Enter opens the highlighted result. Esc closes.

GLM 5.2 vs GPT-5.4

GPT-5.4 leads GLM 5.2 on coding, 64.4 to 61.1 on the Vibe Coding Index, and GLM 5.2 costs 3.4x less per output token ($4.40 vs $15.00 per million). Updated October 22, 2026; 85 benchmarks have a result for both.

Replace GLM 5.2 Replace GPT-5.4
GLM 5.2Z.ai
Coding
61.1
Overall
62.5
Output $/M
$4.40
35
GPT-5.4OpenAI
Coding
64.4
Overall
69.6
Output $/M
$15.00
49
vs boards won of 85 shared, 1 tied

GLM 5.2 or GPT-5.4: which to pick

Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 61.1 for GLM 5.2, though on 3 benchmarks against 4.

Pick GLM 5.2 for output tokens 3.4x cheaper ($4.40 vs $15.00 per million) and a lower cost per solved task ($0.86 against $1.02).

Model AGLM 5.2Z.ai61.1/1004 independent benchmarks$0.86 per solved taskModel BGPT-5.4OpenAI64.4/1003 independent benchmarks$1.02 per solved task
Shared results
85
GLM 5.2 only
13
GPT-5.4 only
25
Like-for-like categories
8 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, GPT-5.4 64.4 from 3 benchmarks.
Widest category
Agentic work, 13.6 points apart on average over 9 shared benchmarks.
Widest single gap
ARC-AGI-2: GLM 5.2 22.8% against GPT-5.4 74.0%, 51.2 points apart on a 0 to 100 scale.
Output price
GLM 5.2 $4.40 against GPT-5.4 $15.00 per million output tokens, 3.4x apart.
Context window
GLM 5.2 takes 1.05M tokens, GPT-5.4 1.05M.

