Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 vs GLM 4.5 Air

DeepSeek V3.2 leads GLM 4.5 Air on the Artificial Analysis Intelligence Index, 21.5 to 11.1, and DeepSeek V3.2 costs 1.3x less per output token ($0.88 vs $1.10 per million). Updated October 22, 2026; 46 benchmarks have a result for both.

Replace DeepSeek V3.2 Replace GLM 4.5 Air
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
44
GLM 4.5 AirZ.ai
Coding
No data
Overall
No data
Output $/M
$1.10
2
vs boards won of 46 shared

DeepSeek V3.2 or GLM 4.5 Air: which to pick

Only DeepSeek V3.2 has a coding score, 30.0 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 work measured by Design Arena: data viz or Design Arena: SVG, where it leads.

Model ADeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved taskModel BGLM 4.5 AirZ.aiNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
46
DeepSeek V3.2 only
29
GLM 4.5 Air only
2
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
DeepSeek V3.2 30.0 from 3 benchmarks, GLM 4.5 Air not benchmarked.
Widest category
Agentic work, 44.2 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: DeepSeek V3.2 90.6% against GLM 4.5 Air 46.5%, 44.2 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 $0.88 against GLM 4.5 Air $1.10 per million output tokens, 1.3x apart.
Context window
DeepSeek V3.2 takes 164K tokens, GLM 4.5 Air 131K.

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
CategoryDeepSeek V3.2BarsGLM 4.5 AirTies
Coding40
Intelligence10
Agentic work10
Reasoning50
Math40
Knowledge50
Web design52
General190
All shared boards442
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
Coding benchmarks for DeepSeek V3.2 and GLM 4.5 Air
BenchmarkDeepSeek V3.2GLM 4.5 AirLeader
SWE-bench Verified70.0%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Multilingual59.0%Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev1362Not measuredOnly DeepSeek V3.2 measured
AA Coding Index44.2Not measuredOnly DeepSeek V3.2 measured
LiveCodeBench (Vals AI)80.7%Not measuredOnly DeepSeek V3.2 measured
SWE-bench Verified (Vals AI)67.6%Not measuredOnly DeepSeek V3.2 measured
Vibe Code Bench (Vals AI)5.1%Not measuredOnly DeepSeek V3.2 measured
LiveCodeBench (Artificial Analysis run)86.2%68.4%DeepSeek V3.2
Terminal-Bench Hard (Artificial Analysis run)35.6%20.5%DeepSeek V3.2
Terminal-Bench39.6%Not measuredOnly DeepSeek V3.2 measured
GSO-BenchNot measured2.9%Only GLM 4.5 Air measured
LMArena Text: coding14531397DeepSeek V3.2
LMArena Text: software and IT14491401DeepSeek V3.2
LMArena WebDev: React1350Not measuredOnly DeepSeek V3.2 measured
LMArena WebDev: HTML1371Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V3.2 and GLM 4.5 Air
BenchmarkDeepSeek V3.2GLM 4.5 AirLeader
AA Intelligence Index21.511.1DeepSeek V3.2
Epoch Capabilities Index146.1Not measuredOnly DeepSeek V3.2 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for DeepSeek V3.2 and GLM 4.5 Air
BenchmarkDeepSeek V3.2GLM 4.5 AirLeader
τ²-Bench Telecom90.6%46.5%DeepSeek V3.2
APEX-Agents21.3%Not measuredOnly DeepSeek V3.2 measured
Vending-Bench 2$1,034Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for DeepSeek V3.2 and GLM 4.5 Air
BenchmarkDeepSeek V3.2GLM 4.5 AirLeader
GPQA Diamond80.3%Not measuredOnly DeepSeek V3.2 measured
GPQA Diamond (Artificial Analysis run)84.0%73.3%DeepSeek V3.2
Humanity's Last Exam (Artificial Analysis run)24.6%7.0%DeepSeek V3.2
ARC-AGI57.0%Not measuredOnly DeepSeek V3.2 measured
ARC-AGI-24.0%Not measuredOnly DeepSeek V3.2 measured
LMArena Text: hard prompts14341379DeepSeek V3.2
LMArena Text: expert14361370DeepSeek V3.2
LMArena Text: hard prompts in English14461388DeepSeek V3.2
Kagi LLM BenchmarkNot measured43.0%Only GLM 4.5 Air measured
Neither model has a result on the other 13 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for DeepSeek V3.2 and GLM 4.5 Air
BenchmarkDeepSeek V3.2GLM 4.5 AirLeader
AIME84.6%Not measuredOnly DeepSeek V3.2 measured
MGSM (Vals AI)86.0%Not measuredOnly DeepSeek V3.2 measured
AA Math Index92.080.7DeepSeek V3.2
AIME 2025 (Artificial Analysis run)92.0%80.7%DeepSeek V3.2
LMArena Text: math14351396DeepSeek V3.2
LMArena Text: mathematical work14401396DeepSeek V3.2
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 DeepSeek V3.2 and GLM 4.5 Air
BenchmarkDeepSeek V3.2GLM 4.5 AirLeader
MMLU Pro84.9%Not measuredOnly DeepSeek V3.2 measured
LegalBench (Vals AI)76.1%Not measuredOnly DeepSeek V3.2 measured
CaseLaw (Vals AI)55.4%Not measuredOnly DeepSeek V3.2 measured
CorpFin (Vals AI)51.0%Not measuredOnly DeepSeek V3.2 measured
TaxEval (Vals AI)68.2%Not measuredOnly DeepSeek V3.2 measured
MedQA (Vals AI)93.9%Not measuredOnly DeepSeek V3.2 measured
MMLU Pro (Artificial Analysis run)86.2%81.5%DeepSeek V3.2
LMArena Text: science14461407DeepSeek V3.2
LMArena Text: medicine and healthcare14401402DeepSeek V3.2
LMArena Text: legal and government14251382DeepSeek V3.2
LMArena Text: business and finance14101371DeepSeek V3.2
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index52
Web design benchmarks for DeepSeek V3.2 and GLM 4.5 Air
BenchmarkDeepSeek V3.2GLM 4.5 AirLeader
Design Arena: websites11751146DeepSeek V3.2
Design Arena: UI components11461120DeepSeek V3.2
Design Arena: game dev11311094DeepSeek V3.2
Design Arena: data viz11581186GLM 4.5 Air
Design Arena: 3D11321122DeepSeek V3.2
Design Arena: all code categories11631137DeepSeek V3.2
Design Arena: SVG10321071GLM 4.5 Air
Design Arena: ASCII art1083Not measuredOnly DeepSeek V3.2 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index190
General benchmarks for DeepSeek V3.2 and GLM 4.5 Air
BenchmarkDeepSeek V3.2GLM 4.5 AirLeader
IFBench60.7%37.6%DeepSeek V3.2
Long context reasoning (AA-LCR)73.3%46.7%DeepSeek V3.2
DTBench85.6%Not measuredOnly DeepSeek V3.2 measured
LMCA28.8%Not measuredOnly DeepSeek V3.2 measured
CL-bench12.4%Not measuredOnly DeepSeek V3.2 measured
CL-bench Life7.4%Not measuredOnly DeepSeek V3.2 measured
LMArena Text14251384DeepSeek V3.2
LMArena Text: instruction following14131354DeepSeek V3.2
LMArena Text: creative writing14001343DeepSeek V3.2
LMArena Text: English14391397DeepSeek V3.2
LMArena Text: non-English14091366DeepSeek V3.2
LMArena Text: Chinese14551426DeepSeek V3.2
LMArena Text: German14131377DeepSeek V3.2
LMArena Text: Japanese13741348DeepSeek V3.2
LMArena Text: Korean13701308DeepSeek V3.2
LMArena Text: French14291400DeepSeek V3.2
LMArena Text: Spanish14241385DeepSeek V3.2
LMArena Text: Russian14241373DeepSeek V3.2
LMArena Text: Polish14191368DeepSeek V3.2
LMArena Text: multi-turn14271371DeepSeek V3.2
LMArena Text: longer queries14281366DeepSeek V3.2
LMArena Text: writing and language14071354DeepSeek V3.2
LMArena Text: entertainment and media13951339DeepSeek V3.2
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 DeepSeek V3.2 and GLM 4.5 Air
BenchmarkDeepSeek V3.2GLM 4.5 AirLeader
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

