Enter opens the highlighted result. Esc closes.

Qwen4 Max vs Step 5 Preview

Qwen4 Max leads Step 5 Preview on coding, 74.0 to 57.3 on the Vibe Coding Index, and Step 5 Preview costs 1.6x less per output token ($2.70 vs $4.275 per million). Updated November 22, 2026; 25 benchmarks have a result for both.

Qwen4 MaxQwen
Coding
74.0
Overall
66.6
Output $/M
$4.275
25
Step 5 PreviewStepFun
Coding
57.3
Overall
55.1
Output $/M
$2.70
0
vs boards won of 25 shared

Qwen4 Max or Step 5 Preview: which to pick

Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 57.3 for Step 5 Preview.

Pick Step 5 Preview for output tokens 1.6x cheaper ($2.70 vs $4.275 per million).

Shared results
25
Qwen4 Max only
1
Step 5 Preview only
51
Like-for-like categories
7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Qwen4 Max 74.0 from 4 benchmarks, Step 5 Preview 57.3 from 4 benchmarks.
Widest category
Agentic work, 19.1 points apart on average over 6 shared benchmarks.
Widest single gap
LiveBench browser: Qwen4 Max 80.7% against Step 5 Preview 24.8%, 55.9 points apart on a 0 to 100 scale.
Output price
Qwen4 Max $4.275 against Step 5 Preview $2.70 per million output tokens, 1.6x apart.
Context window
Both take 1M tokens.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryQwen4 MaxBarsStep 5 PreviewTies
Coding100
Intelligence10
Agentic work60
Reasoning30
Knowledge10
Web design10
General30
All shared boards250
CodingLike-for-likeSix of these boards feed the Vibe Coding Index100
Coding benchmarks for Qwen4 Max and Step 5 Preview
BenchmarkQwen4 MaxStep 5 PreviewLeader
LiveBench coding69.8%67.6%Qwen4 Max
LMArena WebDev17511570Qwen4 Max
Terminal-Bench 4 (Vals AI)48.5%31.8%Qwen4 Max
Vibe Code Bench (Vals AI)86.7%70.4%Qwen4 Max
Code migration (Vals AI)Not measured39.0%Only Step 5 Preview measured
IOI (Vals AI)Not measured38.1%Only Step 5 Preview measured
SWE-bench Multimodal (Vals AI)Not measured40.8%Only Step 5 Preview measured
SciCodeNot measured58.9%Only Step 5 Preview measured
Terminal-Bench 4.0 (Artificial Analysis run)48.5%33.3%Qwen4 Max
FrontierCode 2.026.5%12.0%Qwen4 Max
ALE-Bench1831.0Not measuredOnly Qwen4 Max measured
LMArena Text: codingNot measured1481Only Step 5 Preview measured
LMArena Text: software and ITNot measured1472Only Step 5 Preview measured
LMArena WebDev: React17851588Qwen4 Max
LMArena WebDev: HTML17521542Qwen4 Max
LMArena WebDev: from an image16751550Qwen4 Max
GameBench 282.453.2Qwen4 Max
Neither model has a result on the other 35 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Qwen4 Max and Step 5 Preview
BenchmarkQwen4 MaxStep 5 PreviewLeader
AA Intelligence Index42.928.5Qwen4 Max
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
Agentic work benchmarks for Qwen4 Max and Step 5 Preview
BenchmarkQwen4 MaxStep 5 PreviewLeader
LiveBench research84.7%75.5%Qwen4 Max
LiveBench browser80.7%24.8%Qwen4 Max
LiveBench long agentic46.6%19.4%Qwen4 Max
SREBench (Vals AI)Not measured0.4%Only Step 5 Preview measured
Finance Agent (Vals AI)Not measured50.7%Only Step 5 Preview measured
Tax Agent Bench (Vals AI)40.4%27.3%Qwen4 Max
Legal Research Bench (Vals AI)41.4%40.4%Qwen4 Max
Harvey's Legal Agent Benchmark (Vals AI)21.3%12.9%Qwen4 Max
Excel Modeling Benchmark (Vals AI)Not measured57.1%Only Step 5 Preview measured
BioMysteryBench (Vals AI)Not measured67.4%Only Step 5 Preview measured
Terminal-Bench-Science (Vals AI)Not measured2.9%Only Step 5 Preview measured
Vals Science IndexNot measured29.6%Only Step 5 Preview measured
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
Reasoning benchmarks for Qwen4 Max and Step 5 Preview
BenchmarkQwen4 MaxStep 5 PreviewLeader
LiveBench reasoning92.2%83.8%Qwen4 Max
MysteryMechanism (Vals AI)Not measured18.5%Only Step 5 Preview measured
Humanity's Last Exam (Artificial Analysis run)Not measured46.5%Only Step 5 Preview measured
HLE-Diamond (Artificial Analysis run)44.9%24.3%Qwen4 Max
CritPt v2, hard subset (Artificial Analysis run)43.0%32.5%Qwen4 Max
LMArena Text: hard promptsNot measured1463Only Step 5 Preview measured
LMArena Text: expertNot measured1479Only Step 5 Preview measured
LMArena Text: hard prompts in EnglishNot measured1464Only Step 5 Preview measured
LMArena Vision: diagramsNot measured1301Only Step 5 Preview measured
LMArena Vision: homeworkNot measured1275Only Step 5 Preview measured
Neither model has a result on the other 16 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
Math benchmarks for Qwen4 Max and Step 5 Preview
BenchmarkQwen4 MaxStep 5 PreviewLeader
ProofBenchNot measured42.0%Only Step 5 Preview measured
LMArena Text: mathNot measured1466Only Step 5 Preview measured
LMArena Text: mathematical workNot measured1466Only Step 5 Preview measured
Neither model has a result on the other 11 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
Knowledge benchmarks for Qwen4 Max and Step 5 Preview
BenchmarkQwen4 MaxStep 5 PreviewLeader
AA-Omniscience27.716.4Qwen4 Max
LMArena Text: scienceNot measured1463Only Step 5 Preview measured
LMArena Text: medicine and healthcareNot measured1443Only Step 5 Preview measured
LMArena Text: legal and governmentNot measured1439Only Step 5 Preview measured
LMArena Text: business and financeNot measured1445Only Step 5 Preview measured
Neither model has a result on the other 16 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index10
Web design benchmarks for Qwen4 Max and Step 5 Preview
BenchmarkQwen4 MaxStep 5 PreviewLeader
LiveBench design79.1%70.8%Qwen4 Max
Neither model has a result on the other 8 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index30
General benchmarks for Qwen4 Max and Step 5 Preview
BenchmarkQwen4 MaxStep 5 PreviewLeader
Vals Index63.2%54.8%Qwen4 Max
LiveBench data analysis83.4%63.5%Qwen4 Max
Public Benefits Bench (Vals AI)Not measured58.1%Only Step 5 Preview measured
Long context reasoning (AA-LCR)Not measured88.3%Only Step 5 Preview measured
GDPval-AA18091591Qwen4 Max
LMArena TextNot measured1444Only Step 5 Preview measured
LMArena Text: instruction followingNot measured1446Only Step 5 Preview measured
LMArena Text: creative writingNot measured1416Only Step 5 Preview measured
LMArena VisionNot measured1265Only Step 5 Preview measured
LMArena Text: EnglishNot measured1456Only Step 5 Preview measured
LMArena Text: non-EnglishNot measured1430Only Step 5 Preview measured
LMArena Text: ChineseNot measured1495Only Step 5 Preview measured
LMArena Text: GermanNot measured1453Only Step 5 Preview measured
LMArena Text: JapaneseNot measured1398Only Step 5 Preview measured
LMArena Text: KoreanNot measured1402Only Step 5 Preview measured
LMArena Text: FrenchNot measured1444Only Step 5 Preview measured
LMArena Text: SpanishNot measured1445Only Step 5 Preview measured
LMArena Text: RussianNot measured1432Only Step 5 Preview measured
LMArena Text: PolishNot measured1406Only Step 5 Preview measured
LMArena Text: multi-turnNot measured1439Only Step 5 Preview measured
LMArena Text: longer queriesNot measured1454Only Step 5 Preview measured
LMArena Text: writing and languageNot measured1431Only Step 5 Preview measured
LMArena Text: entertainment and mediaNot measured1414Only Step 5 Preview measured
LMArena Vision: EnglishNot measured1275Only Step 5 Preview measured
LMArena Vision: ChineseNot measured1318Only Step 5 Preview measured
LMArena Vision: reading textNot measured1279Only Step 5 Preview measured
LMArena Vision: humorNot measured1215Only Step 5 Preview measured
LMArena Vision: creative writingNot measured1250Only Step 5 Preview measured
Neither model has a result on the other 21 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Qwen4 Max and Step 5 Preview
BenchmarkQwen4 MaxStep 5 PreviewLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Qwen4 Max$0.0036Fits in one request
Step 5 Preview$0.0024Fits in one request

