Enter opens the highlighted result. Esc closes.

GPT-5.4 vs Qwen4 Max

Qwen4 Max leads GPT-5.4 on coding, 74.0 to 64.3 on the Vibe Coding Index, and Qwen4 Max costs 3.5x less per output token ($4.275 vs $15.00 per million). Updated November 22, 2026; 8 benchmarks have a result for both.

GPT-5.4OpenAI
Coding
64.3
Overall
72.5
Output $/M
$15.00
0
Qwen4 MaxQwen
Coding
74.0
Overall
66.6
Output $/M
$4.275
8
vs boards won of 8 shared

GPT-5.4 or Qwen4 Max: which to pick

Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 64.3 for GPT-5.4.

Pick GPT-5.4 for a larger context window (1.05M against 1M tokens).

Shared results
8
GPT-5.4 only
112
Qwen4 Max only
18
Like-for-like categories
2 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
GPT-5.4 64.3 from 3 benchmarks, Qwen4 Max 74.0 from 4 benchmarks.
Widest category
General, 46.1 points apart on average over 1 shared benchmark.
Widest single gap
GDPval-AA: GPT-5.4 1255 against Qwen4 Max 1809, 46.1 points apart on a 0 to 100 scale.
Output price
GPT-5.4 $15.00 against Qwen4 Max $4.275 per million output tokens, 3.5x apart.
Context window
GPT-5.4 takes 1.05M tokens, Qwen4 Max 1M.

