Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0423 vs GLM 5.2

GLM 5.2 leads DeepSeek V4 Pro 0423 on coding, 61.1 to 38.7 on the Vibe Coding Index, and DeepSeek V4 Pro 0423 costs 1.5x less per output token ($2.976 vs $4.40 per million). Updated October 22, 2026; 79 benchmarks have a result for both.

Replace DeepSeek V4 Pro 0423 Replace GLM 5.2
DeepSeek V4 Pro 0423DeepSeek
Coding
38.7
Overall
50.0
Output $/M
$2.976
7
GLM 5.2Z.ai
Coding
61.1
Overall
62.5
Output $/M
$4.40
72
vs boards won of 79 shared

DeepSeek V4 Pro 0423 or GLM 5.2: which to pick

Pick GLM 5.2 for coding: it scores 61.1 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 4 benchmarks against 5.

Pick DeepSeek V4 Pro 0423 for output tokens 1.5x cheaper ($2.976 vs $4.40 per million) and a lower cost per solved task ($0.57 against $0.86).

Model ADeepSeek V4 Pro 0423DeepSeek38.7/1005 independent benchmarks$0.57 per solved taskModel BGLM 5.2Z.ai61.1/1004 independent benchmarks$0.86 per solved task
Shared results
79
DeepSeek V4 Pro 0423 only
5
GLM 5.2 only
19
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 V4 Pro 0423 38.7 from 5 benchmarks, GLM 5.2 61.1 from 4 benchmarks.
Widest category
Agentic work, 17.7 points apart on average over 8 shared benchmarks.
Widest single gap
Design Arena: agents building full-stack apps: DeepSeek V4 Pro 0423 948 against GLM 5.2 1241, 36.6 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0423 $2.976 against GLM 5.2 $4.40 per million output tokens, 1.5x apart.
Context window
Both take 1.05M tokens.

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 V4 Pro 0423BarsGLM 5.2Ties
Coding214
Intelligence02
Agentic work08
Reasoning17
Math15
Knowledge28
Web design08
General120
All shared boards772
CodingLike-for-likeSix of these boards feed the Vibe Coding Index214
Coding benchmarks for DeepSeek V4 Pro 0423 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0423GLM 5.2Leader
LMArena WebDev14471604GLM 5.2
AA Coding Index59.468.8GLM 5.2
LiveCodeBench (Vals AI)87.5%69.5%DeepSeek V4 Pro 0423
SWE-bench Verified (Vals AI)77.4%82.8%GLM 5.2
Terminal-Bench 4 (Vals AI)11.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
Vibe Code Bench (Vals AI)49.9%64.0%GLM 5.2
Code migration (Vals AI)26.2%37.9%GLM 5.2
ProgramBench (Vals AI)0.0%0.5%GLM 5.2
Terminal-Bench 2.1 (Vals AI)50.2%67.8%GLM 5.2
SkillsBench (Vals AI)51.3%45.1%DeepSeek V4 Pro 0423
SciCodeNot measured51.2%Only GLM 5.2 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured50.8%Only GLM 5.2 measured
FrontierCode17.6%24.5%GLM 5.2
WeirdML48.9%70.1%GLM 5.2
ALE-Bench1006.11047.0GLM 5.2
LMArena Text: coding14701487GLM 5.2
LMArena Text: software and IT14691486GLM 5.2
LMArena WebDev: React14411617GLM 5.2
LMArena WebDev: HTML14351565GLM 5.2
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V4 Pro 0423 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0423GLM 5.2Leader
AA Intelligence Index30.433.7GLM 5.2
Epoch Capabilities Index149.1151.9GLM 5.2
Agentic workLike-for-likePublic boards, shown as published, kept out of the index08
Agentic work benchmarks for DeepSeek V4 Pro 0423 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0423GLM 5.2Leader
AA Agentic Index26.338.4GLM 5.2
Design Arena: agents building web apps10001222GLM 5.2
Design Arena: agents building full-stack apps9481241GLM 5.2
Design Arena: agents building mobile appsNot measured1159Only GLM 5.2 measured
Design Arena: agents building Android appsNot measured1178Only GLM 5.2 measured
Design Arena: agents building Godot games10591142GLM 5.2
Design Arena: agents building gamesNot measured1206Only GLM 5.2 measured
Design Arena: HTML slidesNot measured1125Only GLM 5.2 measured
Design Arena: PowerPoint slidesNot measured1170Only GLM 5.2 measured
SREBench (Vals AI)Not measured0.0%Only GLM 5.2 measured
Finance Agent (Vals AI)44.1%49.7%GLM 5.2
Tax Agent Bench (Vals AI)25.2%Not measuredOnly DeepSeek V4 Pro 0423 measured
Legal Research Bench (Vals AI)23.1%31.3%GLM 5.2
Excel Modeling Benchmark (Vals AI)51.6%61.5%GLM 5.2
τ²-Bench TelecomNot measured99.1%Only GLM 5.2 measured
APEX-AgentsNot measured45.2%Only GLM 5.2 measured
PostTrainBenchNot measured31.7%Only GLM 5.2 measured
Vending-Bench 2$3,285$8,314GLM 5.2
Neither model has a result on the other 23 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index17
Reasoning benchmarks for DeepSeek V4 Pro 0423 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0423GLM 5.2Leader
GPQA Diamond89.4%85.6%DeepSeek V4 Pro 0423
GPQA Diamond (Artificial Analysis run)Not measured89.5%Only GLM 5.2 measured
Humanity's Last Exam (Artificial Analysis run)Not measured41.1%Only GLM 5.2 measured
GPQA Diamond (Epoch AI run)90.9%91.9%GLM 5.2
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 puzzles19.0%22.0%GLM 5.2
Mystery game puzzles17.0%19.0%GLM 5.2
EBR-benchNot measured9.5%Only GLM 5.2 measured
LMArena Text: hard prompts14611481GLM 5.2
LMArena Text: expert14631487GLM 5.2
LMArena Text: hard prompts in English14661481GLM 5.2
Kagi LLM Benchmark53.5%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 index15
Math benchmarks for DeepSeek V4 Pro 0423 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0423GLM 5.2Leader
OTIS Mock AIME96.7%86.4%DeepSeek V4 Pro 0423
FrontierMath, tiers 1 to 345.3%59.2%GLM 5.2
FrontierMath, tier 42.4%29.3%GLM 5.2
ProofBench16.0%35.0%GLM 5.2
LMArena Text: math14431483GLM 5.2
LMArena Text: mathematical work14551489GLM 5.2
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index28
Knowledge benchmarks for DeepSeek V4 Pro 0423 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0423GLM 5.2Leader
MMLU Pro87.3%86.7%DeepSeek V4 Pro 0423
LegalBench (Vals AI)80.3%84.1%GLM 5.2
CaseLaw (Vals AI)59.4%Not measuredOnly DeepSeek V4 Pro 0423 measured
CorpFin (Vals AI)61.4%66.1%GLM 5.2
TaxEval (Vals AI)72.1%73.3%GLM 5.2
MedCode (Vals AI)40.5%40.8%GLM 5.2
SimpleQA Verified47.0%34.2%DeepSeek V4 Pro 0423
LMArena Text: science14701489GLM 5.2
LMArena Text: medicine and healthcare14661475GLM 5.2
LMArena Text: legal and government14641486GLM 5.2
LMArena Text: business and finance14431451GLM 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 index08
Web design benchmarks for DeepSeek V4 Pro 0423 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0423GLM 5.2Leader
Design Arena: websites12341285GLM 5.2
Design Arena: UI components12191294GLM 5.2
Design Arena: game dev12281268GLM 5.2
Design Arena: data viz12031285GLM 5.2
Design Arena: 3D12531287GLM 5.2
Design Arena: all code categories12401287GLM 5.2
Design Arena: SVG11391213GLM 5.2
Design Arena: ASCII art11491191GLM 5.2
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index120
General benchmarks for DeepSeek V4 Pro 0423 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0423GLM 5.2Leader
Public Benefits Bench (Vals AI)62.9%Not measuredOnly DeepSeek V4 Pro 0423 measured
MedScribe (Vals AI)75.1%83.5%GLM 5.2
IFBenchNot measured73.3%Only GLM 5.2 measured
Long context reasoning (AA-LCR)Not measured78.3%Only GLM 5.2 measured
DTBench90.7%93.6%GLM 5.2
LMCA41.2%45.8%GLM 5.2
Surface Evolver Bench40.0%55.6%GLM 5.2
CL-bench Life13.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text14511470GLM 5.2
LMArena Text: instruction following14451466GLM 5.2
LMArena Text: creative writing14461463GLM 5.2
LMArena Text: English14591475GLM 5.2
LMArena Text: non-English14391459GLM 5.2
LMArena Text: Chinese14811522GLM 5.2
LMArena Text: German14581470GLM 5.2
LMArena Text: Japanese14461450GLM 5.2
LMArena Text: Korean14091440GLM 5.2
LMArena Text: French14731479GLM 5.2
LMArena Text: Spanish14571478GLM 5.2
LMArena Text: Russian14531468GLM 5.2
LMArena Text: Polish14611456DeepSeek V4 Pro 0423
LMArena Text: multi-turn14681469GLM 5.2
LMArena Text: longer queries14581480GLM 5.2
LMArena Text: writing and language14471463GLM 5.2
LMArena Text: entertainment and media14311450GLM 5.2
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 V4 Pro 0423 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0423GLM 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

