Enter opens the highlighted result. Esc closes.

Claude Fable 5.1 vs Qwen4 Max

Claude Fable 5.1 leads Qwen4 Max on coding, 82.8 to 74.0 on the Vibe Coding Index, and Qwen4 Max costs 11.7x less per output token ($4.275 vs $50.00 per million). Updated November 22, 2026; 24 benchmarks have a result for both.

Claude Fable 5.1Anthropic
Coding
82.8
Overall
83.0
Output $/M
$50.00
19
Qwen4 MaxQwen
Coding
74.0
Overall
66.6
Output $/M
$4.275
5
vs boards won of 24 shared

Claude Fable 5.1 or Qwen4 Max: which to pick

Pick Claude Fable 5.1 for coding: it scores 82.8 on the Vibe Coding Index against 74.0 for Qwen4 Max.

Pick Qwen4 Max for output tokens 11.7x cheaper ($4.275 vs $50.00 per million) and work measured by LMArena WebDev or LMArena WebDev: HTML, where it leads.

Shared results
24
Claude Fable 5.1 only
121
Qwen4 Max only
2
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
Claude Fable 5.1 82.8 from 5 benchmarks, Qwen4 Max 74.0 from 4 benchmarks.
Widest category
Agentic work, 13.0 points apart on average over 5 shared benchmarks.
Widest single gap
LiveBench long agentic: Claude Fable 5.1 74.2% against Qwen4 Max 46.6%, 27.6 points apart on a 0 to 100 scale.
Output price
Claude Fable 5.1 $50.00 against Qwen4 Max $4.275 per million output tokens, 11.7x 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
CategoryClaude Fable 5.1BarsQwen4 MaxTies
Coding92
Intelligence10
Agentic work50
Reasoning21
Knowledge10
Web design10
General02
All shared boards195
CodingLike-for-likeSix of these boards feed the Vibe Coding Index92
Coding benchmarks for Claude Fable 5.1 and Qwen4 Max
BenchmarkClaude Fable 5.1Qwen4 MaxLeader
LiveBench coding89.7%69.8%Claude Fable 5.1
LMArena WebDev17421751Qwen4 Max
LiveCodeBench (Vals AI)90.5%Not measuredOnly Claude Fable 5.1 measured
Terminal-Bench 4 (Vals AI)58.1%48.5%Claude Fable 5.1
Vibe Code Bench (Vals AI)90.3%86.7%Claude Fable 5.1
Code migration (Vals AI)54.6%Not measuredOnly Claude Fable 5.1 measured
ProgramBench (Vals AI)7.0%Not measuredOnly Claude Fable 5.1 measured
IOI (Vals AI)90.8%Not measuredOnly Claude Fable 5.1 measured
Terminal-Bench 2.1 (Vals AI)85.0%Not measuredOnly Claude Fable 5.1 measured
SWE-bench Multimodal (Vals AI)61.3%Not measuredOnly Claude Fable 5.1 measured
Vibe Code Bench 1-100 (Vals AI)28.0%Not measuredOnly Claude Fable 5.1 measured
SkillsBench (Vals AI)61.5%Not measuredOnly Claude Fable 5.1 measured
CyberBench (Vals AI)70.4%Not measuredOnly Claude Fable 5.1 measured
SciCode63.1%Not measuredOnly Claude Fable 5.1 measured
Terminal-Bench 4.0 (Artificial Analysis run)55.1%48.5%Claude Fable 5.1
FrontierCode 2.035.7%26.5%Claude Fable 5.1
FrontierCode50.9%Not measuredOnly Claude Fable 5.1 measured
FrontierSWE56.3%Not measuredOnly Claude Fable 5.1 measured
GSO-Bench88.2%Not measuredOnly Claude Fable 5.1 measured
WeirdML92.9%Not measuredOnly Claude Fable 5.1 measured
MirrorCode93.3%Not measuredOnly Claude Fable 5.1 measured
ALE-Bench2143.21831.0Claude Fable 5.1
LMArena Text: coding1527Not measuredOnly Claude Fable 5.1 measured
LMArena Text: software and IT1525Not measuredOnly Claude Fable 5.1 measured
LMArena WebDev: React17871785Claude Fable 5.1
LMArena WebDev: HTML16861752Qwen4 Max
LMArena WebDev: from an image17231675Claude Fable 5.1
SWE-Bench Pro V299.1%Not measuredOnly Claude Fable 5.1 measured
SWE Atlas: Codebase QnA60.0%Not measuredOnly Claude Fable 5.1 measured
SWE Atlas: Refactoring56.7%Not measuredOnly Claude Fable 5.1 measured
SWE Atlas: Test Writing67.0%Not measuredOnly Claude Fable 5.1 measured
GameBench 293.882.4Claude Fable 5.1
Terminal-Bench 4.057.9%Not measuredOnly Claude Fable 5.1 measured
ProgramBench9.0%Not measuredOnly Claude Fable 5.1 measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Claude Fable 5.1 and Qwen4 Max
BenchmarkClaude Fable 5.1Qwen4 MaxLeader
AA Intelligence Index50.042.9Claude Fable 5.1
Epoch Capabilities Index167.1Not measuredOnly Claude Fable 5.1 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
Agentic work benchmarks for Claude Fable 5.1 and Qwen4 Max
BenchmarkClaude Fable 5.1Qwen4 MaxLeader
Design Arena: agents building web apps1307Not measuredOnly Claude Fable 5.1 measured
Design Arena: agents building full-stack apps1303Not measuredOnly Claude Fable 5.1 measured
