LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0423 vs GLM 5.3

Updated October 21, 2026. 76 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace DeepSeek V4 Pro 0423 Replace GLM 5.3
DeepSeek V4 Pro 0423DeepSeek
Coding
35.3
Overall
30.4
Output $/M
$1.9105
7
GLM 5.3Z.ai
Coding
73.1
Overall
44.8
Output $/M
$1.40
68
vs boards won of 76 shared, 1 tied

Decision reading

Pick GLM 5.3 for coding: it scores 73.1 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423.

Pick DeepSeek V4 Pro 0423 when what matters is LiveCodeBench (Vals AI) or SkillsBench (Vals AI), where it leads.

Model ADeepSeek V4 Pro 0423DeepSeek35.3/1001 independent benchmark$0.57 per solved taskModel BGLM 5.3Z.ai73.1/1002 independent benchmarks$0.36 per solved task
Shared results
76
DeepSeek V4 Pro 0423 only
7
GLM 5.3 only
24
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 35.3 from 1 benchmark, GLM 5.3 73.1 from 2 benchmarks.
Widest category
Agentic work, 19.0 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: DeepSeek V4 Pro 0423 16.0% against GLM 5.3 49.0%, 33.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0423 $1.9105 against GLM 5.3 $1.40 per million output tokens, 1.4x 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 5.3Ties
Coding215
Intelligence02
Agentic work06
Reasoning151 tie
Math15
Knowledge27
Web design08
General120
All shared boards7681 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index215
Coding benchmarks for DeepSeek V4 Pro 0423 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0423GLM 5.3Leader
LiveBench codingNot measured82.8%Only GLM 5.3 measured
LMArena WebDev14471621GLM 5.3
AA Coding Index59.474.8GLM 5.3
LiveCodeBench (Vals AI)87.5%80.5%DeepSeek V4 Pro 0423
SWE-bench Verified (Vals AI)77.4%95.4%GLM 5.3
Terminal-Bench 4 (Vals AI)11.1%38.9%GLM 5.3
Vibe Code Bench (Vals AI)49.9%78.1%GLM 5.3
Code migration (Vals AI)26.2%44.2%GLM 5.3
ProgramBench (Vals AI)0.0%1.5%GLM 5.3
IOI (Vals AI)Not measured68.4%Only GLM 5.3 measured
Terminal-Bench 2.1 (Vals AI)50.2%71.5%GLM 5.3
Vibe Code Bench 1-100 (Vals AI)Not measured20.0%Only GLM 5.3 measured
SkillsBench (Vals AI)51.3%47.5%DeepSeek V4 Pro 0423
CyberBench (Vals AI)Not measured72.1%Only GLM 5.3 measured
SciCodeNot measured59.0%Only GLM 5.3 measured
FrontierCode17.6%40.1%GLM 5.3
FrontierSWENot measured30.2%Only GLM 5.3 measured
WeirdML48.9%75.4%GLM 5.3
ALE-Bench1006.11317.4GLM 5.3
LMArena Text: coding14701497GLM 5.3
LMArena Text: software and IT14691493GLM 5.3
LMArena WebDev: React14411641GLM 5.3
LMArena WebDev: HTML14351595GLM 5.3
Neither model has a result on the other 15 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V4 Pro 0423 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0423GLM 5.3Leader
AA Intelligence Index30.444.8GLM 5.3
Epoch Capabilities Index149.1156.0GLM 5.3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index06
Agentic work benchmarks for DeepSeek V4 Pro 0423 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0423GLM 5.3Leader
AA Agentic Index26.353.1GLM 5.3
Design Arena: agents building web apps1000Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: agents building full-stack apps948Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: agents building mobile appsNot measured1194Only GLM 5.3 measured
Design Arena: agents building Godot games1059Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: HTML slidesNot measured1189Only GLM 5.3 measured
Design Arena: PowerPoint slidesNot measured1255Only GLM 5.3 measured
LiveBench researchNot measured73.2%Only GLM 5.3 measured
LiveBench browserNot measured0.0%Only GLM 5.3 measured
LiveBench long agenticNot measured35.9%Only GLM 5.3 measured
SREBench (Vals AI)Not measured9.2%Only GLM 5.3 measured
Finance Agent (Vals AI)44.1%55.8%GLM 5.3
Tax Agent Bench (Vals AI)25.2%39.7%GLM 5.3
Legal Research Bench (Vals AI)23.1%49.0%GLM 5.3
Harvey's Legal Agent Benchmark (Vals AI)Not measured14.6%Only GLM 5.3 measured
