Enter opens the highlighted result. Esc closes.

GLM 4.5 Air vs GLM 5.2

GLM 5.2 leads GLM 4.5 Air on the Artificial Analysis Intelligence Index, 33.7 to 11.1, and GLM 4.5 Air costs 4.0x less per output token ($1.10 vs $4.40 per million). Updated October 21, 2026; 43 benchmarks have a result for both.

Replace GLM 4.5 Air Replace GLM 5.2
GLM 4.5 AirZ.ai
Coding
No data
Overall
No data
Output $/M
$1.10
0
GLM 5.2Z.ai
Coding
61.1
Overall
62.5
Output $/M
$4.40
43
vs boards won of 43 shared

GLM 4.5 Air or GLM 5.2: which to pick

Only GLM 5.2 has a coding score, 61.1 on the Vibe Coding Index; GLM 4.5 Air has none, so the two cannot be ranked on coding.

Pick GLM 4.5 Air for output tokens 4.0x cheaper ($1.10 vs $4.40 per million).

Model AGLM 4.5 AirZ.aiNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGLM 5.2Z.ai61.1/1004 independent benchmarks$0.86 per solved task
Shared results
43
GLM 4.5 Air only
5
GLM 5.2 only
55
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 4.5 Air not benchmarked, GLM 5.2 61.1 from 4 benchmarks.
Widest category
Agentic work, 52.6 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: GLM 4.5 Air 46.5% against GLM 5.2 99.1%, 52.6 points apart on a 0 to 100 scale.
Output price
GLM 4.5 Air $1.10 against GLM 5.2 $4.40 per million output tokens, 4.0x apart.
Context window
GLM 4.5 Air takes 131K 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 4.5 AirBarsGLM 5.2Ties
Coding03
Intelligence01
Agentic work01
Reasoning06
Math02
Knowledge04
Web design07
General019
All shared boards043
CodingLike-for-likeSix of these boards feed the Vibe Coding Index03
Coding benchmarks for GLM 4.5 Air and GLM 5.2
BenchmarkGLM 4.5 AirGLM 5.2Leader
LMArena WebDevNot measured1604Only GLM 5.2 measured
AA Coding IndexNot measured68.8Only GLM 5.2 measured
LiveCodeBench (Vals AI)Not measured69.5%Only GLM 5.2 measured
SWE-bench Verified (Vals AI)Not measured82.8%Only GLM 5.2 measured
Vibe Code Bench (Vals AI)Not measured64.0%Only GLM 5.2 measured
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
LiveCodeBench (Artificial Analysis run)68.4%Not measuredOnly GLM 4.5 Air measured
SciCodeNot measured51.2%Only GLM 5.2 measured
Terminal-Bench Hard (Artificial Analysis run)20.5%50.8%GLM 5.2
FrontierCodeNot measured24.5%Only GLM 5.2 measured
GSO-Bench2.9%Not measuredOnly GLM 4.5 Air measured
WeirdMLNot measured70.1%Only GLM 5.2 measured
ALE-BenchNot measured1047.0Only GLM 5.2 measured
LMArena Text: coding13971487GLM 5.2
LMArena Text: software and IT14011486GLM 5.2
LMArena WebDev: ReactNot measured1617Only GLM 5.2 measured
LMArena WebDev: HTMLNot measured1565Only GLM 5.2 measured
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for GLM 4.5 Air and GLM 5.2
BenchmarkGLM 4.5 AirGLM 5.2Leader
AA Intelligence Index11.133.7GLM 5.2
Epoch Capabilities IndexNot measured151.9Only GLM 5.2 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for GLM 4.5 Air and GLM 5.2
BenchmarkGLM 4.5 AirGLM 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 appsNot measured1241Only GLM 5.2 measured
Design Arena: agents building mobile appsNot measured1160Only GLM 5.2 measured
Design Arena: agents building Android appsNot measured1178Only GLM 5.2 measured
Design Arena: agents building Godot gamesNot measured1142Only GLM 5.2 measured
Design Arena: agents building gamesNot measured1206Only GLM 5.2 measured
Design Arena: HTML slidesNot measured1175Only GLM 5.2 measured
Design Arena: PowerPoint slidesNot measured1195Only 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 Telecom46.5%99.1%GLM 5.2
APEX-AgentsNot measured45.2%Only GLM 5.2 measured
PostTrainBenchNot measured31.7%Only GLM 5.2 measured
Vending-Bench 2Not measured$8,314Only GLM 5.2 measured
Neither model has a result on the other 24 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
Reasoning benchmarks for GLM 4.5 Air and GLM 5.2
BenchmarkGLM 4.5 AirGLM 5.2Leader
GPQA DiamondNot measured85.6%Only GLM 5.2 measured
GPQA Diamond (Artificial Analysis run)73.3%89.5%GLM 5.2
Humanity's Last Exam (Artificial Analysis run)7.0%41.1%GLM 5.2
GPQA Diamond (Epoch AI run)Not measured91.9%Only GLM 5.2 measured
ARC-AGINot measured77.0%Only GLM 5.2 measured
ARC-AGI-2Not measured22.8%Only GLM 5.2 measured
SimpleBenchNot measured58.8%Only GLM 5.2 measured
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 prompts13791481GLM 5.2
LMArena Text: expert13701487GLM 5.2
LMArena Text: hard prompts in English13881481GLM 5.2
Kagi LLM Benchmark43.0%62.6%GLM 5.2
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for GLM 4.5 Air and GLM 5.2
BenchmarkGLM 4.5 AirGLM 5.2Leader
AA Math Index80.7Not measuredOnly GLM 4.5 Air measured
AIME 2025 (Artificial Analysis run)80.7%Not measuredOnly GLM 4.5 Air measured
OTIS Mock AIMENot measured86.4%Only GLM 5.2 measured
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: math13961483GLM 5.2
LMArena Text: mathematical work13961489GLM 5.2
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for GLM 4.5 Air and GLM 5.2
BenchmarkGLM 4.5 AirGLM 5.2Leader
MMLU ProNot measured86.7%Only GLM 5.2 measured
LegalBench (Vals AI)Not measured84.1%Only GLM 5.2 measured
CorpFin (Vals AI)Not measured66.1%Only GLM 5.2 measured
TaxEval (Vals AI)Not measured73.3%Only GLM 5.2 measured
MedCode (Vals AI)Not measured40.8%Only GLM 5.2 measured
MMLU Pro (Artificial Analysis run)81.5%Not measuredOnly GLM 4.5 Air measured
SimpleQA VerifiedNot measured34.2%Only GLM 5.2 measured
LMArena Text: science14071489GLM 5.2
LMArena Text: medicine and healthcare14021475GLM 5.2
LMArena Text: legal and government13821486GLM 5.2
LMArena Text: business and finance13711451GLM 5.2
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for GLM 4.5 Air and GLM 5.2
BenchmarkGLM 4.5 AirGLM 5.2Leader
Design Arena: websites11461285GLM 5.2
Design Arena: UI components11231296GLM 5.2
Design Arena: game dev10941268GLM 5.2
Design Arena: data viz11861285GLM 5.2
Design Arena: 3D11231288GLM 5.2
Design Arena: all code categories11371288GLM 5.2
Design Arena: SVG10711214GLM 5.2
Design Arena: ASCII artNot measured1190Only GLM 5.2 measured
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 4.5 Air and GLM 5.2
BenchmarkGLM 4.5 AirGLM 5.2Leader
MedScribe (Vals AI)Not measured83.5%Only GLM 5.2 measured
IFBench37.6%73.3%GLM 5.2
Long context reasoning (AA-LCR)46.7%78.3%GLM 5.2
DTBenchNot measured93.6%Only GLM 5.2 measured
LMCANot measured45.8%Only GLM 5.2 measured
Surface Evolver BenchNot measured55.6%Only GLM 5.2 measured
LMArena Text13841470GLM 5.2
LMArena Text: instruction following13541466GLM 5.2
LMArena Text: creative writing13431463GLM 5.2
LMArena Text: English13971475GLM 5.2
LMArena Text: non-English13661459GLM 5.2
LMArena Text: Chinese14261522GLM 5.2
LMArena Text: German13771470GLM 5.2
LMArena Text: Japanese13481450GLM 5.2
LMArena Text: Korean13081440GLM 5.2
LMArena Text: French14001479GLM 5.2
LMArena Text: Spanish13851478GLM 5.2
LMArena Text: Russian13731468GLM 5.2
LMArena Text: Polish13681456GLM 5.2
LMArena Text: multi-turn13711469GLM 5.2
LMArena Text: longer queries13661480GLM 5.2
LMArena Text: writing and language13541463GLM 5.2
LMArena Text: entertainment and media13391450GLM 5.2
Neither model has a result on the other 23 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GLM 4.5 Air and GLM 5.2
BenchmarkGLM 4.5 AirGLM 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 4.5 Air$0.0008Fits in one request
GLM 5.2$0.0036Fits in one request