Design Arena: agents building mobile apps1254Not measuredOnly Claude Fable 5.1 measured
Design Arena: agents building Godot games1296Not measuredOnly Claude Fable 5.1 measured
Design Arena: HTML slides1394Not measuredOnly Claude Fable 5.1 measured
Design Arena: PowerPoint slides1318Not measuredOnly Claude Fable 5.1 measured
Design Arena: spreadsheets1342Not measuredOnly Claude Fable 5.1 measured
LiveBench research88.5%84.7%Claude Fable 5.1
LiveBench browser89.8%80.7%Claude Fable 5.1
LiveBench long agentic74.2%46.6%Claude Fable 5.1
SREBench (Vals AI)22.9%Not measuredOnly Claude Fable 5.1 measured
Finance Agent (Vals AI)58.9%Not measuredOnly Claude Fable 5.1 measured
Tax Agent Bench (Vals AI)50.7%40.4%Claude Fable 5.1
Legal Research Bench (Vals AI)55.3%41.4%Claude Fable 5.1
Harvey's Legal Agent Benchmark (Vals AI)Not measured21.3%Only Qwen4 Max measured
Excel Modeling Benchmark (Vals AI)76.7%Not measuredOnly Claude Fable 5.1 measured
Terminal-Bench-Science (Vals AI)40.0%Not measuredOnly Claude Fable 5.1 measured
Time Horizon Index (Vals AI)63.3%Not measuredOnly Claude Fable 5.1 measured
CUA-bench (Vals AI)13.2%Not measuredOnly Claude Fable 5.1 measured
Robo-bench (Vals AI)5.8%Not measuredOnly Claude Fable 5.1 measured
APEX-Agents68.6%Not measuredOnly Claude Fable 5.1 measured
Remote Labor Index17.9%Not measuredOnly Claude Fable 5.1 measured
PostTrainBench44.6%Not measuredOnly Claude Fable 5.1 measured
SpireClimb2.0%Not measuredOnly Claude Fable 5.1 measured
Vending-Bench 2$5,422Not measuredOnly Claude Fable 5.1 measured
LMArena Search1237Not measuredOnly Claude Fable 5.1 measured
MCP Atlas87.2%Not measuredOnly Claude Fable 5.1 measured
Neither model has a result on the other 17 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index21
Reasoning benchmarks for Claude Fable 5.1 and Qwen4 Max
BenchmarkClaude Fable 5.1Qwen4 MaxLeader
GPQA Diamond93.4%Not measuredOnly Claude Fable 5.1 measured
LiveBench reasoning91.7%92.2%Qwen4 Max
MysteryMechanism (Vals AI)47.8%Not measuredOnly Claude Fable 5.1 measured
MMMU Pro (Vals AI)90.6%Not measuredOnly Claude Fable 5.1 measured
GPQA Diamond (Artificial Analysis run)93.7%Not measuredOnly Claude Fable 5.1 measured
Humanity's Last Exam (Artificial Analysis run)59.1%Not measuredOnly Claude Fable 5.1 measured
HLE-Diamond (Artificial Analysis run)60.1%44.9%Claude Fable 5.1
CritPt v2, hard subset (Artificial Analysis run)62.0%43.0%Claude Fable 5.1
ARC-AGI97.5%Not measuredOnly Claude Fable 5.1 measured
ARC-AGI-290.0%Not measuredOnly Claude Fable 5.1 measured
SimpleBench86.6%Not measuredOnly Claude Fable 5.1 measured
Chess puzzles48.0%Not measuredOnly Claude Fable 5.1 measured
Mystery game puzzles58.0%Not measuredOnly Claude Fable 5.1 measured
EBR-bench57.1%Not measuredOnly Claude Fable 5.1 measured
LMArena Text: hard prompts1527Not measuredOnly Claude Fable 5.1 measured
LMArena Text: expert1546Not measuredOnly Claude Fable 5.1 measured
LMArena Text: hard prompts in English1523Not measuredOnly Claude Fable 5.1 measured
LMArena Vision: diagrams1345Not measuredOnly Claude Fable 5.1 measured
LMArena Vision: homework1339Not measuredOnly Claude Fable 5.1 measured
Humanity's Last Exam (Scale run)51.3%Not measuredOnly Claude Fable 5.1 measured
GoBench2266Not measuredOnly Claude Fable 5.1 measured
Neither model has a result on the other 5 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Math benchmarks for Claude Fable 5.1 and Qwen4 Max
BenchmarkClaude Fable 5.1Qwen4 MaxLeader
OTIS Mock AIME100.0%Not measuredOnly Claude Fable 5.1 measured
FrontierMath, tiers 1 to 390.2%Not measuredOnly Claude Fable 5.1 measured
FrontierMath, tier 487.8%Not measuredOnly Claude Fable 5.1 measured
ProofBench100.0%Not measuredOnly Claude Fable 5.1 measured
LMArena Text: math1533Not measuredOnly Claude Fable 5.1 measured
LMArena Text: mathematical work1543Not measuredOnly Claude Fable 5.1 measured
MathArena73.6%Not measuredOnly Claude Fable 5.1 measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
Knowledge benchmarks for Claude Fable 5.1 and Qwen4 Max
BenchmarkClaude Fable 5.1Qwen4 MaxLeader
MMLU Pro92.4%Not measuredOnly Claude Fable 5.1 measured
