Enter opens the highlighted result. Esc closes.

GLM 5 vs GPT-5.2

GPT-5.2 leads GLM 5 on coding, 55.9 to 41.7 on the Vibe Coding Index, and GLM 5 costs 4.4x less per output token ($3.20 vs $14.00 per million). Updated October 22, 2026; 74 benchmarks have a result for both.

Replace GLM 5 Replace GPT-5.2
GLM 5Z.ai
Coding
41.7
Overall
54.3
Output $/M
$3.20
48
GPT-5.2OpenAI
Coding
55.9
Overall
60.7
Output $/M
$14.00
25
vs boards won of 74 shared, 1 tied

GLM 5 or GPT-5.2: which to pick

Pick GPT-5.2 for coding: it scores 55.9 on the Vibe Coding Index against 41.7 for GLM 5.

Pick GLM 5 for output tokens 4.4x cheaper ($3.20 vs $14.00 per million) and a lower cost per solved task ($0.63 against $1.91).

Model AGLM 5Z.ai41.7/1003 independent benchmarks$0.63 per solved taskModel BGPT-5.2OpenAI55.9/1003 independent benchmarks$1.91 per solved task
Shared results
74
GLM 5 only
2
GPT-5.2 only
40
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 41.7 from 3 benchmarks, GPT-5.2 55.9 from 3 benchmarks.
Widest category
Reasoning, 12.5 points apart on average over 11 shared benchmarks.
Widest single gap
ARC-AGI-2: GLM 5 4.9% against GPT-5.2 52.9%, 48.1 points apart on a 0 to 100 scale.
Output price
GLM 5 $3.20 against GPT-5.2 $14.00 per million output tokens, 4.4x apart.
Context window
GLM 5 takes 205K tokens, GPT-5.2 400K.