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
CategoryGPT-5.4BarsQwen4 MaxTies
Coding07
General01
All shared boards08
CodingLike-for-likeSix of these boards feed the Vibe Coding Index07
Coding benchmarks for GPT-5.4 and Qwen4 Max
BenchmarkGPT-5.4Qwen4 MaxLeader
LiveBench codingNot measured69.8%Only Qwen4 Max measured
LMArena WebDev14621751Qwen4 Max
LiveCodeBench (Vals AI)84.1%Not measuredOnly GPT-5.4 measured
SWE-bench Verified (Vals AI)78.2%Not measuredOnly GPT-5.4 measured
Terminal-Bench 4 (Vals AI)Not measured48.5%Only Qwen4 Max measured
Vibe Code Bench (Vals AI)67.4%86.7%Qwen4 Max
Code migration (Vals AI)35.0%Not measuredOnly GPT-5.4 measured
ProgramBench (Vals AI)0.5%Not measuredOnly GPT-5.4 measured
SkillsBench (Vals AI)51.7%Not measuredOnly GPT-5.4 measured
Terminal-Bench Hard (Artificial Analysis run)57.6%Not measuredOnly GPT-5.4 measured
Terminal-Bench 4.0 (Artificial Analysis run)Not measured48.5%Only Qwen4 Max measured
FrontierCode 2.0Not measured26.5%Only Qwen4 Max measured
Terminal-Bench81.8%Not measuredOnly GPT-5.4 measured
GSO-Bench31.4%Not measuredOnly GPT-5.4 measured
WeirdML77.7%Not measuredOnly GPT-5.4 measured
MirrorCode23.3%Not measuredOnly GPT-5.4 measured
ALE-Bench1607.01831.0Qwen4 Max
LMArena Text: coding1497Not measuredOnly GPT-5.4 measured
LMArena Text: software and IT1492Not measuredOnly GPT-5.4 measured
LMArena WebDev: React14511785Qwen4 Max
LMArena WebDev: HTML14761752Qwen4 Max
LMArena WebDev: from an image14411675Qwen4 Max
SWE Atlas: Codebase QnA40.8%Not measuredOnly GPT-5.4 measured
SWE Atlas: Refactoring44.3%Not measuredOnly GPT-5.4 measured
SWE Atlas: Test Writing44.4%Not measuredOnly GPT-5.4 measured
GameBench 262.282.4Qwen4 Max
ProgramBench0.0%Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 25 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for GPT-5.4 and Qwen4 Max
BenchmarkGPT-5.4Qwen4 MaxLeader
AA Intelligence IndexNot measured42.9Only Qwen4 Max measured
Epoch Capabilities Index157.9Not measuredOnly GPT-5.4 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index20 boards, none shared
Agentic work benchmarks for GPT-5.4 and Qwen4 Max
BenchmarkGPT-5.4Qwen4 MaxLeader
Design Arena: agents building web apps1027Not measuredOnly GPT-5.4 measured
Design Arena: agents building full-stack apps995Not measuredOnly GPT-5.4 measured
Design Arena: agents building mobile apps1079Not measuredOnly GPT-5.4 measured
Design Arena: agents building Android apps1020Not measuredOnly GPT-5.4 measured
Design Arena: agents building Godot games1135Not measuredOnly GPT-5.4 measured
LiveBench researchNot measured84.7%Only Qwen4 Max measured
LiveBench browserNot measured80.7%Only Qwen4 Max measured
LiveBench long agenticNot measured46.6%Only Qwen4 Max measured
Tax Agent Bench (Vals AI)Not measured40.4%Only Qwen4 Max measured
Legal Research Bench (Vals AI)Not measured41.4%Only Qwen4 Max measured
Harvey's Legal Agent Benchmark (Vals AI)Not measured21.3%Only Qwen4 Max measured
τ²-Bench Telecom87.1%Not measuredOnly GPT-5.4 measured
APEX-Agents52.4%Not measuredOnly GPT-5.4 measured
METR time horizons74.3%Not measuredOnly GPT-5.4 measured
DeepResearch Bench35.1%Not measuredOnly GPT-5.4 measured
PostTrainBench17.8%Not measuredOnly GPT-5.4 measured
Vending-Bench 2$6,144Not measuredOnly GPT-5.4 measured
LMArena Search1198Not measuredOnly GPT-5.4 measured
MCP Atlas70.6%Not measuredOnly GPT-5.4 measured
τ³-Banking39.4%Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 24 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index19 boards, none shared
Reasoning benchmarks for GPT-5.4 and Qwen4 Max
BenchmarkGPT-5.4Qwen4 MaxLeader
GPQA Diamond91.7%Not measuredOnly GPT-5.4 measured
LiveBench reasoningNot measured92.2%Only Qwen4 Max measured
MMMU Pro (Vals AI)87.5%Not measuredOnly GPT-5.4 measured
GPQA Diamond (Artificial Analysis run)92.0%Not measuredOnly GPT-5.4 measured
Humanity's Last Exam (Artificial Analysis run)43.7%Not measuredOnly GPT-5.4 measured
HLE-Diamond (Artificial Analysis run)Not measured44.9%Only Qwen4 Max measured
CritPt v2, hard subset (Artificial Analysis run)Not measured43.0%Only Qwen4 Max measured
GPQA Diamond (Epoch AI run)93.3%Not measuredOnly GPT-5.4 measured
ARC-AGI93.7%Not measuredOnly GPT-5.4 measured
ARC-AGI-274.0%Not measuredOnly GPT-5.4 measured
Chess puzzles48.0%Not measuredOnly GPT-5.4 measured
Mystery game puzzles37.0%Not measuredOnly GPT-5.4 measured
EBR-bench25.4%Not measuredOnly GPT-5.4 measured
LMArena Text: hard prompts1485Not measuredOnly GPT-5.4 measured
LMArena Text: expert1507Not measuredOnly GPT-5.4 measured
LMArena Text: hard prompts in English1479Not measuredOnly GPT-5.4 measured
LMArena Vision: diagrams1326Not measuredOnly GPT-5.4 measured
LMArena Vision: homework1336Not measuredOnly GPT-5.4 measured
Kagi LLM Benchmark63.8%Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 7 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Math benchmarks for GPT-5.4 and Qwen4 Max
BenchmarkGPT-5.4Qwen4 MaxLeader
AIME96.7%Not measuredOnly GPT-5.4 measured
OTIS Mock AIME97.8%Not measuredOnly GPT-5.4 measured
FrontierMath, tiers 1 to 378.6%Not measuredOnly GPT-5.4 measured
FrontierMath, tier 449.0%Not measuredOnly GPT-5.4 measured
ProofBench56.0%Not measuredOnly GPT-5.4 measured
LMArena Text: math1488Not measuredOnly GPT-5.4 measured
LMArena Text: mathematical work1497Not measuredOnly GPT-5.4 measured
MathArena33.8%Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 6 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index16 boards, none shared
Knowledge benchmarks for GPT-5.4 and Qwen4 Max
BenchmarkGPT-5.4Qwen4 MaxLeader
MMLU Pro87.5%Not measuredOnly GPT-5.4 measured
LegalBench (Vals AI)86.0%Not measuredOnly GPT-5.4 measured
CaseLaw (Vals AI)63.8%Not measuredOnly GPT-5.4 measured
CorpFin (Vals AI)65.3%Not measuredOnly GPT-5.4 measured
TaxEval (Vals AI)74.0%Not measuredOnly GPT-5.4 measured
MortgageTax (Vals AI)68.3%Not measuredOnly GPT-5.4 measured
MedQA (Vals AI)96.1%Not measuredOnly GPT-5.4 measured
MedCode (Vals AI)41.3%Not measuredOnly GPT-5.4 measured
AA-OmniscienceNot measured27.7Only Qwen4 Max measured
SimpleQA Verified45.1%Not measuredOnly GPT-5.4 measured
LMArena Text: science1478Not measuredOnly GPT-5.4 measured
LMArena Text: medicine and healthcare1458Not measuredOnly GPT-5.4 measured
LMArena Text: legal and government1485Not measuredOnly GPT-5.4 measured
LMArena Text: business and finance1475Not measuredOnly GPT-5.4 measured
PRBench Finance45.6%Not measuredOnly GPT-5.4 measured
PRBench Legal45.6%Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for GPT-5.4 and Qwen4 Max
BenchmarkGPT-5.4Qwen4 MaxLeader
Design Arena: websites1186Not measuredOnly GPT-5.4 measured
Design Arena: UI components1199Not measuredOnly GPT-5.4 measured
Design Arena: game dev1166Not measuredOnly GPT-5.4 measured
Design Arena: data viz1190Not measuredOnly GPT-5.4 measured
Design Arena: 3D1032Not measuredOnly GPT-5.4 measured
Design Arena: all code categories1161Not measuredOnly GPT-5.4 measured
Design Arena: SVG1126Not measuredOnly GPT-5.4 measured
Design Arena: ASCII art1174Not measuredOnly GPT-5.4 measured
LiveBench designNot measured79.1%Only Qwen4 Max measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
General benchmarks for GPT-5.4 and Qwen4 Max
BenchmarkGPT-5.4Qwen4 MaxLeader
Vals IndexNot measured63.2%Only Qwen4 Max measured
LiveBench data analysisNot measured83.4%Only Qwen4 Max measured
MedScribe (Vals AI)77.5%Not measuredOnly GPT-5.4 measured
IFBench73.9%Not measuredOnly GPT-5.4 measured
Long context reasoning (AA-LCR)82.0%Not measuredOnly GPT-5.4 measured
GDPval-AA12551809Qwen4 Max
DTBench94.4%Not measuredOnly GPT-5.4 measured
LMCA52.0%Not measuredOnly GPT-5.4 measured
CL-bench27.9%Not measuredOnly GPT-5.4 measured
Furniture assembly37.5%Not measuredOnly GPT-5.4 measured
CL-bench Life21.7%Not measuredOnly GPT-5.4 measured
LMArena Text1469Not measuredOnly GPT-5.4 measured
LMArena Text: instruction following1469Not measuredOnly GPT-5.4 measured
LMArena Text: creative writing1437Not measuredOnly GPT-5.4 measured
LMArena Vision1301Not measuredOnly GPT-5.4 measured
LMArena Text: English1467Not measuredOnly GPT-5.4 measured
LMArena Text: non-English1465Not measuredOnly GPT-5.4 measured
LMArena Text: Chinese1518Not measuredOnly GPT-5.4 measured
LMArena Text: German1472Not measuredOnly GPT-5.4 measured
LMArena Text: Japanese1484Not measuredOnly GPT-5.4 measured
LMArena Text: Korean1449Not measuredOnly GPT-5.4 measured
LMArena Text: French1494Not measuredOnly GPT-5.4 measured
LMArena Text: Spanish1453Not measuredOnly GPT-5.4 measured
LMArena Text: Russian1481Not measuredOnly GPT-5.4 measured
LMArena Text: Polish1472Not measuredOnly GPT-5.4 measured
LMArena Text: multi-turn1482Not measuredOnly GPT-5.4 measured
LMArena Text: longer queries1473Not measuredOnly GPT-5.4 measured
LMArena Text: writing and language1457Not measuredOnly GPT-5.4 measured
LMArena Text: entertainment and media1438Not measuredOnly GPT-5.4 measured
LMArena Vision: English1298Not measuredOnly GPT-5.4 measured
LMArena Vision: Chinese1356Not measuredOnly GPT-5.4 measured
LMArena Vision: reading text1310Not measuredOnly GPT-5.4 measured
LMArena Vision: humor1285Not measuredOnly GPT-5.4 measured
LMArena Vision: recognizing things1246Not measuredOnly GPT-5.4 measured
LMArena Vision: creative writing1286Not measuredOnly GPT-5.4 measured
LMArena Document1473Not measuredOnly GPT-5.4 measured
EQ-Bench 41258Not measuredOnly GPT-5.4 measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5.4 and Qwen4 Max
BenchmarkGPT-5.4Qwen4 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