LegalBench (Vals AI)88.5%Not measuredOnly Claude Fable 5.1 measured
TaxEval (Vals AI)76.0%Not measuredOnly Claude Fable 5.1 measured
MortgageTax (Vals AI)70.8%Not measuredOnly Claude Fable 5.1 measured
MedCode (Vals AI)53.5%Not measuredOnly Claude Fable 5.1 measured
AA-Omniscience46.327.7Claude Fable 5.1
SimpleQA Verified70.8%Not measuredOnly Claude Fable 5.1 measured
GeoBench84.0%Not measuredOnly Claude Fable 5.1 measured
LMArena Text: science1537Not measuredOnly Claude Fable 5.1 measured
LMArena Text: medicine and healthcare1529Not measuredOnly Claude Fable 5.1 measured
LMArena Text: legal and government1522Not measuredOnly Claude Fable 5.1 measured
LMArena Text: business and finance1496Not measuredOnly Claude Fable 5.1 measured
PRBench Finance50.8%Not measuredOnly Claude Fable 5.1 measured
PRBench Legal50.8%Not measuredOnly Claude Fable 5.1 measured
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index10
Web design benchmarks for Claude Fable 5.1 and Qwen4 Max
BenchmarkClaude Fable 5.1Qwen4 MaxLeader
Design Arena: websites1300Not measuredOnly Claude Fable 5.1 measured
Design Arena: UI components1325Not measuredOnly Claude Fable 5.1 measured
Design Arena: game dev1348Not measuredOnly Claude Fable 5.1 measured
Design Arena: data viz1343Not measuredOnly Claude Fable 5.1 measured
Design Arena: 3D1375Not measuredOnly Claude Fable 5.1 measured
Design Arena: all code categories1322Not measuredOnly Claude Fable 5.1 measured
Design Arena: SVG1287Not measuredOnly Claude Fable 5.1 measured
Design Arena: ASCII art1309Not measuredOnly Claude Fable 5.1 measured
LiveBench design81.6%79.1%Claude Fable 5.1
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
General benchmarks for Claude Fable 5.1 and Qwen4 Max
BenchmarkClaude Fable 5.1Qwen4 MaxLeader
Vals IndexNot measured63.2%Only Qwen4 Max measured
LiveBench data analysis80.3%83.4%Qwen4 Max
Public Benefits Bench (Vals AI)74.9%Not measuredOnly Claude Fable 5.1 measured
MedScribe (Vals AI)91.3%Not measuredOnly Claude Fable 5.1 measured
Long context reasoning (AA-LCR)85.3%Not measuredOnly Claude Fable 5.1 measured
GDPval-AA17651809Qwen4 Max
DTBench97.6%Not measuredOnly Claude Fable 5.1 measured
LMCA65.5%Not measuredOnly Claude Fable 5.1 measured
Furniture assembly70.0%Not measuredOnly Claude Fable 5.1 measured
LMArena Text1512Not measuredOnly Claude Fable 5.1 measured
LMArena Text: instruction following1522Not measuredOnly Claude Fable 5.1 measured
LMArena Text: creative writing1516Not measuredOnly Claude Fable 5.1 measured
LMArena Vision1322Not measuredOnly Claude Fable 5.1 measured
LMArena Text: English1508Not measuredOnly Claude Fable 5.1 measured
LMArena Text: non-English1507Not measuredOnly Claude Fable 5.1 measured
LMArena Text: Chinese1586Not measuredOnly Claude Fable 5.1 measured
LMArena Text: German1505Not measuredOnly Claude Fable 5.1 measured
LMArena Text: Japanese1557Not measuredOnly Claude Fable 5.1 measured
LMArena Text: Korean1499Not measuredOnly Claude Fable 5.1 measured
LMArena Text: French1522Not measuredOnly Claude Fable 5.1 measured
LMArena Text: Spanish1508Not measuredOnly Claude Fable 5.1 measured
LMArena Text: Russian1519Not measuredOnly Claude Fable 5.1 measured
LMArena Text: Polish1536Not measuredOnly Claude Fable 5.1 measured
LMArena Text: multi-turn1490Not measuredOnly Claude Fable 5.1 measured
LMArena Text: longer queries1524Not measuredOnly Claude Fable 5.1 measured
LMArena Text: writing and language1516Not measuredOnly Claude Fable 5.1 measured
LMArena Text: entertainment and media1499Not measuredOnly Claude Fable 5.1 measured
LMArena Vision: English1319Not measuredOnly Claude Fable 5.1 measured
LMArena Vision: Chinese1394Not measuredOnly Claude Fable 5.1 measured
LMArena Vision: reading text1330Not measuredOnly Claude Fable 5.1 measured
LMArena Vision: humor1324Not measuredOnly Claude Fable 5.1 measured
LMArena Vision: creative writing1327Not measuredOnly Claude Fable 5.1 measured
LMArena Document1515Not measuredOnly Claude Fable 5.1 measured
Neither model has a result on the other 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Fable 5.1 and Qwen4 Max
BenchmarkClaude Fable 5.1Qwen4 MaxLeader
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

