Enter opens the highlighted result. Esc closes.

GLM 5 vs GLM 5.2

GLM 5.2 leads GLM 5 on coding, 61.1 to 41.7 on the Vibe Coding Index, and GLM 5 costs 1.4x less per output token ($3.20 vs $4.40 per million). Updated October 22, 2026; 69 benchmarks have a result for both.

Replace GLM 5 Replace GLM 5.2
GLM 5Z.ai
Coding
41.7
Overall
54.3
Output $/M
$3.20
3
GLM 5.2Z.ai
Coding
61.1
Overall
62.5
Output $/M
$4.40
66
vs boards won of 69 shared

GLM 5 or GLM 5.2: which to pick

Pick GLM 5.2 for coding: it scores 61.1 on the Vibe Coding Index against 41.7 for GLM 5.

Pick GLM 5 for output tokens 1.4x cheaper ($3.20 vs $4.40 per million) and a lower cost per solved task ($0.63 against $0.86).

Model AGLM 5Z.ai41.7/1003 independent benchmarks$0.63 per solved taskModel BGLM 5.2Z.ai61.1/1004 independent benchmarks$0.86 per solved task
Shared results
69
GLM 5 only
7
GLM 5.2 only
29
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, GLM 5.2 61.1 from 4 benchmarks.
Widest category
Coding, 16.8 points apart on average over 11 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): GLM 5 23.4% against GLM 5.2 64.0%, 40.6 points apart on a 0 to 100 scale.
Output price
GLM 5 $3.20 against GLM 5.2 $4.40 per million output tokens, 1.4x apart.
Context window
GLM 5 takes 205K tokens, GLM 5.2 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 5BarsGLM 5.2Ties
Coding110
Intelligence02
Agentic work16
Reasoning110
Math03
Knowledge08
Web design08
General019
All shared boards366
CodingLike-for-likeSix of these boards feed the Vibe Coding Index110
Coding benchmarks for GLM 5 and GLM 5.2
BenchmarkGLM 5GLM 5.2Leader
SWE-bench Verified72.8%Not measuredOnly GLM 5 measured
SWE-bench Multilingual69.7%Not measuredOnly GLM 5 measured
LMArena WebDev14351604GLM 5.2
AA Coding IndexNot measured68.8Only GLM 5.2 measured
LiveCodeBench (Vals AI)81.9%69.5%GLM 5
SWE-bench Verified (Vals AI)71.4%82.8%GLM 5.2
Vibe Code Bench (Vals AI)23.4%64.0%GLM 5.2
Code migration (Vals AI)Not measured37.9%Only GLM 5.2 measured
ProgramBench (Vals AI)Not measured0.5%Only GLM 5.2 measured
Terminal-Bench 2.1 (Vals AI)Not measured67.8%Only GLM 5.2 measured
SkillsBench (Vals AI)Not measured45.1%Only GLM 5.2 measured
SciCodeNot measured51.2%Only GLM 5.2 measured
Terminal-Bench Hard (Artificial Analysis run)43.2%50.8%GLM 5.2
Terminal-Bench52.4%Not measuredOnly GLM 5 measured
FrontierCodeNot measured24.5%Only GLM 5.2 measured
WeirdML48.2%70.1%GLM 5.2
ALE-Bench765.61047.0GLM 5.2
LMArena Text: coding14611487GLM 5.2
LMArena Text: software and IT14601486GLM 5.2
LMArena WebDev: React14241617GLM 5.2
LMArena WebDev: HTML14501565GLM 5.2
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for GLM 5 and GLM 5.2
BenchmarkGLM 5GLM 5.2Leader
AA Intelligence Index27.933.7GLM 5.2
Epoch Capabilities Index145.8151.9GLM 5.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index16
Agentic work benchmarks for GLM 5 and GLM 5.2
BenchmarkGLM 5GLM 5.2Leader
AA Agentic IndexNot measured38.4Only GLM 5.2 measured
Design Arena: agents building web appsNot measured1222Only GLM 5.2 measured
Design Arena: agents building full-stack apps11231241GLM 5.2
Design Arena: agents building mobile apps11361159GLM 5.2
Design Arena: agents building Android apps11471178GLM 5.2
Design Arena: agents building Godot games11441142GLM 5
Design Arena: agents building gamesNot measured1206Only GLM 5.2 measured
Design Arena: HTML slides10981125GLM 5.2
Design Arena: PowerPoint slidesNot measured1170Only GLM 5.2 measured
SREBench (Vals AI)Not measured0.0%Only GLM 5.2 measured
Finance Agent (Vals AI)Not measured49.7%Only GLM 5.2 measured
Legal Research Bench (Vals AI)Not measured31.3%Only GLM 5.2 measured
Excel Modeling Benchmark (Vals AI)Not measured61.5%Only GLM 5.2 measured
τ²-Bench Telecom98.2%99.1%GLM 5.2
APEX-AgentsNot measured45.2%Only GLM 5.2 measured
PostTrainBenchNot measured31.7%Only GLM 5.2 measured
Vending-Bench 2$4,432$8,314GLM 5.2
Neither model has a result on the other 24 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index110
Reasoning benchmarks for GLM 5 and GLM 5.2
BenchmarkGLM 5GLM 5.2Leader
GPQA Diamond83.3%85.6%GLM 5.2
GPQA Diamond (Artificial Analysis run)82.0%89.5%GLM 5.2
Humanity's Last Exam (Artificial Analysis run)29.3%41.1%GLM 5.2
GPQA Diamond (Epoch AI run)87.8%91.9%GLM 5.2
ARC-AGI44.7%77.0%GLM 5.2
ARC-AGI-24.9%22.8%GLM 5.2
SimpleBench53.2%58.8%GLM 5.2
Chess puzzlesNot measured22.0%Only GLM 5.2 measured
Mystery game puzzlesNot measured19.0%Only GLM 5.2 measured
EBR-benchNot measured9.5%Only GLM 5.2 measured
LMArena Text: hard prompts14521481GLM 5.2
LMArena Text: expert14541487GLM 5.2
LMArena Text: hard prompts in English14601481GLM 5.2
Kagi LLM Benchmark75.0%62.6%GLM 5
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for GLM 5 and GLM 5.2
BenchmarkGLM 5GLM 5.2Leader
AIME91.7%Not measuredOnly GLM 5 measured
OTIS Mock AIME80.0%86.4%GLM 5.2
FrontierMath, tiers 1 to 3Not measured59.2%Only GLM 5.2 measured
FrontierMath, tier 4Not measured29.3%Only GLM 5.2 measured
ProofBenchNot measured35.0%Only GLM 5.2 measured
LMArena Text: math14401483GLM 5.2
LMArena Text: mathematical work14511489GLM 5.2
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index08
Knowledge benchmarks for GLM 5 and GLM 5.2
BenchmarkGLM 5GLM 5.2Leader
MMLU Pro86.0%86.7%GLM 5.2
LegalBench (Vals AI)84.1%84.1%GLM 5.2
CaseLaw (Vals AI)52.5%Not measuredOnly GLM 5 measured
CorpFin (Vals AI)62.9%66.1%GLM 5.2
TaxEval (Vals AI)70.0%73.3%GLM 5.2
MedQA (Vals AI)94.3%Not measuredOnly GLM 5 measured
MedCode (Vals AI)Not measured40.8%Only GLM 5.2 measured
SimpleQA VerifiedNot measured34.2%Only GLM 5.2 measured
LMArena Text: science14601489GLM 5.2
LMArena Text: medicine and healthcare14551475GLM 5.2
LMArena Text: legal and government14531486GLM 5.2
LMArena Text: business and finance14301451GLM 5.2
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for GLM 5 and GLM 5.2
BenchmarkGLM 5GLM 5.2Leader
Design Arena: websites12471285GLM 5.2
Design Arena: UI components12271294GLM 5.2
Design Arena: game dev12341268GLM 5.2
Design Arena: data viz12281285GLM 5.2
Design Arena: 3D12281287GLM 5.2
Design Arena: all code categories12461287GLM 5.2
Design Arena: SVG11681213GLM 5.2
Design Arena: ASCII art11471191GLM 5.2
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index019
General benchmarks for GLM 5 and GLM 5.2
BenchmarkGLM 5GLM 5.2Leader
MedScribe (Vals AI)Not measured83.5%Only GLM 5.2 measured
IFBench72.3%73.3%GLM 5.2
Long context reasoning (AA-LCR)75.7%78.3%GLM 5.2
DTBenchNot measured93.6%Only GLM 5.2 measured
LMCANot measured45.8%Only GLM 5.2 measured
CL-bench18.7%Not measuredOnly GLM 5 measured
Surface Evolver BenchNot measured55.6%Only GLM 5.2 measured
LMArena Text14461470GLM 5.2
LMArena Text: instruction following14281466GLM 5.2
LMArena Text: creative writing14381463GLM 5.2
LMArena Text: English14581475GLM 5.2
LMArena Text: non-English14301459GLM 5.2
LMArena Text: Chinese15111522GLM 5.2
LMArena Text: German14471470GLM 5.2
LMArena Text: Japanese14161450GLM 5.2
LMArena Text: Korean14231440GLM 5.2
LMArena Text: French14561479GLM 5.2
LMArena Text: Spanish14541478GLM 5.2
LMArena Text: Russian14361468GLM 5.2
LMArena Text: Polish14341456GLM 5.2
LMArena Text: multi-turn14561469GLM 5.2
LMArena Text: longer queries14461480GLM 5.2
LMArena Text: writing and language14371463GLM 5.2
LMArena Text: entertainment and media14261450GLM 5.2
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 and GLM 5.2
BenchmarkGLM 5GLM 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
GLM 5.2$0.0036Fits in one request