GPT-5.4$0.010Fits in one request
Qwen4 Max$0.0036Fits in one request

Qwen4 Max costs less

Repository review

50K input + 3K output tokens

GPT-5.4$0.170Fits in one request
Qwen4 Max$0.084Fits in one request

Qwen4 Max costs less

Agent loop

200K input + 10K output tokens

GPT-5.4$0.650Fits 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 GPT-5.4 and Qwen4 Max
SpecificationOpenAI GPT-5.4Qwen4 Max
MakerOpenAIQwen
WeightsNo public weights listedNo public weights listed
ReleasedMarch 5, 2026November 16, 2026
Context window1.05M1M
Input $/Mtok$2.50$1.425
Output $/Mtok$15.00$4.275
Coding index64.374.0
Independent measurements behind it34
Cost per solved task$1.02Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.4 better than Qwen4 Max for coding?

Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 64.3 for GPT-5.4. Pick GPT-5.4 for a larger context window (1.05M against 1M tokens).

Which is cheaper, GPT-5.4 or Qwen4 Max?

GPT-5.4 costs $2.50 per million input tokens and $15.00 per million output tokens; Qwen4 Max costs $1.425 and $4.275. Cost per solved task is known for GPT-5.4 only.

Which has the bigger context window, GPT-5.4 or Qwen4 Max?

GPT-5.4, with 1.05M tokens against 1M.

How many benchmarks is the GPT-5.4 vs Qwen4 Max comparison based on?

8 benchmarks have a result for both models as of November 22, 2026. GPT-5.4's coding index rests on 3 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/gpt-5-4-vs-qwen4-max" title="GPT-5.4 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/gpt-5-4-vs-qwen4-max">LLMBenchmark.ai, GPT-5.4 vs Qwen4 Max</a></p>