Enter opens the highlighted result. Esc closes.

Claude Haiku 5.5 vs Qwen4 Max

Qwen4 Max leads Claude Haiku 5.5 on coding, 74.0 to 68.5 on the Vibe Coding Index, and Claude Haiku 5.5 costs 8.6x less per output token ($0.50 vs $4.275 per million). Updated November 22, 2026; 25 benchmarks have a result for both.

Claude Haiku 5.5Anthropic
Coding
68.5
Overall
64.3
Output $/M
$0.50
7
Qwen4 MaxQwen
Coding
74.0
Overall
66.6
Output $/M
$4.275
18
vs boards won of 25 shared

Claude Haiku 5.5 or Qwen4 Max: which to pick

Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 68.5 for Claude Haiku 5.5, though on 4 benchmarks against 5.

Pick Claude Haiku 5.5 for output tokens 8.6x cheaper ($0.50 vs $4.275 per million) and work measured by LiveBench coding or Vibe Code Bench (Vals AI), where it leads.

Shared results
25
Claude Haiku 5.5 only
84
Qwen4 Max only
1
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 Haiku 5.5 68.5 from 5 benchmarks, Qwen4 Max 74.0 from 4 benchmarks.
Widest category
General, 16.6 points apart on average over 3 shared benchmarks.
Widest single gap
LiveBench data analysis: Claude Haiku 5.5 53.1% against Qwen4 Max 83.4%, 30.3 points apart on a 0 to 100 scale.
Output price
Claude Haiku 5.5 $0.50 against Qwen4 Max $4.275 per million output tokens, 8.6x 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
CategoryClaude Haiku 5.5BarsQwen4 MaxTies
Coding37
Intelligence01
Agentic work24
Reasoning12
Knowledge01
Web design10
General03
All shared boards718
CodingLike-for-likeSix of these boards feed the Vibe Coding Index37
Coding benchmarks for Claude Haiku 5.5 and Qwen4 Max
BenchmarkClaude Haiku 5.5Qwen4 MaxLeader
LiveBench coding77.6%69.8%Claude Haiku 5.5
LMArena WebDev15951751Qwen4 Max
Terminal-Bench 4 (Vals AI)36.4%48.5%Qwen4 Max
Vibe Code Bench (Vals AI)90.4%86.7%Claude Haiku 5.5
Code migration (Vals AI)44.6%Not measuredOnly Claude Haiku 5.5 measured
ProgramBench (Vals AI)2.5%Not measuredOnly Claude Haiku 5.5 measured
IOI (Vals AI)47.3%Not measuredOnly Claude Haiku 5.5 measured
SWE-bench Multimodal (Vals AI)44.0%Not measuredOnly Claude Haiku 5.5 measured
Vibe Code Bench 1-100 (Vals AI)20.4%Not measuredOnly Claude Haiku 5.5 measured
CyberBench (Vals AI)75.5%Not measuredOnly Claude Haiku 5.5 measured
SciCode55.0%Not measuredOnly Claude Haiku 5.5 measured
Terminal-Bench 4.0 (Artificial Analysis run)32.8%48.5%Qwen4 Max
FrontierCode 2.034.9%26.5%Claude Haiku 5.5
FrontierCode46.4%Not measuredOnly Claude Haiku 5.5 measured
FrontierSWE43.8%Not measuredOnly Claude Haiku 5.5 measured
MirrorCode78.9%Not measuredOnly Claude Haiku 5.5 measured
ALE-Bench1587.01831.0Qwen4 Max
LMArena Text: coding1452Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: software and IT1441Not measuredOnly Claude Haiku 5.5 measured
LMArena WebDev: React16181785Qwen4 Max
LMArena WebDev: HTML15691752Qwen4 Max
LMArena WebDev: from an imageNot measured1675Only Qwen4 Max measured
SciCode9.2%Not measuredOnly Claude Haiku 5.5 measured
SWE-Bench Pro V287.2%Not measuredOnly Claude Haiku 5.5 measured
GameBench 274.982.4Qwen4 Max
Terminal-Bench 4.040.0%Not measuredOnly Claude Haiku 5.5 measured
CursorBench 4.048.4%Not measuredOnly Claude Haiku 5.5 measured
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Claude Haiku 5.5 and Qwen4 Max
BenchmarkClaude Haiku 5.5Qwen4 MaxLeader
AA Intelligence Index36.542.9Qwen4 Max
Epoch Capabilities Index160.3Not measuredOnly Claude Haiku 5.5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index24
Agentic work benchmarks for Claude Haiku 5.5 and Qwen4 Max
BenchmarkClaude Haiku 5.5Qwen4 MaxLeader
LiveBench research84.3%84.7%Qwen4 Max
LiveBench browser69.5%80.7%Qwen4 Max
LiveBench long agentic47.9%46.6%Claude Haiku 5.5
SREBench (Vals AI)5.7%Not measuredOnly Claude Haiku 5.5 measured
Finance Agent (Vals AI)54.1%Not measuredOnly Claude Haiku 5.5 measured
Tax Agent Bench (Vals AI)31.9%40.4%Qwen4 Max
Legal Research Bench (Vals AI)43.8%41.4%Claude Haiku 5.5
Harvey's Legal Agent Benchmark (Vals AI)4.2%21.3%Qwen4 Max
Excel Modeling Benchmark (Vals AI)59.0%Not measuredOnly Claude Haiku 5.5 measured
BioMysteryBench (Vals AI)70.4%Not measuredOnly Claude Haiku 5.5 measured
Terminal-Bench-Science (Vals AI)10.0%Not measuredOnly Claude Haiku 5.5 measured
Vals Science Index38.5%Not measuredOnly Claude Haiku 5.5 measured
APEX-Agents56.1%Not measuredOnly Claude Haiku 5.5 measured
Vending-Bench 2$3,602Not measuredOnly Claude Haiku 5.5 measured
Neither model has a result on the other 30 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index12
Reasoning benchmarks for Claude Haiku 5.5 and Qwen4 Max
BenchmarkClaude Haiku 5.5Qwen4 MaxLeader
LiveBench reasoning82.4%92.2%Qwen4 Max
MysteryMechanism (Vals AI)35.1%Not measuredOnly Claude Haiku 5.5 measured
Humanity's Last Exam (Artificial Analysis run)44.4%Not measuredOnly Claude Haiku 5.5 measured
HLE-Diamond (Artificial Analysis run)29.6%44.9%Qwen4 Max
CritPt v2, hard subset (Artificial Analysis run)47.5%43.0%Claude Haiku 5.5
