Enter opens the highlighted result. Esc closes.

GPT-5 Mini vs Qwen4 Max

Qwen4 Max leads GPT-5 Mini on coding, 74.0 to 34.2 on the Vibe Coding Index, and GPT-5 Mini costs 2.1x less per output token ($2.00 vs $4.275 per million). Updated November 22, 2026; 3 benchmarks have a result for both.

GPT-5 MiniOpenAI
Coding
34.2
Overall
46.7
Output $/M
$2.00
0
Qwen4 MaxQwen
Coding
74.0
Overall
66.6
Output $/M
$4.275
3
vs boards won of 3 shared

GPT-5 Mini or Qwen4 Max: which to pick

Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 34.2 for GPT-5 Mini.

Pick GPT-5 Mini for output tokens 2.1x cheaper ($2.00 vs $4.275 per million).

Shared results
3
GPT-5 Mini only
98
Qwen4 Max only
23
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 Mini 34.2 from 2 benchmarks, Qwen4 Max 74.0 from 4 benchmarks.
Widest category
General, 84.1 points apart on average over 1 shared benchmark.
Widest single gap
GDPval-AA: GPT-5 Mini 773 against Qwen4 Max 1809, 84.1 points apart on a 0 to 100 scale.
Output price
GPT-5 Mini $2.00 against Qwen4 Max $4.275 per million output tokens, 2.1x apart.
Context window
GPT-5 Mini 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 MiniBarsQwen4 MaxTies
Coding02
General01
All shared boards03
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
Coding benchmarks for GPT-5 Mini and Qwen4 Max
BenchmarkGPT-5 MiniQwen4 MaxLeader
SWE-bench Verified59.8%Not measuredOnly GPT-5 Mini measured
SWE-bench Multilingual39.7%Not measuredOnly GPT-5 Mini measured
LiveBench codingNot measured69.8%Only Qwen4 Max measured
LMArena WebDevNot measured1751Only Qwen4 Max measured
LiveCodeBench (Vals AI)86.6%Not measuredOnly GPT-5 Mini measured
SWE-bench Verified (Vals AI)60.8%Not measuredOnly GPT-5 Mini measured
Terminal-Bench 4 (Vals AI)Not measured48.5%Only Qwen4 Max measured
Vibe Code Bench (Vals AI)14.2%86.7%Qwen4 Max
LiveCodeBench (Artificial Analysis run)83.8%Not measuredOnly GPT-5 Mini measured
SciCode39.0%Not measuredOnly GPT-5 Mini measured
Terminal-Bench Hard (Artificial Analysis run)33.3%Not measuredOnly GPT-5 Mini measured
Terminal-Bench 4.0 (Artificial Analysis run)0.0%48.5%Qwen4 Max
FrontierCode 2.0Not measured26.5%Only Qwen4 Max measured
Terminal-Bench34.8%Not measuredOnly GPT-5 Mini measured
WeirdML52.7%Not measuredOnly GPT-5 Mini measured
ALE-BenchNot measured1831.0Only Qwen4 Max measured
LMArena Text: coding1406Not measuredOnly GPT-5 Mini measured
LMArena Text: software and IT1394Not measuredOnly GPT-5 Mini measured
LMArena WebDev: ReactNot measured1785Only Qwen4 Max measured
LMArena WebDev: HTMLNot measured1752Only Qwen4 Max measured
LMArena WebDev: from an imageNot measured1675Only Qwen4 Max measured
GameBench 2Not measured82.4Only Qwen4 Max measured
Terminal-Bench 2.034.8%Not measuredOnly GPT-5 Mini measured
ProgramBench0.0%Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 28 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for GPT-5 Mini and Qwen4 Max
BenchmarkGPT-5 MiniQwen4 MaxLeader
AA Intelligence IndexNot measured42.9Only Qwen4 Max measured
Epoch Capabilities Index146.0Not measuredOnly GPT-5 Mini measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Agentic work benchmarks for GPT-5 Mini and Qwen4 Max
BenchmarkGPT-5 MiniQwen4 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 Telecom71.1%Not measuredOnly GPT-5 Mini measured
Vending-Bench 2-$31Not measuredOnly GPT-5 Mini measured
Berkeley Function Calling Leaderboard (BFCL)55.5%Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 35 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index19 boards, none shared
Reasoning benchmarks for GPT-5 Mini and Qwen4 Max
BenchmarkGPT-5 MiniQwen4 MaxLeader
GPQA Diamond80.3%Not measuredOnly GPT-5 Mini measured
LiveBench reasoningNot measured92.2%Only Qwen4 Max measured
MMMU Pro (Vals AI)78.9%Not measuredOnly GPT-5 Mini measured
GPQA Diamond (Artificial Analysis run)82.8%Not measuredOnly GPT-5 Mini measured
Humanity's Last Exam (Artificial Analysis run)21.5%Not measuredOnly GPT-5 Mini 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)75.0%Not measuredOnly GPT-5 Mini measured
ARC-AGI54.3%Not measuredOnly GPT-5 Mini measured
ARC-AGI-24.4%Not measuredOnly GPT-5 Mini measured
Chess puzzles24.0%Not measuredOnly GPT-5 Mini measured
Mystery game puzzles10.0%Not measuredOnly GPT-5 Mini measured
VPCT40.2%Not measuredOnly GPT-5 Mini measured
LMArena Text: hard prompts1380Not measuredOnly GPT-5 Mini measured
LMArena Text: expert1379Not measuredOnly GPT-5 Mini measured
LMArena Text: hard prompts in English1384Not measuredOnly GPT-5 Mini measured
LMArena Vision: diagrams1202Not measuredOnly GPT-5 Mini measured
LMArena Vision: homework1212Not measuredOnly GPT-5 Mini measured
Kagi LLM Benchmark70.3%Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 7 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
Math benchmarks for GPT-5 Mini and Qwen4 Max
