Enter opens the highlighted result. Esc closes.

GPT-5.1 vs Qwen4 Max

Qwen4 Max leads GPT-5.1 on coding, 74.0 to 40.5 on the Vibe Coding Index, and Qwen4 Max costs 2.3x less per output token ($4.275 vs $10.00 per million). Updated November 22, 2026; 6 benchmarks have a result for both.

GPT-5.1OpenAI
Coding
40.5
Overall
59.3
Output $/M
$10.00
0
Qwen4 MaxQwen
Coding
74.0
Overall
66.6
Output $/M
$4.275
6
vs boards won of 6 shared

GPT-5.1 or Qwen4 Max: which to pick

Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 40.5 for GPT-5.1.

GPT-5.1 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.

Shared results
6
GPT-5.1 only
98
Qwen4 Max only
20
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-5.1 40.5 from 3 benchmarks, Qwen4 Max 74.0 from 4 benchmarks.
Widest category
General, 81.3 points apart on average over 1 shared benchmark.
Widest single gap
GDPval-AA: GPT-5.1 833 against Qwen4 Max 1809, 81.3 points apart on a 0 to 100 scale.
Output price
GPT-5.1 $10.00 against Qwen4 Max $4.275 per million output tokens, 2.3x apart.
Context window
GPT-5.1 takes 400K 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-5.1BarsQwen4 MaxTies
Coding05
General01
All shared boards06
CodingLike-for-likeSix of these boards feed the Vibe Coding Index05
Coding benchmarks for GPT-5.1 and Qwen4 Max
BenchmarkGPT-5.1Qwen4 MaxLeader
SWE-bench Verified66.0%Not measuredOnly GPT-5.1 measured
LiveBench codingNot measured69.8%Only Qwen4 Max measured
LMArena WebDev13971751Qwen4 Max
LiveCodeBench (Vals AI)86.5%Not measuredOnly GPT-5.1 measured
SWE-bench Verified (Vals AI)69.8%Not measuredOnly GPT-5.1 measured
Terminal-Bench 4 (Vals AI)Not measured48.5%Only Qwen4 Max measured
Vibe Code Bench (Vals AI)24.6%86.7%Qwen4 Max
LiveCodeBench (Artificial Analysis run)86.8%Not measuredOnly GPT-5.1 measured
Terminal-Bench Hard (Artificial Analysis run)45.5%Not measuredOnly GPT-5.1 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-Bench47.6%Not measuredOnly GPT-5.1 measured
GSO-Bench13.7%Not measuredOnly GPT-5.1 measured
WeirdML60.8%Not measuredOnly GPT-5.1 measured
ALE-BenchNot measured1831.0Only Qwen4 Max measured
LMArena Text: coding1453Not measuredOnly GPT-5.1 measured
LMArena Text: software and IT1454Not measuredOnly GPT-5.1 measured
LMArena WebDev: React13071785Qwen4 Max
LMArena WebDev: HTML14061752Qwen4 Max
LMArena WebDev: from an image14191675Qwen4 Max
GameBench 2Not measured82.4Only Qwen4 Max measured
Terminal-Bench 2.047.6%Not measuredOnly GPT-5.1 measured
Neither model has a result on the other 30 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for GPT-5.1 and Qwen4 Max
BenchmarkGPT-5.1Qwen4 MaxLeader
AA Intelligence IndexNot measured42.9Only Qwen4 Max measured
Epoch Capabilities Index150.9Not measuredOnly GPT-5.1 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
Agentic work benchmarks for GPT-5.1 and Qwen4 Max
BenchmarkGPT-5.1Qwen4 MaxLeader
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 Telecom81.9%Not measuredOnly GPT-5.1 measured
DeepResearch Bench42.8%Not measuredOnly GPT-5.1 measured
Vending-Bench 2$1,473Not measuredOnly GPT-5.1 measured
LMArena Search1199Not measuredOnly GPT-5.1 measured
MCP Atlas50.1%Not measuredOnly GPT-5.1 measured
Neither model has a result on the other 33 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index19 boards, none shared
Reasoning benchmarks for GPT-5.1 and Qwen4 Max
BenchmarkGPT-5.1Qwen4 MaxLeader
GPQA Diamond86.6%Not measuredOnly GPT-5.1 measured
LiveBench reasoningNot measured92.2%Only Qwen4 Max measured
MMMU Pro (Vals AI)83.2%Not measuredOnly GPT-5.1 measured
GPQA Diamond (Artificial Analysis run)87.3%Not measuredOnly GPT-5.1 measured
Humanity's Last Exam (Artificial Analysis run)28.5%Not measuredOnly GPT-5.1 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)87.6%Not measuredOnly GPT-5.1 measured
ARC-AGI72.8%Not measuredOnly GPT-5.1 measured
ARC-AGI-217.6%Not measuredOnly GPT-5.1 measured
SimpleBench53.2%Not measuredOnly GPT-5.1 measured
Chess puzzles42.0%Not measuredOnly GPT-5.1 measured
Mystery game puzzles19.0%Not measuredOnly GPT-5.1 measured
VPCT58.7%Not measuredOnly GPT-5.1 measured
LMArena Text: hard prompts1457Not measuredOnly GPT-5.1 measured
LMArena Text: expert1469Not measuredOnly GPT-5.1 measured
LMArena Text: hard prompts in English1462Not measuredOnly GPT-5.1 measured
LMArena Vision: diagrams1264Not measuredOnly GPT-5.1 measured
LMArena Vision: homework1273Not measuredOnly GPT-5.1 measured
Neither model has a result on the other 7 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Math benchmarks for GPT-5.1 and Qwen4 Max
BenchmarkGPT-5.1Qwen4 MaxLeader