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 5BarsGPT-5.2Ties
Coding571 tie
Intelligence02
Agentic work60
Reasoning56
Math22
Knowledge64
Web design71
General173
All shared boards48251 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index57
Coding benchmarks for GLM 5 and GPT-5.2
BenchmarkGLM 5GPT-5.2Leader
SWE-bench Verified72.8%72.8%Tie
SWE-bench Multilingual69.7%66.7%GLM 5
LMArena WebDev14351417GLM 5
LiveCodeBench (Vals AI)81.9%85.4%GPT-5.2
SWE-bench Verified (Vals AI)71.4%75.8%GPT-5.2
Vibe Code Bench (Vals AI)23.4%53.5%GPT-5.2
LiveCodeBench (Artificial Analysis run)Not measured89.4%Only GPT-5.2 measured
Terminal-Bench Hard (Artificial Analysis run)43.2%47.0%GPT-5.2
Terminal-Bench52.4%64.9%GPT-5.2
GSO-BenchNot measured27.5%Only GPT-5.2 measured
WeirdML48.2%72.2%GPT-5.2
ALE-Bench765.61293.5GPT-5.2
LMArena Text: coding14611442GLM 5
LMArena Text: software and IT14601434GLM 5
LMArena WebDev: React1424Not measuredOnly GLM 5 measured
LMArena WebDev: HTML14501427GLM 5
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GLM 5 and GPT-5.2
BenchmarkGLM 5GPT-5.2Leader
AA Intelligence Index27.930.4GPT-5.2
Epoch Capabilities Index145.8153.7GPT-5.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
Agentic work benchmarks for GLM 5 and GPT-5.2
BenchmarkGLM 5GPT-5.2Leader
Design Arena: agents building web appsNot measured1086Only GPT-5.2 measured
Design Arena: agents building full-stack apps11231043GLM 5
Design Arena: agents building mobile apps11361093GLM 5
Design Arena: agents building Android apps11471059GLM 5
Design Arena: agents building Godot games11441142GLM 5
Design Arena: HTML slides1098Not measuredOnly GLM 5 measured
τ²-Bench Telecom98.2%84.8%GLM 5
METR time horizonsNot measured75.3%Only GPT-5.2 measured
Remote Labor IndexNot measured2.5%Only GPT-5.2 measured
GDPvalNot measured49.7%Only GPT-5.2 measured
DeepResearch BenchNot measured41.1%Only GPT-5.2 measured
Vending-Bench 2$4,432$3,591GLM 5
Berkeley Function Calling Leaderboard (BFCL)Not measured55.9%Only GPT-5.2 measured
Neither model has a result on the other 28 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index56
Reasoning benchmarks for GLM 5 and GPT-5.2
BenchmarkGLM 5GPT-5.2Leader
GPQA Diamond83.3%91.7%GPT-5.2
MMMU Pro (Vals AI)Not measured86.7%Only GPT-5.2 measured
GPQA Diamond (Artificial Analysis run)82.0%90.3%GPT-5.2
Humanity's Last Exam (Artificial Analysis run)29.3%37.7%GPT-5.2
GPQA Diamond (Epoch AI run)87.8%91.4%GPT-5.2
ARC-AGI44.7%86.2%GPT-5.2
ARC-AGI-24.9%52.9%GPT-5.2
SimpleBench53.2%45.8%GLM 5
Chess puzzlesNot measured48.0%Only GPT-5.2 measured
Mystery game puzzlesNot measured23.0%Only GPT-5.2 measured
EBR-benchNot measured23.0%Only GPT-5.2 measured
VPCTNot measured84.0%Only GPT-5.2 measured
LMArena Text: hard prompts14521428GLM 5
LMArena Text: expert14541445GLM 5
LMArena Text: hard prompts in English14601431GLM 5
LMArena Vision: diagramsNot measured1265Only GPT-5.2 measured
LMArena Vision: homeworkNot measured1276Only GPT-5.2 measured
Kagi LLM Benchmark75.0%73.3%GLM 5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index22
Math benchmarks for GLM 5 and GPT-5.2
BenchmarkGLM 5GPT-5.2Leader
AIME91.7%96.9%GPT-5.2
MGSM (Vals AI)Not measured94.0%Only GPT-5.2 measured
AA Math IndexNot measured99.0Only GPT-5.2 measured
AIME 2025 (Artificial Analysis run)Not measured99.0%Only GPT-5.2 measured
OTIS Mock AIME80.0%96.1%GPT-5.2
FrontierMath, tiers 1 to 3Not measured67.4%Only GPT-5.2 measured
FrontierMath, tier 4Not measured31.7%Only GPT-5.2 measured
ProofBenchNot measured15.0%Only GPT-5.2 measured
LMArena Text: math14401440GLM 5
LMArena Text: mathematical work14511442GLM 5
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index64
Knowledge benchmarks for GLM 5 and GPT-5.2
BenchmarkGLM 5GPT-5.2Leader
MMLU Pro86.0%86.2%GPT-5.2
LegalBench (Vals AI)84.1%82.8%GLM 5
CaseLaw (Vals AI)52.5%66.0%GPT-5.2
CorpFin (Vals AI)62.9%65.9%GPT-5.2
TaxEval (Vals AI)70.0%75.8%GPT-5.2
MortgageTax (Vals AI)Not measured67.1%Only GPT-5.2 measured
MedQA (Vals AI)94.3%94.1%GLM 5
MedCode (Vals AI)Not measured49.8%Only GPT-5.2 measured
MMLU Pro (Artificial Analysis run)Not measured87.4%Only GPT-5.2 measured
SimpleQA VerifiedNot measured37.1%Only GPT-5.2 measured
LMArena Text: science14601425GLM 5
LMArena Text: medicine and healthcare14551425GLM 5
LMArena Text: legal and government14531427GLM 5
LMArena Text: business and finance14301414GLM 5
FACTS Benchmark SuiteNot measured48.5%Only GPT-5.2 measured
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index71
Web design benchmarks for GLM 5 and GPT-5.2
BenchmarkGLM 5GPT-5.2Leader
Design Arena: websites12471195GLM 5
Design Arena: UI components12271190GLM 5
Design Arena: game dev12341195GLM 5
Design Arena: data viz12281202GLM 5
Design Arena: 3D12281079GLM 5
Design Arena: all code categories12461170GLM 5
Design Arena: SVG11681139GLM 5
Design Arena: ASCII art11471152GPT-5.2
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index173
General benchmarks for GLM 5 and GPT-5.2
BenchmarkGLM 5GPT-5.2Leader
SAGE (Vals AI)Not measured49.3%Only GPT-5.2 measured
MedScribe (Vals AI)Not measured84.4%Only GPT-5.2 measured
IFBench72.3%75.4%GPT-5.2
Long context reasoning (AA-LCR)75.7%82.7%GPT-5.2
DTBenchNot measured90.9%Only GPT-5.2 measured
LMCANot measured43.9%Only GPT-5.2 measured
CL-bench18.7%18.2%GLM 5
Furniture assemblyNot measured38.3%Only GPT-5.2 measured
LMArena Text14461416GLM 5
LMArena Text: instruction following14281409GLM 5
LMArena Text: creative writing14381376GLM 5
LMArena VisionNot measured1246Only GPT-5.2 measured
LMArena Text: English14581422GLM 5
LMArena Text: non-English14301405GLM 5
LMArena Text: Chinese15111447GLM 5
LMArena Text: German14471444GLM 5
LMArena Text: Japanese14161420GPT-5.2
LMArena Text: Korean14231374GLM 5
LMArena Text: French14561454GLM 5
LMArena Text: Spanish14541413GLM 5
LMArena Text: Russian14361415GLM 5
LMArena Text: Polish14341426GLM 5
LMArena Text: multi-turn14561419GLM 5
LMArena Text: longer queries14461413GLM 5
LMArena Text: writing and language14371392GLM 5
LMArena Text: entertainment and media14261378GLM 5
LMArena Vision: EnglishNot measured1243Only GPT-5.2 measured
LMArena Vision: ChineseNot measured1305Only GPT-5.2 measured
LMArena Vision: reading textNot measured1257Only GPT-5.2 measured
LMArena Vision: humorNot measured1227Only GPT-5.2 measured
LMArena Vision: captioningNot measured1267Only GPT-5.2 measured
LMArena Vision: recognizing thingsNot measured1232Only GPT-5.2 measured
LMArena Vision: creative writingNot measured1225Only GPT-5.2 measured
LMArena DocumentNot measured1405Only GPT-5.2 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 GLM 5 and GPT-5.2
BenchmarkGLM 5GPT-5.2Leader
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$0.0026Fits in one request
GPT-5.2$0.0088Fits in one request