BenchmarkGPT-5 MiniQwen4 MaxLeader
AIME91.5%Not measuredOnly GPT-5 Mini measured
MATH 500 (Vals AI)94.8%Not measuredOnly GPT-5 Mini measured
MGSM (Vals AI)92.6%Not measuredOnly GPT-5 Mini measured
AIME 2025 (Artificial Analysis run)90.7%Not measuredOnly GPT-5 Mini measured
OTIS Mock AIME86.7%Not measuredOnly GPT-5 Mini measured
FrontierMath, tiers 1 to 346.7%Not measuredOnly GPT-5 Mini measured
FrontierMath, tier 412.2%Not measuredOnly GPT-5 Mini measured
ProofBench9.0%Not measuredOnly GPT-5 Mini measured
MATH level 597.8%Not measuredOnly GPT-5 Mini measured
LMArena Text: math1378Not measuredOnly GPT-5 Mini measured
LMArena Text: mathematical work1381Not measuredOnly GPT-5 Mini measured
MathArena13.5%Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 2 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index14 boards, none shared
Knowledge benchmarks for GPT-5 Mini and Qwen4 Max
BenchmarkGPT-5 MiniQwen4 MaxLeader
MMLU Pro82.2%Not measuredOnly GPT-5 Mini measured
LegalBench (Vals AI)81.8%Not measuredOnly GPT-5 Mini measured
CaseLaw (Vals AI)68.5%Not measuredOnly GPT-5 Mini measured
CorpFin (Vals AI)60.2%Not measuredOnly GPT-5 Mini measured
TaxEval (Vals AI)75.2%Not measuredOnly GPT-5 Mini measured
MortgageTax (Vals AI)66.9%Not measuredOnly GPT-5 Mini measured
MedQA (Vals AI)96.1%Not measuredOnly GPT-5 Mini measured
MedCode (Vals AI)43.0%Not measuredOnly GPT-5 Mini measured
AA-OmniscienceNot measured27.7Only Qwen4 Max measured
SimpleQA Verified21.6%Not measuredOnly GPT-5 Mini measured
LMArena Text: science1370Not measuredOnly GPT-5 Mini measured
LMArena Text: medicine and healthcare1380Not measuredOnly GPT-5 Mini measured
LMArena Text: legal and government1375Not measuredOnly GPT-5 Mini measured
LMArena Text: business and finance1358Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for GPT-5 Mini and Qwen4 Max
BenchmarkGPT-5 MiniQwen4 MaxLeader
Design Arena: websites1112Not measuredOnly GPT-5 Mini measured
Design Arena: UI components1089Not measuredOnly GPT-5 Mini measured
Design Arena: game dev1101Not measuredOnly GPT-5 Mini measured
Design Arena: data viz1125Not measuredOnly GPT-5 Mini measured
Design Arena: 3D1004Not measuredOnly GPT-5 Mini measured
Design Arena: all code categories1096Not measuredOnly GPT-5 Mini measured
Design Arena: SVG1075Not measuredOnly GPT-5 Mini measured
Design Arena: ASCII art1110Not measuredOnly GPT-5 Mini 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 Mini and Qwen4 Max
BenchmarkGPT-5 MiniQwen4 MaxLeader
Vals IndexNot measured63.2%Only Qwen4 Max measured
LiveBench data analysisNot measured83.4%Only Qwen4 Max measured
MedScribe (Vals AI)80.6%Not measuredOnly GPT-5 Mini measured
IFBench75.4%Not measuredOnly GPT-5 Mini measured
Long context reasoning (AA-LCR)72.3%Not measuredOnly GPT-5 Mini measured
GDPval-AA7731809Qwen4 Max
DTBench80.5%Not measuredOnly GPT-5 Mini measured
LMCA34.2%Not measuredOnly GPT-5 Mini measured
Fiction.LiveBench69.4%Not measuredOnly GPT-5 Mini measured
LMArena Text1374Not measuredOnly GPT-5 Mini measured
LMArena Text: instruction following1357Not measuredOnly GPT-5 Mini measured
LMArena Text: creative writing1325Not measuredOnly GPT-5 Mini measured
LMArena Vision1203Not measuredOnly GPT-5 Mini measured
LMArena Text: English1379Not measuredOnly GPT-5 Mini measured
LMArena Text: non-English1363Not measuredOnly GPT-5 Mini measured
LMArena Text: Chinese1386Not measuredOnly GPT-5 Mini measured
LMArena Text: German1365Not measuredOnly GPT-5 Mini measured
LMArena Text: Japanese1341Not measuredOnly GPT-5 Mini measured
LMArena Text: Korean1304Not measuredOnly GPT-5 Mini measured
LMArena Text: French1386Not measuredOnly GPT-5 Mini measured
LMArena Text: Spanish1355Not measuredOnly GPT-5 Mini measured
LMArena Text: Russian1362Not measuredOnly GPT-5 Mini measured
LMArena Text: Polish1378Not measuredOnly GPT-5 Mini measured
LMArena Text: multi-turn1363Not measuredOnly GPT-5 Mini measured
LMArena Text: longer queries1355Not measuredOnly GPT-5 Mini measured
LMArena Text: writing and language1345Not measuredOnly GPT-5 Mini measured
LMArena Text: entertainment and media1340Not measuredOnly GPT-5 Mini measured
LMArena Vision: English1216Not measuredOnly GPT-5 Mini measured
LMArena Vision: Chinese1214Not measuredOnly GPT-5 Mini measured
LMArena Vision: reading text1199Not measuredOnly GPT-5 Mini measured
LMArena Vision: humor1205Not measuredOnly GPT-5 Mini measured
LMArena Vision: captioning1216Not measuredOnly GPT-5 Mini measured
LMArena Vision: recognizing things1226Not measuredOnly GPT-5 Mini measured
LMArena Vision: creative writing1182Not measuredOnly GPT-5 Mini measured
MultiChallenge59.0%Not measuredOnly GPT-5 Mini measured
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-5 Mini and Qwen4 Max
BenchmarkGPT-5 MiniQwen4 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 Mini$0.0013Fits in one request
Qwen4 Max$0.0036Fits in one request

