Enter opens the highlighted result. Esc closes.

DeepSeek V3.2 Exp vs GLM 4.7

GLM 4.7 leads DeepSeek V3.2 Exp on the Artificial Analysis Intelligence Index, 22.2 to 16.6, and DeepSeek V3.2 Exp costs 5.4x less per output token ($0.41 vs $2.20 per million). Updated October 22, 2026; 51 benchmarks have a result for both.

Replace DeepSeek V3.2 Exp Replace GLM 4.7
DeepSeek V3.2 ExpDeepSeek
Coding
No data
Overall
No data
Output $/M
$0.41
8
GLM 4.7Z.ai
Coding
55.1
Overall
56.9
Output $/M
$2.20
43
vs boards won of 51 shared

DeepSeek V3.2 Exp or GLM 4.7: which to pick

Only GLM 4.7 has a coding score, 55.1 on the Vibe Coding Index; DeepSeek V3.2 Exp has none, so the two cannot be ranked on coding.

Pick DeepSeek V3.2 Exp for output tokens 5.4x cheaper ($0.41 vs $2.20 per million) and work measured by Epoch Capabilities Index or LMArena Text: mathematical work, where it leads.

Model ADeepSeek V3.2 ExpDeepSeekNot benchmarked1 independent benchmarkNo cost per solved taskModel BGLM 4.7Z.ai55.1/1002 independent benchmarks$0.29 per solved task
Shared results
51
DeepSeek V3.2 Exp only
8
GLM 4.7 only
30
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 Exp not benchmarked, GLM 4.7 55.1 from 2 benchmarks.
Widest category
Agentic work, 62.0 points apart on average over 1 shared benchmark.
Widest single gap
τ²-Bench Telecom: DeepSeek V3.2 Exp 33.9% against GLM 4.7 95.9%, 62.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.2 Exp $0.41 against GLM 4.7 $2.20 per million output tokens, 5.4x apart.
Context window
DeepSeek V3.2 Exp takes 164K tokens, GLM 4.7 205K.