GLM 4.5 Air costs less

Repository review

50K input + 3K output tokens

GLM 4.5 Air$0.013Fits in one request
GLM 5.2$0.083Fits in one request

GLM 4.5 Air costs less

Agent loop

200K input + 10K output tokens

GLM 4.5 Air$0.051Exceeds the context window
GLM 5.2$0.324Fits in one request

GLM 4.5 Air 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 4.5 Air and GLM 5.2
SpecificationZ.ai GLM 4.5 AirZ.ai GLM 5.2
MakerZ.aiZ.ai
WeightsOpen weightsOpen weights
ReleasedJuly 25, 2025June 16, 2026
Context window131K1.05M
Input $/Mtok$0.20$1.40
Output $/Mtok$1.10$4.40
Coding indexNot benchmarked61.1
Independent measurements behind it04
Cost per solved taskNot computable$0.86
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 4.5 Air better than GLM 5.2 for coding?

Only GLM 5.2 has a coding score, 61.1 on the Vibe Coding Index; GLM 4.5 Air has none, so the two cannot be ranked on coding. Pick GLM 4.5 Air for output tokens 4.0x cheaper ($1.10 vs $4.40 per million).

Which is cheaper, GLM 4.5 Air or GLM 5.2?

GLM 4.5 Air costs $0.20 per million input tokens and $1.10 per million output tokens; GLM 5.2 costs $1.40 and $4.40. Cost per solved task is known for GLM 5.2 only.

Which has the bigger context window, GLM 4.5 Air or GLM 5.2?

GLM 5.2, with 1.05M tokens against 131K.

How many benchmarks is the GLM 4.5 Air vs GLM 5.2 comparison based on?

43 benchmarks have a result for both models as of October 21, 2026. GLM 4.5 Air's coding index rests on 0 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