMMMU

    Qwen3.7 Plus85.4%
    Source
    Step 5 Preview—

    Not directly comparable

  • MLVU (M-Avg)

    Qwen3.7 Plus87.4%
    Source
    Step 5 Preview—

    Not directly comparable

  • OfficeQA Pro

    Qwen3.7 Plus—
    Step 5 Preview60.3%
    Source

    Not directly comparable

Knowledge

  • GPQA

    Qwen3.7 Plus90.3%
    Source
    Step 5 Preview—

    Not directly comparable

  • GPQA-D

    Qwen3.7 Plus90.3%
    Source
    Step 5 Preview93.5%
    Source

    Step 5 Preview leads this result

  • HLE

    Qwen3.7 Plus34.7%
    Source
    Step 5 Preview46.5%
    Source

    Step 5 Preview leads this result

  • MMLU-Pro

    Qwen3.7 Plus88.5%
    Source
    Step 5 Preview—

    Not directly comparable

  • MMLU-Redux

    Qwen3.7 Plus94.5%
    Source
    Step 5 Preview—

    Not directly comparable

  • SuperGPQA

    Qwen3.7 Plus71.4%
    Source
    Step 5 Preview—

    Not directly comparable

  • MMMLU

    Qwen3.7 Plus89.0%
    Source
    Step 5 Preview—

    Not directly comparable

Multilingual

  • MMLU-ProX

    Qwen3.7 Plus85.4%
    Source
    Step 5 Preview—

    Not directly comparable

  • NOVA-63

    Qwen3.7 Plus58.8%
    Source
    Step 5 Preview—

    Not directly comparable

  • INCLUDE

    Qwen3.7 Plus83.0%
    Source
    Step 5 Preview—

    Not directly comparable

  • MAXIFE

    Qwen3.7 Plus88.8%
    Source
    Step 5 Preview—

    Not directly comparable

  • PolyMath

    Qwen3.7 Plus84.0%
    Source
    Step 5 Preview—

    Not directly comparable

Instruction following

  • IFEval

    Qwen3.7 Plus94.6%
    Source
    Step 5 Preview—

    Not directly comparable

  • IFBench

    Qwen3.7 Plus79.1%
    Source
    Step 5 Preview—

    Not directly comparable

Math

  • HMMT Feb 2026

    Qwen3.7 Plus92.9%
    Source
    Step 5 Preview—

    Not directly comparable

  • IMOAnswerBench

    Qwen3.7 Plus86.0%
    Source
    Step 5 Preview—

    Not directly comparable

  • Apex

    Qwen3.7 Plus22.7%
    Source
    Step 5 Preview—

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    Qwen3.7 Plus34.386%
    Source
    Step 5 Preview—

    Not directly comparable

71 public results · 6 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Qwen3.7 Plus vs Step 5 Preview

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

Read a sample issue

Join 6,100+ subscribers.

Last updated November 5, 2026