GPT-5 Mini costs less

Repository review

50K input + 3K output tokens

GPT-5 Mini$0.018Fits in one request
Qwen4 Max$0.084Fits in one request

GPT-5 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-5 Mini$0.070Fits in one request
Qwen4 Max$0.328Fits in one request

GPT-5 Mini 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 Mini and Qwen4 Max
SpecificationOpenAI GPT-5 MiniQwen4 Max
MakerOpenAIQwen
WeightsNo public weights listedNo public weights listed
ReleasedAugust 7, 2025November 16, 2026
Context window400K1M
Input $/Mtok$0.25$1.425
Output $/Mtok$2.00$4.275
Coding index34.274.0
Independent measurements behind it24
Cost per solved task$0.08Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-5 Mini better than Qwen4 Max for coding?

Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 34.2 for GPT-5 Mini. Pick GPT-5 Mini for output tokens 2.1x cheaper ($2.00 vs $4.275 per million).

Which is cheaper, GPT-5 Mini or Qwen4 Max?

GPT-5 Mini costs $0.25 per million input tokens and $2.00 per million output tokens; Qwen4 Max costs $1.425 and $4.275. Cost per solved task is known for GPT-5 Mini only.

Which has the bigger context window, GPT-5 Mini or Qwen4 Max?

Qwen4 Max, with 1M tokens against 400K.

How many benchmarks is the GPT-5 Mini vs Qwen4 Max comparison based on?

3 benchmarks have a result for both models as of November 22, 2026. GPT-5 Mini's coding index rests on 2 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-mini-vs-qwen4-max" title="GPT-5 Mini 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-mini-vs-qwen4-max">LLMBenchmark.ai, GPT-5 Mini vs Qwen4 Max</a></p>