Enter opens the highlighted result. Esc closes.

GLM 5.2 vs Qwen4 Max

Qwen4 Max leads GLM 5.2 on coding, 74.0 to 61.1 on the Vibe Coding Index, at about the same output price ($4.275 vs $4.40 per million). Updated November 22, 2026; 11 benchmarks have a result for both.

GLM 5.2Z.ai
Coding
61.1
Overall
65.6
Output $/M
$4.40
0
Qwen4 MaxQwen
Coding
74.0
Overall
66.6
Output $/M
$4.275
11
vs boards won of 11 shared

GLM 5.2 or Qwen4 Max: which to pick

Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 61.1 for GLM 5.2.

Pick GLM 5.2 for a larger context window (1.05M against 1M tokens).

Shared results
11
GLM 5.2 only
101
Qwen4 Max only
15
Like-for-like categories
5 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
GLM 5.2 61.1 from 4 benchmarks, Qwen4 Max 74.0 from 4 benchmarks.
Widest category
General, 35.7 points apart on average over 1 shared benchmark.
Widest single gap
Terminal-Bench 4.0 (Artificial Analysis run): GLM 5.2 1.0% against Qwen4 Max 48.5%, 47.5 points apart on a 0 to 100 scale.
Output price
GLM 5.2 $4.40 against Qwen4 Max $4.275 per million output tokens, 1.0x apart.
Context window
GLM 5.2 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
CategoryGLM 5.2BarsQwen4 MaxTies
Coding07
Agentic work01
Reasoning01
Knowledge01
General01
All shared boards011
CodingLike-for-likeSix of these boards feed the Vibe Coding Index07
Coding benchmarks for GLM 5.2 and Qwen4 Max
BenchmarkGLM 5.2Qwen4 MaxLeader
LiveBench codingNot measured69.8%Only Qwen4 Max measured
LMArena WebDev16081751Qwen4 Max
LiveCodeBench (Vals AI)69.5%Not measuredOnly GLM 5.2 measured
SWE-bench Verified (Vals AI)82.8%Not measuredOnly GLM 5.2 measured
Terminal-Bench 4 (Vals AI)Not measured48.5%Only Qwen4 Max measured
Vibe Code Bench (Vals AI)64.0%86.7%Qwen4 Max
Code migration (Vals AI)37.9%Not measuredOnly GLM 5.2 measured
ProgramBench (Vals AI)0.5%Not measuredOnly GLM 5.2 measured
Terminal-Bench 2.1 (Vals AI)67.8%Not measuredOnly GLM 5.2 measured
SkillsBench (Vals AI)45.1%Not measuredOnly GLM 5.2 measured
SciCode51.2%Not measuredOnly GLM 5.2 measured
Terminal-Bench Hard (Artificial Analysis run)50.8%Not measuredOnly GLM 5.2 measured
Terminal-Bench 4.0 (Artificial Analysis run)1.0%48.5%Qwen4 Max
FrontierCode 2.0Not measured26.5%Only Qwen4 Max measured
FrontierCode24.5%Not measuredOnly GLM 5.2 measured
WeirdML70.1%Not measuredOnly GLM 5.2 measured
MirrorCode36.7%Not measuredOnly GLM 5.2 measured
ALE-Bench1047.01831.0Qwen4 Max
LMArena Text: coding1488Not measuredOnly GLM 5.2 measured
LMArena Text: software and IT1487Not measuredOnly GLM 5.2 measured
LMArena WebDev: React16211785Qwen4 Max
LMArena WebDev: HTML15671752Qwen4 Max
LMArena WebDev: from an imageNot measured1675Only Qwen4 Max measured
SWE Atlas: Codebase QnA48.1%Not measuredOnly GLM 5.2 measured
SWE Atlas: Refactoring42.4%Not measuredOnly GLM 5.2 measured
SWE Atlas: Test Writing41.5%Not measuredOnly GLM 5.2 measured
GameBench 249.982.4Qwen4 Max
Terminal-Bench 3.04.6%Not measuredOnly GLM 5.2 measured
ProgramBench0.0%Not measuredOnly GLM 5.2 measured
Neither model has a result on the other 23 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for GLM 5.2 and Qwen4 Max
BenchmarkGLM 5.2Qwen4 MaxLeader
AA Intelligence IndexNot measured42.9Only Qwen4 Max measured
Epoch Capabilities Index153.1Not measuredOnly GLM 5.2 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GLM 5.2 and Qwen4 Max
BenchmarkGLM 5.2Qwen4 MaxLeader
Design Arena: agents building web apps1191Not measuredOnly GLM 5.2 measured
Design Arena: agents building full-stack apps1218Not measuredOnly GLM 5.2 measured
Design Arena: agents building mobile apps1154Not measuredOnly GLM 5.2 measured
Design Arena: agents building Android apps1168Not measuredOnly GLM 5.2 measured
Design Arena: agents building Godot games1142Not measuredOnly GLM 5.2 measured
Design Arena: agents building games1156Not measuredOnly GLM 5.2 measured
Design Arena: HTML slides1075Not measuredOnly GLM 5.2 measured
Design Arena: PowerPoint slides1160Not measuredOnly GLM 5.2 measured
Design Arena: spreadsheets1027Not measuredOnly GLM 5.2 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
SREBench (Vals AI)0.0%Not measuredOnly GLM 5.2 measured
Finance Agent (Vals AI)49.7%Not measuredOnly GLM 5.2 measured
Tax Agent Bench (Vals AI)Not measured40.4%Only Qwen4 Max measured
Legal Research Bench (Vals AI)31.3%41.4%Qwen4 Max
Harvey's Legal Agent Benchmark (Vals AI)Not measured21.3%Only Qwen4 Max measured
Excel Modeling Benchmark (Vals AI)61.5%Not measuredOnly GLM 5.2 measured
τ²-Bench Telecom99.1%Not measuredOnly GLM 5.2 measured
APEX-Agents45.2%Not measuredOnly GLM 5.2 measured
PostTrainBench30.4%Not measuredOnly GLM 5.2 measured
Vending-Bench 2$8,314Not measuredOnly GLM 5.2 measured
MCP Atlas77.8%Not measuredOnly GLM 5.2 measured
Toolathlon-Verified59.9%Not measuredOnly GLM 5.2 measured
τ³-Banking37.1%Not measuredOnly GLM 5.2 measured
Neither model has a result on the other 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
Reasoning benchmarks for GLM 5.2 and Qwen4 Max