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 V3.2 ExpBarsGLM 4.7Ties
Coding06
Intelligence11
Agentic work01
Reasoning05
Math13
Knowledge05
Web design07
General615
All shared boards843
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
Coding benchmarks for DeepSeek V3.2 Exp and GLM 4.7
BenchmarkDeepSeek V3.2 ExpGLM 4.7Leader
Aider polyglot74.2%Not measuredOnly DeepSeek V3.2 Exp measured
LMArena WebDev12721435GLM 4.7
AA Coding IndexNot measured45.3Only GLM 4.7 measured
LiveCodeBench (Vals AI)Not measured82.2%Only GLM 4.7 measured
SWE-bench Verified (Vals AI)Not measured69.4%Only GLM 4.7 measured
LiveCodeBench (Artificial Analysis run)78.9%89.4%GLM 4.7
Terminal-Bench Hard (Artificial Analysis run)31.1%31.8%GLM 4.7
Terminal-BenchNot measured33.4%Only GLM 4.7 measured
WeirdML39.5%Not measuredOnly DeepSeek V3.2 Exp measured
ALE-BenchNot measured399.5Only GLM 4.7 measured
LMArena Text: coding14381454GLM 4.7
LMArena Text: software and IT14381453GLM 4.7
LMArena WebDev: ReactNot measured1420Only GLM 4.7 measured
LMArena WebDev: HTML12811447GLM 4.7
Neither model has a result on the other 25 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for DeepSeek V3.2 Exp and GLM 4.7
BenchmarkDeepSeek V3.2 ExpGLM 4.7Leader
AA Intelligence Index16.622.2GLM 4.7
Epoch Capabilities Index144.9143.6DeepSeek V3.2 Exp
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for DeepSeek V3.2 Exp and GLM 4.7
BenchmarkDeepSeek V3.2 ExpGLM 4.7Leader
Design Arena: agents building full-stack appsNot measured1050Only GLM 4.7 measured
Design Arena: agents building mobile appsNot measured1105Only GLM 4.7 measured
Design Arena: agents building Android appsNot measured1112Only GLM 4.7 measured
Design Arena: agents building Godot gamesNot measured1058Only GLM 4.7 measured
τ²-Bench Telecom33.9%95.9%GLM 4.7
TheAgentCompany42.9%Not measuredOnly DeepSeek V3.2 Exp measured
Vending-Bench 2Not measured$2,377Only GLM 4.7 measured
Berkeley Function Calling Leaderboard (BFCL)56.7%Not measuredOnly DeepSeek V3.2 Exp measured
BrowseComp-PlusNot measured64.7%Only GLM 4.7 measured
Neither model has a result on the other 32 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for DeepSeek V3.2 Exp and GLM 4.7
BenchmarkDeepSeek V3.2 ExpGLM 4.7Leader
GPQA DiamondNot measured80.0%Only GLM 4.7 measured
GPQA Diamond (Artificial Analysis run)79.7%85.9%GLM 4.7
Humanity's Last Exam (Artificial Analysis run)14.9%27.4%GLM 4.7
GPQA Diamond (Epoch AI run)Not measured83.3%Only GLM 4.7 measured
SimpleBenchNot measured47.7%Only GLM 4.7 measured
Chess puzzlesNot measured21.0%Only GLM 4.7 measured
LMArena Text: hard prompts14291443GLM 4.7
LMArena Text: expert14221424GLM 4.7
LMArena Text: hard prompts in English14441452GLM 4.7
Kagi LLM Benchmark52.2%Not measuredOnly DeepSeek V3.2 Exp measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index13
Math benchmarks for DeepSeek V3.2 Exp and GLM 4.7
BenchmarkDeepSeek V3.2 ExpGLM 4.7Leader
AIMENot measured93.3%Only GLM 4.7 measured
MGSM (Vals AI)Not measured88.2%Only GLM 4.7 measured
AA Math Index87.795.0GLM 4.7
AIME 2025 (Artificial Analysis run)87.7%95.0%GLM 4.7
OTIS Mock AIMENot measured83.3%Only GLM 4.7 measured
ProofBenchNot measured6.0%Only GLM 4.7 measured
LMArena Text: math14221424GLM 4.7
LMArena Text: mathematical work14331411DeepSeek V3.2 Exp
Neither model has a result on the other 5 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for DeepSeek V3.2 Exp and GLM 4.7
BenchmarkDeepSeek V3.2 ExpGLM 4.7Leader
MMLU ProNot measured82.7%Only GLM 4.7 measured
LegalBench (Vals AI)Not measured83.4%Only GLM 4.7 measured
CaseLaw (Vals AI)Not measured54.9%Only GLM 4.7 measured
CorpFin (Vals AI)Not measured46.4%Only GLM 4.7 measured
TaxEval (Vals AI)Not measured68.8%Only GLM 4.7 measured
MedQA (Vals AI)Not measured93.7%Only GLM 4.7 measured
MedCode (Vals AI)Not measured32.8%Only GLM 4.7 measured
MMLU Pro (Artificial Analysis run)85.0%85.6%GLM 4.7
SimpleQA VerifiedNot measured32.2%Only GLM 4.7 measured
LMArena Text: science14431457GLM 4.7
LMArena Text: medicine and healthcare14681469GLM 4.7
LMArena Text: legal and government14191444GLM 4.7
LMArena Text: business and finance14121429GLM 4.7
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for DeepSeek V3.2 Exp and GLM 4.7
BenchmarkDeepSeek V3.2 ExpGLM 4.7Leader
Design Arena: websites11781225GLM 4.7
Design Arena: UI components11641196GLM 4.7
Design Arena: game dev11441188GLM 4.7
Design Arena: data viz11521195GLM 4.7
Design Arena: 3D11481190GLM 4.7
Design Arena: all code categories11701216GLM 4.7
Design Arena: SVG10311142GLM 4.7
Design Arena: ASCII artNot measured1165Only GLM 4.7 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index615
General benchmarks for DeepSeek V3.2 Exp and GLM 4.7
BenchmarkDeepSeek V3.2 ExpGLM 4.7Leader
MedScribe (Vals AI)Not measured68.6%Only GLM 4.7 measured
IFBench54.1%67.9%GLM 4.7
Long context reasoning (AA-LCR)72.3%71.0%DeepSeek V3.2 Exp
DTBench87.7%Not measuredOnly DeepSeek V3.2 Exp measured
LMCA29.1%Not measuredOnly DeepSeek V3.2 Exp measured
Fiction.LiveBench83.3%Not measuredOnly DeepSeek V3.2 Exp measured
CL-bench13.2%15.9%GLM 4.7
CL-bench Life9.5%10.9%GLM 4.7
LMArena Text14251435GLM 4.7
LMArena Text: instruction following14011412GLM 4.7
LMArena Text: creative writing14041401DeepSeek V3.2 Exp
LMArena Text: English14411453GLM 4.7
LMArena Text: non-English14041417GLM 4.7
LMArena Text: Chinese14611495GLM 4.7
LMArena Text: German14401426DeepSeek V3.2 Exp
LMArena Text: Japanese13311439GLM 4.7
LMArena Text: Korean13721399GLM 4.7
LMArena Text: French14341432DeepSeek V3.2 Exp
LMArena Text: Spanish14411434DeepSeek V3.2 Exp
LMArena Text: Russian14121423GLM 4.7
LMArena Text: Polish14351435GLM 4.7
LMArena Text: multi-turn14221446GLM 4.7
LMArena Text: longer queries14181432GLM 4.7
LMArena Text: writing and language14071411GLM 4.7
LMArena Text: entertainment and media14071400DeepSeek V3.2 Exp
Neither model has a result on the other 21 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.2 Exp and GLM 4.7
BenchmarkDeepSeek V3.2 ExpGLM 4.7Leader
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 Exp$0.0005Fits in one request
GLM 4.7$0.0017Fits in one request