DeepSeek V4 Pro 0423$0.0028Fits in one request
GLM 5.2$0.0036Fits in one request

DeepSeek V4 Pro 0423 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0423$0.077Fits in one request
GLM 5.2$0.083Fits in one request

DeepSeek V4 Pro 0423 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0423$0.301Fits in one request
GLM 5.2$0.324Fits in one request

DeepSeek V4 Pro 0423 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 V4 Pro 0423 and GLM 5.2
SpecificationDeepSeek V4 Pro 0423Z.ai GLM 5.2
MakerDeepSeekZ.ai
WeightsOpen weightsOpen weights
ReleasedApril 24, 2026June 16, 2026
Context window1.05M1.05M
Input $/Mtok$1.358$1.40
Output $/Mtok$2.976$4.40
Coding index38.761.1
Independent measurements behind it54
Cost per solved task$0.57$0.86
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0423 better than GLM 5.2 for coding?

Pick GLM 5.2 for coding: it scores 61.1 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 4 benchmarks against 5. Pick DeepSeek V4 Pro 0423 for output tokens 1.5x cheaper ($2.976 vs $4.40 per million) and a lower cost per solved task ($0.57 against $0.86).

Which is cheaper, DeepSeek V4 Pro 0423 or GLM 5.2?

DeepSeek V4 Pro 0423 costs $1.358 per million input tokens and $2.976 per million output tokens; GLM 5.2 costs $1.40 and $4.40. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0423 costs $0.57 and GLM 5.2 $0.86.

Which has the bigger context window, DeepSeek V4 Pro 0423 or GLM 5.2?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4 Pro 0423 vs GLM 5.2 comparison based on?

79 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Pro 0423's coding index rests on 5 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/deepseek-v4-pro-vs-glm-5-2" title="DeepSeek V4 Pro 0423 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/deepseek-v4-pro-vs-glm-5-2">LLMBenchmark.ai, DeepSeek V4 Pro 0423 vs GLM 5.2</a></p>