GPQA Diamond (Epoch AI run)89.6%Not measuredOnly Claude Haiku 5.5 measured
ARC-AGI89.0%Not measuredOnly Claude Haiku 5.5 measured
ARC-AGI-261.3%Not measuredOnly Claude Haiku 5.5 measured
SimpleBench59.2%Not measuredOnly Claude Haiku 5.5 measured
Chess puzzles55.0%Not measuredOnly Claude Haiku 5.5 measured
Mystery game puzzles30.0%Not measuredOnly Claude Haiku 5.5 measured
EBR-bench43.8%Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: hard prompts1416Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: expert1438Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: hard prompts in English1420Not measuredOnly Claude Haiku 5.5 measured
Humanity's Last Exam (Scale run)21.1%Not measuredOnly Claude Haiku 5.5 measured
Neither model has a result on the other 10 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Math benchmarks for Claude Haiku 5.5 and Qwen4 Max
BenchmarkClaude Haiku 5.5Qwen4 MaxLeader
OTIS Mock AIME98.9%Not measuredOnly Claude Haiku 5.5 measured
FrontierMath, tiers 1 to 375.1%Not measuredOnly Claude Haiku 5.5 measured
FrontierMath, tier 446.3%Not measuredOnly Claude Haiku 5.5 measured
ProofBench89.0%Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: math1433Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: mathematical work1432Not measuredOnly Claude Haiku 5.5 measured
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
Knowledge benchmarks for Claude Haiku 5.5 and Qwen4 Max
BenchmarkClaude Haiku 5.5Qwen4 MaxLeader
MedCode (Vals AI)51.5%Not measuredOnly Claude Haiku 5.5 measured
AA-Omniscience12.327.7Qwen4 Max
SimpleQA Verified23.8%Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: science1415Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: medicine and healthcare1377Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: legal and government1390Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: business and finance1392Not measuredOnly Claude Haiku 5.5 measured
FACTS Benchmark Suite47.3%Not measuredOnly Claude Haiku 5.5 measured
Neither model has a result on the other 13 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index10
Web design benchmarks for Claude Haiku 5.5 and Qwen4 Max
BenchmarkClaude Haiku 5.5Qwen4 MaxLeader
Design Arena: websites1248Not measuredOnly Claude Haiku 5.5 measured
Design Arena: UI components1259Not measuredOnly Claude Haiku 5.5 measured
Design Arena: game dev1313Not measuredOnly Claude Haiku 5.5 measured
Design Arena: data viz1276Not measuredOnly Claude Haiku 5.5 measured
Design Arena: 3D1307Not measuredOnly Claude Haiku 5.5 measured
Design Arena: all code categories1273Not measuredOnly Claude Haiku 5.5 measured
Design Arena: SVG1201Not measuredOnly Claude Haiku 5.5 measured
Design Arena: ASCII art1213Not measuredOnly Claude Haiku 5.5 measured
LiveBench design79.3%79.1%Claude Haiku 5.5
GeneralLike-for-likePublic boards, shown as published, kept out of the index03
General benchmarks for Claude Haiku 5.5 and Qwen4 Max
BenchmarkClaude Haiku 5.5Qwen4 MaxLeader
Vals Index58.7%63.2%Qwen4 Max
LiveBench data analysis53.1%83.4%Qwen4 Max
Public Benefits Bench (Vals AI)63.2%Not measuredOnly Claude Haiku 5.5 measured
SAGE (Vals AI)89.8%Not measuredOnly Claude Haiku 5.5 measured
MedScribe (Vals AI)89.5%Not measuredOnly Claude Haiku 5.5 measured
Long context reasoning (AA-LCR)82.7%Not measuredOnly Claude Haiku 5.5 measured
GDPval-AA16291809Qwen4 Max
DTBench95.0%Not measuredOnly Claude Haiku 5.5 measured
LMCA51.1%Not measuredOnly Claude Haiku 5.5 measured
Furniture assembly47.5%Not measuredOnly Claude Haiku 5.5 measured
LMArena Text1398Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: instruction following1407Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: creative writing1334Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: English1405Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: non-English1385Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: Chinese1435Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: German1427Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: Japanese1378Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: Korean1375Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: French1425Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: Spanish1396Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: Russian1379Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: Polish1385Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: multi-turn1387Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: longer queries1392Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: writing and language1366Not measuredOnly Claude Haiku 5.5 measured
LMArena Text: entertainment and media1350Not measuredOnly Claude Haiku 5.5 measured
MultiChallenge67.7%Not measuredOnly Claude Haiku 5.5 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 Claude Haiku 5.5 and Qwen4 Max
BenchmarkClaude Haiku 5.5Qwen4 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 Haiku 5.5$0.0003Fits in one request
Qwen4 Max$0.0036Fits in one request