DeepSeek V3.2$0.0007Fits in one request
GLM 4.5 Air$0.0008Fits in one request

DeepSeek V3.2 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2$0.017Fits in one request
GLM 4.5 Air$0.013Fits in one request

GLM 4.5 Air costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2$0.067Exceeds the context window
GLM 4.5 Air$0.051Exceeds 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 DeepSeek V3.2 and GLM 4.5 Air
SpecificationDeepSeek V3.2Z.ai GLM 4.5 Air
MakerDeepSeekZ.ai
WeightsOpen weightsOpen weights
ReleasedDecember 1, 2025July 25, 2025
Context window164K131K
Input $/Mtok$0.29$0.20
Output $/Mtok$0.88$1.10
Coding index30.0Not benchmarked
Independent measurements behind it30
Cost per solved task$0.99Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 better than GLM 4.5 Air for coding?

Only DeepSeek V3.2 has a coding score, 30.0 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 work measured by Design Arena: data viz or Design Arena: SVG, where it leads.

Which is cheaper, DeepSeek V3.2 or GLM 4.5 Air?

DeepSeek V3.2 costs $0.29 per million input tokens and $0.88 per million output tokens; GLM 4.5 Air costs $0.20 and $1.10. Cost per solved task is known for DeepSeek V3.2 only.

Which has the bigger context window, DeepSeek V3.2 or GLM 4.5 Air?

DeepSeek V3.2, with 164K tokens against 131K.

How many benchmarks is the DeepSeek V3.2 vs GLM 4.5 Air comparison based on?

46 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2's coding index rests on 3 independent benchmarks and GLM 4.5 Air's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next