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 5.2BarsGPT-5.4Ties
Coding591 tie
Intelligence02
Agentic work81
Reasoning112
Math06
Knowledge46
Web design80
General913
All shared boards35491 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index59
Coding benchmarks for GLM 5.2 and GPT-5.4
BenchmarkGLM 5.2GPT-5.4Leader
LMArena WebDev16041464GLM 5.2
AA Coding Index68.871.1GPT-5.4
LiveCodeBench (Vals AI)69.5%84.1%GPT-5.4
SWE-bench Verified (Vals AI)82.8%78.2%GLM 5.2
Vibe Code Bench (Vals AI)64.0%67.4%GPT-5.4
Code migration (Vals AI)37.9%35.0%GLM 5.2
ProgramBench (Vals AI)0.5%0.5%Tie
Terminal-Bench 2.1 (Vals AI)67.8%Not measuredOnly GLM 5.2 measured
SkillsBench (Vals AI)45.1%51.7%GPT-5.4
SciCode51.2%Not measuredOnly GLM 5.2 measured
Terminal-Bench Hard (Artificial Analysis run)50.8%57.6%GPT-5.4
Terminal-BenchNot measured81.8%Only GPT-5.4 measured
FrontierCode24.5%Not measuredOnly GLM 5.2 measured
GSO-BenchNot measured31.4%Only GPT-5.4 measured
WeirdML70.1%77.7%GPT-5.4
MirrorCodeNot measured15.6%Only GPT-5.4 measured
ALE-Bench1047.01607.0GPT-5.4
LMArena Text: coding14871496GPT-5.4
LMArena Text: software and IT14861491GPT-5.4
LMArena WebDev: React16171454GLM 5.2
LMArena WebDev: HTML15651478GLM 5.2
LMArena WebDev: from an imageNot measured1436Only GPT-5.4 measured
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GLM 5.2 and GPT-5.4
BenchmarkGLM 5.2GPT-5.4Leader
AA Intelligence Index33.739.0GPT-5.4
Epoch Capabilities Index151.9157.3GPT-5.4
Agentic workLike-for-likePublic boards, shown as published, kept out of the index81
Agentic work benchmarks for GLM 5.2 and GPT-5.4
BenchmarkGLM 5.2GPT-5.4Leader
AA Agentic Index38.4Not measuredOnly GLM 5.2 measured
Design Arena: agents building web apps12221059GLM 5.2
Design Arena: agents building full-stack apps12411017GLM 5.2
Design Arena: agents building mobile apps11591087GLM 5.2
Design Arena: agents building Android apps11781031GLM 5.2
Design Arena: agents building Godot games11421135GLM 5.2
Design Arena: agents building games1206Not measuredOnly GLM 5.2 measured
Design Arena: HTML slides1125Not measuredOnly GLM 5.2 measured
Design Arena: PowerPoint slides1170Not measuredOnly GLM 5.2 measured
SREBench (Vals AI)0.0%Not measuredOnly GLM 5.2 measured
Finance Agent (Vals AI)49.7%Not measuredOnly GLM 5.2 measured
Legal Research Bench (Vals AI)31.3%Not measuredOnly GLM 5.2 measured
Excel Modeling Benchmark (Vals AI)61.5%Not measuredOnly GLM 5.2 measured
τ²-Bench Telecom99.1%87.1%GLM 5.2
APEX-Agents45.2%52.4%GPT-5.4
METR time horizonsNot measured74.3%Only GPT-5.4 measured
DeepResearch BenchNot measured35.1%Only GPT-5.4 measured
PostTrainBench31.7%19.0%GLM 5.2
Vending-Bench 2$8,314$6,144GLM 5.2
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index112
Reasoning benchmarks for GLM 5.2 and GPT-5.4
BenchmarkGLM 5.2GPT-5.4Leader
GPQA Diamond85.6%91.7%GPT-5.4
MMMU Pro (Vals AI)Not measured87.5%Only GPT-5.4 measured
GPQA Diamond (Artificial Analysis run)89.5%92.0%GPT-5.4
Humanity's Last Exam (Artificial Analysis run)41.1%43.7%GPT-5.4
GPQA Diamond (Epoch AI run)91.9%93.3%GPT-5.4
ARC-AGI77.0%93.7%GPT-5.4
ARC-AGI-222.8%74.0%GPT-5.4
SimpleBench58.8%Not measuredOnly GLM 5.2 measured
Chess puzzles22.0%48.0%GPT-5.4
Mystery game puzzles19.0%37.0%GPT-5.4
EBR-bench9.5%25.4%GPT-5.4
LMArena Text: hard prompts14811485GPT-5.4
LMArena Text: expert14871507GPT-5.4
LMArena Text: hard prompts in English14811479GLM 5.2
LMArena Vision: diagramsNot measured1327Only GPT-5.4 measured
LMArena Vision: homeworkNot measured1336Only GPT-5.4 measured
Kagi LLM Benchmark62.6%63.8%GPT-5.4
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index06
Math benchmarks for GLM 5.2 and GPT-5.4
BenchmarkGLM 5.2GPT-5.4Leader
AIMENot measured96.7%Only GPT-5.4 measured
OTIS Mock AIME86.4%97.8%GPT-5.4
FrontierMath, tiers 1 to 359.2%78.6%GPT-5.4
FrontierMath, tier 429.3%49.0%GPT-5.4
ProofBench35.0%56.0%GPT-5.4
LMArena Text: math14831488GPT-5.4
LMArena Text: mathematical work14891497GPT-5.4
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index46
Knowledge benchmarks for GLM 5.2 and GPT-5.4
BenchmarkGLM 5.2GPT-5.4Leader
MMLU Pro86.7%87.5%GPT-5.4
LegalBench (Vals AI)84.1%86.0%GPT-5.4
CaseLaw (Vals AI)Not measured63.8%Only GPT-5.4 measured
CorpFin (Vals AI)66.1%65.3%GLM 5.2
TaxEval (Vals AI)73.3%74.0%GPT-5.4
MortgageTax (Vals AI)Not measured68.3%Only GPT-5.4 measured
MedQA (Vals AI)Not measured96.1%Only GPT-5.4 measured
MedCode (Vals AI)40.8%41.3%GPT-5.4
SimpleQA Verified34.2%45.1%GPT-5.4
LMArena Text: science14891479GLM 5.2
LMArena Text: medicine and healthcare14751458GLM 5.2
LMArena Text: legal and government14861486GLM 5.2
LMArena Text: business and finance14511474GPT-5.4
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for GLM 5.2 and GPT-5.4
BenchmarkGLM 5.2GPT-5.4Leader
Design Arena: websites12851198GLM 5.2
Design Arena: UI components12941212GLM 5.2
Design Arena: game dev12681194GLM 5.2
Design Arena: data viz12851196GLM 5.2
Design Arena: 3D12871065GLM 5.2
Design Arena: all code categories12871179GLM 5.2
Design Arena: SVG12131141GLM 5.2
Design Arena: ASCII art11911188GLM 5.2
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index913
General benchmarks for GLM 5.2 and GPT-5.4
BenchmarkGLM 5.2GPT-5.4Leader
SAGE (Vals AI)Not measured43.3%Only GPT-5.4 measured
MedScribe (Vals AI)83.5%77.5%GLM 5.2
IFBench73.3%73.9%GPT-5.4
Long context reasoning (AA-LCR)78.3%82.0%GPT-5.4
DTBench93.6%94.4%GPT-5.4
LMCA45.8%52.0%GPT-5.4
CL-benchNot measured27.9%Only GPT-5.4 measured
Surface Evolver Bench55.6%Not measuredOnly GLM 5.2 measured
Furniture assemblyNot measured37.5%Only GPT-5.4 measured
CL-bench LifeNot measured21.7%Only GPT-5.4 measured
LMArena Text14701469GLM 5.2
LMArena Text: instruction following14661469GPT-5.4
LMArena Text: creative writing14631439GLM 5.2
LMArena VisionNot measured1303Only GPT-5.4 measured
LMArena Text: English14751467GLM 5.2
LMArena Text: non-English14591465GPT-5.4
LMArena Text: Chinese15221520GLM 5.2
LMArena Text: German14701472GPT-5.4
LMArena Text: Japanese14501485GPT-5.4
LMArena Text: Korean14401449GPT-5.4
LMArena Text: French14791493GPT-5.4
LMArena Text: Spanish14781452GLM 5.2
LMArena Text: Russian14681480GPT-5.4
LMArena Text: Polish14561472GPT-5.4
LMArena Text: multi-turn14691482GPT-5.4
LMArena Text: longer queries14801473GLM 5.2
LMArena Text: writing and language14631458GLM 5.2
LMArena Text: entertainment and media14501438GLM 5.2
LMArena Vision: EnglishNot measured1301Only GPT-5.4 measured
LMArena Vision: ChineseNot measured1354Only GPT-5.4 measured
LMArena Vision: reading textNot measured1312Only GPT-5.4 measured
LMArena Vision: humorNot measured1284Only GPT-5.4 measured
LMArena Vision: recognizing thingsNot measured1251Only GPT-5.4 measured
LMArena Vision: creative writingNot measured1283Only GPT-5.4 measured
LMArena DocumentNot measured1471Only GPT-5.4 measured
Neither model has a result on the other 11 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 GPT-5.4
BenchmarkGLM 5.2GPT-5.4Leader
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
GPT-5.4$0.010Fits in one request