Claude Haiku 5.5 costs less

Repository review

50K input + 3K output tokens

Claude Haiku 5.5$0.0065Fits in one request
Qwen4 Max$0.084Fits in one request

Claude Haiku 5.5 costs less

Agent loop

200K input + 10K output tokens

Claude Haiku 5.5$0.025Fits in one request
Qwen4 Max$0.328Fits in one request

Claude Haiku 5.5 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 Haiku 5.5 and Qwen4 Max
SpecificationAnthropic Claude Haiku 5.5Qwen4 Max
MakerAnthropicQwen
WeightsNo public weights listedNo public weights listed
ReleasedOctober 7, 2026November 16, 2026
Context window1M1M
Input $/Mtok$0.10$1.425
Output $/Mtok$0.50$4.275
Coding index68.574.0
Independent measurements behind it54
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Haiku 5.5 better than Qwen4 Max for coding?

Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 68.5 for Claude Haiku 5.5, though on 4 benchmarks against 5. Pick Claude Haiku 5.5 for output tokens 8.6x cheaper ($0.50 vs $4.275 per million) and work measured by LiveBench coding or Vibe Code Bench (Vals AI), where it leads.

Which is cheaper, Claude Haiku 5.5 or Qwen4 Max?

Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 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 Haiku 5.5 or Qwen4 Max?

Neither: both take 1M tokens.

How many benchmarks is the Claude Haiku 5.5 vs Qwen4 Max comparison based on?

25 benchmarks have a result for both models as of November 22, 2026. Claude Haiku 5.5'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-haiku-5-5-vs-qwen4-max" title="Claude Haiku 5.5 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-haiku-5-5-vs-qwen4-max">LLMBenchmark.ai, Claude Haiku 5.5 vs Qwen4 Max</a></p>