DeepSeek V3.2 Exp costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.2 Exp$0.015Fits in one request
GLM 4.7$0.037Fits in one request

DeepSeek V3.2 Exp costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.2 Exp$0.058Exceeds the context window
GLM 4.7$0.142Exceeds the context window

DeepSeek V3.2 Exp 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 Exp and GLM 4.7
SpecificationDeepSeek V3.2 ExpZ.ai GLM 4.7
MakerDeepSeekZ.ai
WeightsOpen weightsOpen weights
ReleasedSeptember 29, 2025December 22, 2025
Context window164K205K
Input $/Mtok$0.27$0.60
Output $/Mtok$0.41$2.20
Coding indexNot benchmarked55.1
Independent measurements behind it12
Cost per solved taskNot computable$0.29
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.2 Exp better than GLM 4.7 for coding?

Only GLM 4.7 has a coding score, 55.1 on the Vibe Coding Index; DeepSeek V3.2 Exp has none, so the two cannot be ranked on coding. Pick DeepSeek V3.2 Exp for output tokens 5.4x cheaper ($0.41 vs $2.20 per million) and work measured by Epoch Capabilities Index or LMArena Text: mathematical work, where it leads.

Which is cheaper, DeepSeek V3.2 Exp or GLM 4.7?

DeepSeek V3.2 Exp costs $0.27 per million input tokens and $0.41 per million output tokens; GLM 4.7 costs $0.60 and $2.20. Cost per solved task is known for GLM 4.7 only.

Which has the bigger context window, DeepSeek V3.2 Exp or GLM 4.7?

GLM 4.7, with 205K tokens against 164K.

How many benchmarks is the DeepSeek V3.2 Exp vs GLM 4.7 comparison based on?

51 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.2 Exp's coding index rests on 1 independent benchmark and GLM 4.7's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next