GLM 5 costs less

Repository review

50K input + 3K output tokens

GLM 5$0.060Fits in one request
GLM 5.2$0.083Fits in one request

GLM 5 costs less

Agent loop

200K input + 10K output tokens

GLM 5$0.232Exceeds the context window
GLM 5.2$0.324Fits 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 GLM 5.2
SpecificationZ.ai GLM 5Z.ai GLM 5.2
MakerZ.aiZ.ai
WeightsOpen weightsOpen weights
ReleasedFebruary 11, 2026June 16, 2026
Context window205K1.05M
Input $/Mtok$1.00$1.40
Output $/Mtok$3.20$4.40
Coding index41.761.1
Independent measurements behind it34
Cost per solved task$0.63$0.86
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 5 better than GLM 5.2 for coding?

Pick GLM 5.2 for coding: it scores 61.1 on the Vibe Coding Index against 41.7 for GLM 5. Pick GLM 5 for output tokens 1.4x cheaper ($3.20 vs $4.40 per million) and a lower cost per solved task ($0.63 against $0.86).

Which is cheaper, GLM 5 or GLM 5.2?

GLM 5 costs $1.00 per million input tokens and $3.20 per million output tokens; GLM 5.2 costs $1.40 and $4.40. Per solved SWE-bench Verified task, GLM 5 costs $0.63 and GLM 5.2 $0.86.

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

GLM 5.2, with 1.05M tokens against 205K.

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

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