Enter opens the highlighted result. Esc closes.

GLM 4.5 Air vs Qwen2.5 72B Instruct

GLM 4.5 Air leads Qwen2.5 72B Instruct on the Artificial Analysis Intelligence Index, 11.1 to 7.7, and Qwen2.5 72B Instruct costs 2.8x less per output token ($0.40 vs $1.10 per million). Updated October 22, 2026; 37 benchmarks have a result for both.

Replace GLM 4.5 Air Replace Qwen2.5 72B Instruct
GLM 4.5 AirZ.ai
Coding
No data
Overall
No data
Output $/M
$1.10
37
Qwen2.5 72B InstructQwen
Coding
No data
Overall
26.5
Output $/M
$0.40
0
vs boards won of 37 shared

GLM 4.5 Air or Qwen2.5 72B Instruct: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick GLM 4.5 Air for a larger context window (131K against 33K tokens).

Model AGLM 4.5 AirZ.aiNot benchmarkedNo coding benchmarkNo cost per solved taskModel BQwen2.5 72B InstructQwenNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
37
GLM 4.5 Air only
11
Qwen2.5 72B Instruct only
16
Like-for-like categories
7 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, Qwen2.5 72B Instruct not benchmarked.
Widest category
Math, 42.4 points apart on average over 4 shared benchmarks.
Widest single gap
AA Math Index: GLM 4.5 Air 80.7 against Qwen2.5 72B Instruct 14.0, 66.7 points apart on a 0 to 100 scale.
Output price
GLM 4.5 Air $1.10 against Qwen2.5 72B Instruct $0.40 per million output tokens, 2.8x apart.
Context window
GLM 4.5 Air takes 131K tokens, Qwen2.5 72B Instruct 33K.