BenchmarkGLM 5.2Qwen4 MaxLeader
GPQA Diamond85.6%Not measuredOnly GLM 5.2 measured
LiveBench reasoningNot measured92.2%Only Qwen4 Max measured
GPQA Diamond (Artificial Analysis run)89.5%Not measuredOnly GLM 5.2 measured
Humanity's Last Exam (Artificial Analysis run)41.1%Not measuredOnly GLM 5.2 measured
HLE-Diamond (Artificial Analysis run)17.7%44.9%Qwen4 Max
CritPt v2, hard subset (Artificial Analysis run)Not measured43.0%Only Qwen4 Max measured
GPQA Diamond (Epoch AI run)91.9%Not measuredOnly GLM 5.2 measured
ARC-AGI77.0%Not measuredOnly GLM 5.2 measured
ARC-AGI-222.8%Not measuredOnly GLM 5.2 measured
SimpleBench58.8%Not measuredOnly GLM 5.2 measured
Chess puzzles22.0%Not measuredOnly GLM 5.2 measured
Mystery game puzzles19.0%Not measuredOnly GLM 5.2 measured
EBR-bench9.5%Not measuredOnly GLM 5.2 measured
LMArena Text: hard prompts1481Not measuredOnly GLM 5.2 measured
LMArena Text: expert1489Not measuredOnly GLM 5.2 measured
LMArena Text: hard prompts in English1481Not measuredOnly GLM 5.2 measured
Kagi LLM Benchmark62.6%Not measuredOnly GLM 5.2 measured
Neither model has a result on the other 9 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Math benchmarks for GLM 5.2 and Qwen4 Max
BenchmarkGLM 5.2Qwen4 MaxLeader
OTIS Mock AIME86.4%Not measuredOnly GLM 5.2 measured
FrontierMath, tiers 1 to 359.2%Not measuredOnly GLM 5.2 measured
FrontierMath, tier 429.3%Not measuredOnly GLM 5.2 measured
ProofBench35.0%Not measuredOnly GLM 5.2 measured
LMArena Text: math1484Not measuredOnly GLM 5.2 measured
LMArena Text: mathematical work1490Not measuredOnly GLM 5.2 measured
MathArena20.4%Not measuredOnly GLM 5.2 measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
Knowledge benchmarks for GLM 5.2 and Qwen4 Max
BenchmarkGLM 5.2Qwen4 MaxLeader
MMLU Pro86.7%Not measuredOnly GLM 5.2 measured
LegalBench (Vals AI)84.1%Not measuredOnly GLM 5.2 measured
CorpFin (Vals AI)66.1%Not measuredOnly GLM 5.2 measured
TaxEval (Vals AI)73.3%Not measuredOnly GLM 5.2 measured
MedCode (Vals AI)40.8%Not measuredOnly GLM 5.2 measured
AA-Omniscience0.627.7Qwen4 Max
SimpleQA Verified34.2%Not measuredOnly GLM 5.2 measured
LMArena Text: science1489Not measuredOnly GLM 5.2 measured
LMArena Text: medicine and healthcare1476Not measuredOnly GLM 5.2 measured
LMArena Text: legal and government1490Not measuredOnly GLM 5.2 measured
LMArena Text: business and finance1450Not measuredOnly GLM 5.2 measured
Neither model has a result on the other 10 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for GLM 5.2 and Qwen4 Max
BenchmarkGLM 5.2Qwen4 MaxLeader
Design Arena: websites1272Not measuredOnly GLM 5.2 measured
Design Arena: UI components1279Not measuredOnly GLM 5.2 measured
Design Arena: game dev1239Not measuredOnly GLM 5.2 measured
Design Arena: data viz1279Not measuredOnly GLM 5.2 measured
Design Arena: 3D1252Not measuredOnly GLM 5.2 measured
Design Arena: all code categories1268Not measuredOnly GLM 5.2 measured
Design Arena: SVG1189Not measuredOnly GLM 5.2 measured
Design Arena: ASCII art1175Not measuredOnly GLM 5.2 measured
LiveBench designNot measured79.1%Only Qwen4 Max measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
General benchmarks for GLM 5.2 and Qwen4 Max
BenchmarkGLM 5.2Qwen4 MaxLeader
Vals IndexNot measured63.2%Only Qwen4 Max measured
LiveBench data analysisNot measured83.4%Only Qwen4 Max measured
MedScribe (Vals AI)83.5%Not measuredOnly GLM 5.2 measured
IFBench73.3%Not measuredOnly GLM 5.2 measured
Long context reasoning (AA-LCR)78.3%Not measuredOnly GLM 5.2 measured
GDPval-AA13801809Qwen4 Max
DTBench93.6%Not measuredOnly GLM 5.2 measured
LMCA45.8%Not measuredOnly GLM 5.2 measured
Surface Evolver Bench55.6%Not measuredOnly GLM 5.2 measured
LMArena Text1469Not measuredOnly GLM 5.2 measured
LMArena Text: instruction following1467Not measuredOnly GLM 5.2 measured
LMArena Text: creative writing1460Not measuredOnly GLM 5.2 measured
LMArena Text: English1475Not measuredOnly GLM 5.2 measured
LMArena Text: non-English1458Not measuredOnly GLM 5.2 measured
LMArena Text: Chinese1523Not measuredOnly GLM 5.2 measured
LMArena Text: German1467Not measuredOnly GLM 5.2 measured
LMArena Text: Japanese1453Not measuredOnly GLM 5.2 measured
LMArena Text: Korean1429Not measuredOnly GLM 5.2 measured
LMArena Text: French1476Not measuredOnly GLM 5.2 measured
LMArena Text: Spanish1482Not measuredOnly GLM 5.2 measured
LMArena Text: Russian1466Not measuredOnly GLM 5.2 measured
LMArena Text: Polish1459Not measuredOnly GLM 5.2 measured
LMArena Text: multi-turn1470Not measuredOnly GLM 5.2 measured
LMArena Text: longer queries1479Not measuredOnly GLM 5.2 measured
LMArena Text: writing and language1461Not measuredOnly GLM 5.2 measured
LMArena Text: entertainment and media1448Not measuredOnly GLM 5.2 measured
EQ-Bench 41208Not measuredOnly GLM 5.2 measured
Neither model has a result on the other 22 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 5.2 and Qwen4 Max
BenchmarkGLM 5.2Qwen4 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