AIME93.3%Not measuredOnly GPT-5.1 measured
MGSM (Vals AI)93.0%Not measuredOnly GPT-5.1 measured
AIME 2025 (Artificial Analysis run)94.0%Not measuredOnly GPT-5.1 measured
OTIS Mock AIME88.6%Not measuredOnly GPT-5.1 measured
LMArena Text: math1447Not measuredOnly GPT-5.1 measured
LMArena Text: mathematical work1450Not measuredOnly GPT-5.1 measured
MathArena15.5%Not measuredOnly GPT-5.1 measured
Neither model has a result on the other 7 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index17 boards, none shared
Knowledge benchmarks for GPT-5.1 and Qwen4 Max
BenchmarkGPT-5.1Qwen4 MaxLeader
MMLU Pro86.4%Not measuredOnly GPT-5.1 measured
LegalBench (Vals AI)85.7%Not measuredOnly GPT-5.1 measured
CaseLaw (Vals AI)73.4%Not measuredOnly GPT-5.1 measured
CorpFin (Vals AI)63.8%Not measuredOnly GPT-5.1 measured
TaxEval (Vals AI)74.9%Not measuredOnly GPT-5.1 measured
MortgageTax (Vals AI)61.4%Not measuredOnly GPT-5.1 measured
MedQA (Vals AI)96.4%Not measuredOnly GPT-5.1 measured
MedCode (Vals AI)52.7%Not measuredOnly GPT-5.1 measured
MMLU Pro (Artificial Analysis run)87.0%Not measuredOnly GPT-5.1 measured
AA-OmniscienceNot measured27.7Only Qwen4 Max measured
SimpleQA Verified48.0%Not measuredOnly GPT-5.1 measured
LMArena Text: science1459Not measuredOnly GPT-5.1 measured
LMArena Text: medicine and healthcare1456Not measuredOnly GPT-5.1 measured
LMArena Text: legal and government1459Not measuredOnly GPT-5.1 measured
LMArena Text: business and finance1431Not measuredOnly GPT-5.1 measured
PRBench Finance48.0%Not measuredOnly GPT-5.1 measured
PRBench Legal48.0%Not measuredOnly GPT-5.1 measured
Neither model has a result on the other 4 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for GPT-5.1 and Qwen4 Max
BenchmarkGPT-5.1Qwen4 MaxLeader
Design Arena: websites1174Not measuredOnly GPT-5.1 measured
Design Arena: UI components1150Not measuredOnly GPT-5.1 measured
Design Arena: game dev1150Not measuredOnly GPT-5.1 measured
Design Arena: data viz1199Not measuredOnly GPT-5.1 measured
Design Arena: 3D1028Not measuredOnly GPT-5.1 measured
Design Arena: all code categories1152Not measuredOnly GPT-5.1 measured
Design Arena: SVG1133Not measuredOnly GPT-5.1 measured
Design Arena: ASCII art1104Not measuredOnly GPT-5.1 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-5.1 and Qwen4 Max
BenchmarkGPT-5.1Qwen4 MaxLeader
Vals IndexNot measured63.2%Only Qwen4 Max measured
LiveBench data analysisNot measured83.4%Only Qwen4 Max measured
MedScribe (Vals AI)88.1%Not measuredOnly GPT-5.1 measured
IFBench72.9%Not measuredOnly GPT-5.1 measured
Long context reasoning (AA-LCR)80.0%Not measuredOnly GPT-5.1 measured
GDPval-AA8331809Qwen4 Max
DTBench90.1%Not measuredOnly GPT-5.1 measured
LMCA43.9%Not measuredOnly GPT-5.1 measured
CL-bench23.7%Not measuredOnly GPT-5.1 measured
CL-bench Life17.3%Not measuredOnly GPT-5.1 measured
LMArena Text1443Not measuredOnly GPT-5.1 measured
LMArena Text: instruction following1442Not measuredOnly GPT-5.1 measured
LMArena Text: creative writing1427Not measuredOnly GPT-5.1 measured
LMArena Vision1249Not measuredOnly GPT-5.1 measured
LMArena Text: English1451Not measuredOnly GPT-5.1 measured
LMArena Text: non-English1431Not measuredOnly GPT-5.1 measured
LMArena Text: Chinese1495Not measuredOnly GPT-5.1 measured
LMArena Text: German1438Not measuredOnly GPT-5.1 measured
LMArena Text: Japanese1455Not measuredOnly GPT-5.1 measured
LMArena Text: Korean1399Not measuredOnly GPT-5.1 measured
LMArena Text: French1450Not measuredOnly GPT-5.1 measured
LMArena Text: Spanish1433Not measuredOnly GPT-5.1 measured
LMArena Text: Russian1435Not measuredOnly GPT-5.1 measured
LMArena Text: Polish1440Not measuredOnly GPT-5.1 measured
LMArena Text: multi-turn1450Not measuredOnly GPT-5.1 measured
LMArena Text: longer queries1447Not measuredOnly GPT-5.1 measured
LMArena Text: writing and language1428Not measuredOnly GPT-5.1 measured
LMArena Text: entertainment and media1415Not measuredOnly GPT-5.1 measured
LMArena Vision: English1251Not measuredOnly GPT-5.1 measured
LMArena Vision: Chinese1270Not measuredOnly GPT-5.1 measured
LMArena Vision: reading text1254Not measuredOnly GPT-5.1 measured
LMArena Vision: humor1263Not measuredOnly GPT-5.1 measured
LMArena Vision: captioning1252Not measuredOnly GPT-5.1 measured
LMArena Vision: recognizing things1232Not measuredOnly GPT-5.1 measured
LMArena Vision: creative writing1267Not measuredOnly GPT-5.1 measured
LMArena Document1403Not measuredOnly GPT-5.1 measured
MultiChallenge63.4%Not measuredOnly GPT-5.1 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-5.1 and Qwen4 Max
BenchmarkGPT-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