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 AirBarsQwen2.5 72B InstructTies
Coding40
Intelligence10
Agentic work10
Reasoning50
Math40
Knowledge50
General170
All shared boards370
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
Coding benchmarks for GLM 4.5 Air and Qwen2.5 72B Instruct
BenchmarkGLM 4.5 AirQwen2.5 72B InstructLeader
LiveCodeBench (Artificial Analysis run)68.4%27.6%GLM 4.5 Air
Terminal-Bench Hard (Artificial Analysis run)20.5%4.5%GLM 4.5 Air
GSO-Bench2.9%Not measuredOnly GLM 4.5 Air measured
WeirdMLNot measured16.0%Only Qwen2.5 72B Instruct measured
LMArena Text: coding13971292GLM 4.5 Air
LMArena Text: software and IT14011292GLM 4.5 Air
Neither model has a result on the other 33 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for GLM 4.5 Air and Qwen2.5 72B Instruct
BenchmarkGLM 4.5 AirQwen2.5 72B InstructLeader
AA Intelligence Index11.17.7GLM 4.5 Air
Epoch Capabilities IndexNot measured129.0Only Qwen2.5 72B Instruct measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for GLM 4.5 Air and Qwen2.5 72B Instruct
BenchmarkGLM 4.5 AirQwen2.5 72B InstructLeader
τ²-Bench Telecom46.5%34.5%GLM 4.5 Air
METR time horizonsNot measured35.8%Only Qwen2.5 72B Instruct measured
BALROGNot measured16.2%Only Qwen2.5 72B Instruct measured
TheAgentCompanyNot measured5.7%Only Qwen2.5 72B Instruct measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for GLM 4.5 Air and Qwen2.5 72B Instruct
BenchmarkGLM 4.5 AirQwen2.5 72B InstructLeader
GPQA Diamond (Artificial Analysis run)73.3%49.1%GLM 4.5 Air
Humanity's Last Exam (Artificial Analysis run)7.0%3.6%GLM 4.5 Air
GPQA Diamond (Epoch AI run)Not measured49.1%Only Qwen2.5 72B Instruct measured
BIG-Bench HardNot measured79.8%Only Qwen2.5 72B Instruct measured
LMArena Text: hard prompts13791271GLM 4.5 Air
LMArena Text: expert13701245GLM 4.5 Air
LMArena Text: hard prompts in English13881279GLM 4.5 Air
Kagi LLM Benchmark43.0%Not measuredOnly GLM 4.5 Air measured
Neither model has a result on the other 14 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for GLM 4.5 Air and Qwen2.5 72B Instruct
BenchmarkGLM 4.5 AirQwen2.5 72B InstructLeader
AA Math Index80.714.0GLM 4.5 Air
AIME 2025 (Artificial Analysis run)80.7%14.0%GLM 4.5 Air
OTIS Mock AIMENot measured8.1%Only Qwen2.5 72B Instruct measured
MATH level 5Not measured63.2%Only Qwen2.5 72B Instruct measured
LMArena Text: math13961283GLM 4.5 Air
LMArena Text: mathematical work13961290GLM 4.5 Air
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for GLM 4.5 Air and Qwen2.5 72B Instruct
BenchmarkGLM 4.5 AirQwen2.5 72B InstructLeader
MMLU Pro (Artificial Analysis run)81.5%72.0%GLM 4.5 Air
MMLUNot measured85.3%Only Qwen2.5 72B Instruct measured
AI2 Reasoning ChallengeNot measured94.5%Only Qwen2.5 72B Instruct measured
LMArena Text: science14071275GLM 4.5 Air
LMArena Text: medicine and healthcare14021258GLM 4.5 Air
LMArena Text: legal and government13821288GLM 4.5 Air
LMArena Text: business and finance13711253GLM 4.5 Air
Neither model has a result on the other 11 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for GLM 4.5 Air and Qwen2.5 72B Instruct
BenchmarkGLM 4.5 AirQwen2.5 72B InstructLeader
Design Arena: websites1146Not measuredOnly GLM 4.5 Air measured
Design Arena: UI components1120Not measuredOnly GLM 4.5 Air measured
Design Arena: game dev1094Not measuredOnly GLM 4.5 Air measured
Design Arena: data viz1186Not measuredOnly GLM 4.5 Air measured
Design Arena: 3D1122Not measuredOnly GLM 4.5 Air measured
Design Arena: all code categories1137Not measuredOnly GLM 4.5 Air measured
Design Arena: SVG1071Not measuredOnly GLM 4.5 Air measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index170
General benchmarks for GLM 4.5 Air and Qwen2.5 72B Instruct
BenchmarkGLM 4.5 AirQwen2.5 72B InstructLeader
IFBench37.6%36.9%GLM 4.5 Air
Long context reasoning (AA-LCR)46.7%Not measuredOnly GLM 4.5 Air measured
DTBenchNot measured62.9%Only Qwen2.5 72B Instruct measured
LMCANot measured13.4%Only Qwen2.5 72B Instruct measured
HellaSwagNot measured84.8%Only Qwen2.5 72B Instruct measured
WinoGrandeNot measured82.3%Only Qwen2.5 72B Instruct measured
PIQANot measured82.6%Only Qwen2.5 72B Instruct measured
LMArena Text13841269GLM 4.5 Air
LMArena Text: instruction following13541254GLM 4.5 Air
LMArena Text: creative writing13431221GLM 4.5 Air
LMArena Text: English13971283GLM 4.5 Air
LMArena Text: non-English13661252GLM 4.5 Air
LMArena Text: Chinese14261273GLM 4.5 Air
LMArena Text: German13771234GLM 4.5 Air
LMArena Text: Japanese13481180GLM 4.5 Air
LMArena Text: Korean13081188GLM 4.5 Air
LMArena Text: French14001280GLM 4.5 Air
LMArena Text: Spanish13851255GLM 4.5 Air
LMArena Text: Russian13731264GLM 4.5 Air
LMArena Text: Polish1368Not measuredOnly GLM 4.5 Air measured
LMArena Text: multi-turn13711272GLM 4.5 Air
LMArena Text: longer queries13661281GLM 4.5 Air
LMArena Text: writing and language13541247GLM 4.5 Air
LMArena Text: entertainment and media13391211GLM 4.5 Air
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 4.5 Air and Qwen2.5 72B Instruct
BenchmarkGLM 4.5 AirQwen2.5 72B InstructLeader
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
Qwen2.5 72B Instruct$0.0006Fits in one request

Qwen2.5 72B Instruct costs less

Repository review

50K input + 3K output tokens

GLM 4.5 Air$0.013Fits in one request
Qwen2.5 72B Instruct$0.019Exceeds the context window

GLM 4.5 Air costs less

Agent loop

200K input + 10K output tokens

GLM 4.5 Air$0.051Exceeds the context window
Qwen2.5 72B Instruct$0.076Exceeds the context window

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 Qwen2.5 72B Instruct
SpecificationZ.ai GLM 4.5 AirQwen2.5 72B Instruct
MakerZ.aiQwen
WeightsOpen weightsOpen weights
ReleasedJuly 25, 2025September 19, 2024
Context window131K33K
Input $/Mtok$0.20$0.36
Output $/Mtok$1.10$0.40
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is GLM 4.5 Air better than Qwen2.5 72B Instruct for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GLM 4.5 Air for a larger context window (131K against 33K tokens).

Which is cheaper, GLM 4.5 Air or Qwen2.5 72B Instruct?

GLM 4.5 Air costs $0.20 per million input tokens and $1.10 per million output tokens; Qwen2.5 72B Instruct costs $0.36 and $0.40. Cost per solved task is known for neither of them.

Which has the bigger context window, GLM 4.5 Air or Qwen2.5 72B Instruct?

GLM 4.5 Air, with 131K tokens against 33K.

How many benchmarks is the GLM 4.5 Air vs Qwen2.5 72B Instruct comparison based on?

37 benchmarks have a result for both models as of October 22, 2026. GLM 4.5 Air's coding index rests on 0 independent benchmarks and Qwen2.5 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next