GLM 5.2$0.0036Fits in one request
Qwen4 Max$0.0036Fits in one request

Qwen4 Max costs less

Repository review

50K input + 3K output tokens

GLM 5.2$0.083Fits in one request
Qwen4 Max$0.084Fits in one request

GLM 5.2 costs less

Agent loop

200K input + 10K output tokens

GLM 5.2$0.324Fits in one request
Qwen4 Max$0.328Fits in one request

GLM 5.2 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 GLM 5.2 and Qwen4 Max
SpecificationZ.ai GLM 5.2Qwen4 Max
MakerZ.aiQwen
WeightsOpen weightsNo public weights listed
ReleasedJune 16, 2026November 16, 2026
Context window1.05M1M
Input $/Mtok$1.40$1.425
Output $/Mtok$4.40$4.275
Coding index61.174.0
Independent measurements behind it44
Cost per solved task$0.86Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 5.2 better than Qwen4 Max for coding?

Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 61.1 for GLM 5.2. Pick GLM 5.2 for a larger context window (1.05M against 1M tokens).

Which is cheaper, GLM 5.2 or Qwen4 Max?

GLM 5.2 costs $1.40 per million input tokens and $4.40 per million output tokens; Qwen4 Max costs $1.425 and $4.275. Cost per solved task is known for GLM 5.2 only.

Which has the bigger context window, GLM 5.2 or Qwen4 Max?

GLM 5.2, with 1.05M tokens against 1M.

How many benchmarks is the GLM 5.2 vs Qwen4 Max comparison based on?

11 benchmarks have a result for both models as of November 22, 2026. GLM 5.2's coding index rests on 4 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/glm-5-2-vs-qwen4-max" title="GLM 5.2 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/glm-5-2-vs-qwen4-max">LLMBenchmark.ai, GLM 5.2 vs Qwen4 Max</a></p>