GPT-5.1$0.0063Fits in one request
Qwen4 Max$0.0036Fits in one request

Qwen4 Max costs less

Repository review

50K input + 3K output tokens

GPT-5.1$0.092Fits in one request
Qwen4 Max$0.084Fits in one request

Qwen4 Max costs less

Agent loop

200K input + 10K output tokens

GPT-5.1$0.350Fits 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-5.1 and Qwen4 Max
SpecificationOpenAI GPT-5.1Qwen4 Max
MakerOpenAIQwen
WeightsNo public weights listedNo public weights listed
ReleasedNovember 13, 2025November 16, 2026
Context window400K1M
Input $/Mtok$1.25$1.425
Output $/Mtok$10.00$4.275
Coding index40.574.0
Independent measurements behind it34
Cost per solved task$1.02Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5.1 better than Qwen4 Max for coding?

Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 40.5 for GPT-5.1. GPT-5.1 is neither cheaper nor larger in context, and leads no benchmark both models were measured on.

Which is cheaper, GPT-5.1 or Qwen4 Max?

GPT-5.1 costs $1.25 per million input tokens and $10.00 per million output tokens; Qwen4 Max costs $1.425 and $4.275. Cost per solved task is known for GPT-5.1 only.

Which has the bigger context window, GPT-5.1 or Qwen4 Max?

Qwen4 Max, with 1M tokens against 400K.

How many benchmarks is the GPT-5.1 vs Qwen4 Max comparison based on?

6 benchmarks have a result for both models as of November 22, 2026. GPT-5.1'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-5-1-vs-qwen4-max" title="GPT-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/gpt-5-1-vs-qwen4-max">LLMBenchmark.ai, GPT-5.1 vs Qwen4 Max</a></p>