GLM 5 costs less

Repository review

50K input + 3K output tokens

GLM 5$0.060Fits in one request
GPT-5.2$0.130Fits in one request

GLM 5 costs less

Agent loop

200K input + 10K output tokens

GLM 5$0.232Exceeds the context window
GPT-5.2$0.490Fits in one request

GLM 5 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 and GPT-5.2
SpecificationZ.ai GLM 5OpenAI GPT-5.2
MakerZ.aiOpenAI
WeightsOpen weightsNo public weights listed
ReleasedFebruary 11, 2026December 10, 2025
Context window205K400K
Input $/Mtok$1.00$1.75
Output $/Mtok$3.20$14.00
Coding index41.755.9
Independent measurements behind it33
Cost per solved task$0.63$1.91
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 5 better than GPT-5.2 for coding?

Pick GPT-5.2 for coding: it scores 55.9 on the Vibe Coding Index against 41.7 for GLM 5. Pick GLM 5 for output tokens 4.4x cheaper ($3.20 vs $14.00 per million) and a lower cost per solved task ($0.63 against $1.91).

Which is cheaper, GLM 5 or GPT-5.2?

GLM 5 costs $1.00 per million input tokens and $3.20 per million output tokens; GPT-5.2 costs $1.75 and $14.00. Per solved SWE-bench Verified task, GLM 5 costs $0.63 and GPT-5.2 $1.91.

Which has the bigger context window, GLM 5 or GPT-5.2?

GPT-5.2, with 400K tokens against 205K.

How many benchmarks is the GLM 5 vs GPT-5.2 comparison based on?

74 benchmarks have a result for both models as of October 22, 2026. GLM 5's coding index rests on 3 independent benchmarks and GPT-5.2'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-vs-gpt-5-2" title="GLM 5 vs GPT-5.2, 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-vs-gpt-5-2">LLMBenchmark.ai, GLM 5 vs GPT-5.2</a></p>