Claude Fable 5.1$0.035Fits in one request
Qwen4 Max$0.0036Fits in one request

Qwen4 Max costs less

Repository review

50K input + 3K output tokens

Claude Fable 5.1$0.650Fits in one request
Qwen4 Max$0.084Fits in one request

Qwen4 Max costs less

Agent loop

200K input + 10K output tokens

Claude Fable 5.1$2.50Fits in one request
Qwen4 Max$0.328Fits in one request

Qwen4 Max 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 Claude Fable 5.1 and Qwen4 Max
SpecificationAnthropic Claude Fable 5.1Qwen4 Max
MakerAnthropicQwen
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 1, 2026November 16, 2026
Context window1M1M
Input $/Mtok$10.00$1.425
Output $/Mtok$50.00$4.275
Coding index82.874.0
Independent measurements behind it54
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Fable 5.1 better than Qwen4 Max for coding?

Pick Claude Fable 5.1 for coding: it scores 82.8 on the Vibe Coding Index against 74.0 for Qwen4 Max. Pick Qwen4 Max for output tokens 11.7x cheaper ($4.275 vs $50.00 per million) and work measured by LMArena WebDev or LMArena WebDev: HTML, where it leads.

Which is cheaper, Claude Fable 5.1 or Qwen4 Max?

Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens; Qwen4 Max costs $1.425 and $4.275. Cost per solved task is known for neither of them.

Which has the bigger context window, Claude Fable 5.1 or Qwen4 Max?

Neither: both take 1M tokens.

How many benchmarks is the Claude Fable 5.1 vs Qwen4 Max comparison based on?

24 benchmarks have a result for both models as of November 22, 2026. Claude Fable 5.1's coding index rests on 5 independent benchmarks and Qwen4 Max'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/claude-fable-5-1-vs-qwen4-max" title="Claude Fable 5.1 vs Qwen4 Max, 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/claude-fable-5-1-vs-qwen4-max">LLMBenchmark.ai, Claude Fable 5.1 vs Qwen4 Max</a></p>