GLM 5.2 costs less

Repository review

50K input + 3K output tokens

GLM 5.2$0.083Fits in one request
GPT-5.4$0.170Fits in one request

GLM 5.2 costs less

Agent loop

200K input + 10K output tokens

GLM 5.2$0.324Fits in one request
GPT-5.4$0.650Fits 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 GPT-5.4
SpecificationZ.ai GLM 5.2OpenAI GPT-5.4
MakerZ.aiOpenAI
WeightsOpen weightsNo public weights listed
ReleasedJune 16, 2026March 5, 2026
Context window1.05M1.05M
Input $/Mtok$1.40$2.50
Output $/Mtok$4.40$15.00
Coding index61.164.4
Independent measurements behind it43
Cost per solved task$0.86$1.02
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 5.2 better than GPT-5.4 for coding?

Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 61.1 for GLM 5.2, though on 3 benchmarks against 4. Pick GLM 5.2 for output tokens 3.4x cheaper ($4.40 vs $15.00 per million) and a lower cost per solved task ($0.86 against $1.02).

Which is cheaper, GLM 5.2 or GPT-5.4?

GLM 5.2 costs $1.40 per million input tokens and $4.40 per million output tokens; GPT-5.4 costs $2.50 and $15.00. Per solved SWE-bench Verified task, GLM 5.2 costs $0.86 and GPT-5.4 $1.02.

Which has the bigger context window, GLM 5.2 or GPT-5.4?

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

How many benchmarks is the GLM 5.2 vs GPT-5.4 comparison based on?

85 benchmarks have a result for both models as of October 22, 2026. GLM 5.2's coding index rests on 4 independent benchmarks and GPT-5.4's on 3. 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-gpt-5-4" title="GLM 5.2 vs GPT-5.4, 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-gpt-5-4">LLMBenchmark.ai, GLM 5.2 vs GPT-5.4</a></p>