Step 5 Preview costs less

Repository review

50K input + 3K output tokens

Qwen4 Max$0.084Fits in one request
Step 5 Preview$0.058Fits in one request

Step 5 Preview costs less

Agent loop

200K input + 10K output tokens

Qwen4 Max$0.328Fits in one request
Step 5 Preview$0.227Fits in one request

Step 5 Preview costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Qwen4 Max and Step 5 Preview
SpecificationQwen4 MaxStepFun Step 5 Preview
MakerQwenStepFun
WeightsNo public weights listedOpen weights
ReleasedNovember 16, 2026October 8, 2026
Context window1M1M
Input $/Mtok$1.425$1.00
Output $/Mtok$4.275$2.70
Coding index74.057.3
Independent measurements behind it44
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Qwen4 Max better than Step 5 Preview for coding?

Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 57.3 for Step 5 Preview. Pick Step 5 Preview for output tokens 1.6x cheaper ($2.70 vs $4.275 per million).

Which is cheaper, Qwen4 Max or Step 5 Preview?

Qwen4 Max costs $1.425 per million input tokens and $4.275 per million output tokens; Step 5 Preview costs $1.00 and $2.70. Cost per solved task is known for neither of them.

Which has the bigger context window, Qwen4 Max or Step 5 Preview?

Neither: both take 1M tokens.

How many benchmarks is the Qwen4 Max vs Step 5 Preview comparison based on?

25 benchmarks have a result for both models as of November 22, 2026. Qwen4 Max's coding index rests on 4 independent benchmarks and Step 5 Preview's on 4. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/qwen4-max-vs-stepfun-step-5-preview" title="Qwen4 Max vs Step 5 Preview, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/qwen4-max-vs-stepfun-step-5-preview">LLMBenchmark.ai, Qwen4 Max vs Step 5 Preview</a></p>