Excel Modeling Benchmark (Vals AI)51.6%56.3%GLM 5.3
Terminal-Bench-Science (Vals AI)Not measured5.7%Only GLM 5.3 measured
APEX-AgentsNot measured56.6%Only GLM 5.3 measured
Vending-Bench 2$3,285$8,164GLM 5.3
Neither model has a result on the other 20 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index15
Reasoning benchmarks for DeepSeek V4 Pro 0423 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0423GLM 5.3Leader
GPQA Diamond89.4%88.1%DeepSeek V4 Pro 0423
LiveBench reasoningNot measured85.8%Only GLM 5.3 measured
MysteryMechanism (Vals AI)Not measured23.0%Only GLM 5.3 measured
GPQA Diamond (Artificial Analysis run)Not measured91.7%Only GLM 5.3 measured
Humanity's Last Exam (Artificial Analysis run)Not measured42.3%Only GLM 5.3 measured
GPQA Diamond (Epoch AI run)90.9%90.9%Tie
Chess puzzles19.0%37.0%GLM 5.3
Mystery game puzzles17.0%33.0%GLM 5.3
LMArena Text: hard prompts14611490GLM 5.3
LMArena Text: expert14631514GLM 5.3
LMArena Text: hard prompts in English14661496GLM 5.3
Neither model has a result on the other 10 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index15
Math benchmarks for DeepSeek V4 Pro 0423 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0423GLM 5.3Leader
OTIS Mock AIME96.7%91.1%DeepSeek V4 Pro 0423
FrontierMath, tiers 1 to 345.3%68.8%GLM 5.3
FrontierMath, tier 42.4%29.3%GLM 5.3
ProofBench16.0%49.0%GLM 5.3
LMArena Text: math14431495GLM 5.3
LMArena Text: mathematical work14551497GLM 5.3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index27
Knowledge benchmarks for DeepSeek V4 Pro 0423 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0423GLM 5.3Leader
MMLU Pro87.3%86.8%DeepSeek V4 Pro 0423
LegalBench (Vals AI)80.3%84.8%GLM 5.3
CaseLaw (Vals AI)59.4%Not measuredOnly DeepSeek V4 Pro 0423 measured
CorpFin (Vals AI)61.4%Not measuredOnly DeepSeek V4 Pro 0423 measured
TaxEval (Vals AI)72.1%72.4%GLM 5.3
MedCode (Vals AI)40.5%42.9%GLM 5.3
SimpleQA Verified47.0%41.0%DeepSeek V4 Pro 0423
LMArena Text: science14701498GLM 5.3
LMArena Text: medicine and healthcare14661481GLM 5.3
LMArena Text: legal and government14641473GLM 5.3
LMArena Text: business and finance14431459GLM 5.3
Neither model has a result on the other 6 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 5.3
BenchmarkDeepSeek V4 Pro 0423GLM 5.3Leader
Design Arena: websites12351295GLM 5.3
Design Arena: UI components12211314GLM 5.3
Design Arena: game dev12291311GLM 5.3
Design Arena: data viz12031260GLM 5.3
Design Arena: 3D12541332GLM 5.3
Design Arena: all code categories12401304GLM 5.3
Design Arena: SVG11391292GLM 5.3
Design Arena: ASCII art11481213GLM 5.3
LiveBench designNot measured77.3%Only GLM 5.3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index120
General benchmarks for DeepSeek V4 Pro 0423 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0423GLM 5.3Leader
Vals IndexNot measured59.7%Only GLM 5.3 measured
LiveBench data analysisNot measured70.2%Only GLM 5.3 measured
Public Benefits Bench (Vals AI)62.9%68.5%GLM 5.3
MedScribe (Vals AI)75.1%88.8%GLM 5.3
Long context reasoning (AA-LCR)Not measured79.7%Only GLM 5.3 measured
DTBench90.7%87.7%DeepSeek V4 Pro 0423
LMCA41.2%55.5%GLM 5.3
Surface Evolver Bench40.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
CL-bench Life13.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text14511474GLM 5.3
LMArena Text: instruction following14451479GLM 5.3
LMArena Text: creative writing14461458GLM 5.3
LMArena Text: English14591482GLM 5.3
LMArena Text: non-English14391459GLM 5.3
LMArena Text: Chinese14811532GLM 5.3
LMArena Text: German14581488GLM 5.3
LMArena Text: Japanese14461460GLM 5.3
LMArena Text: Korean14091460GLM 5.3
LMArena Text: French14731503GLM 5.3
LMArena Text: Spanish14571462GLM 5.3
LMArena Text: Russian14531469GLM 5.3
LMArena Text: Polish14611466GLM 5.3
LMArena Text: multi-turn14681472GLM 5.3
LMArena Text: longer queries14581483GLM 5.3
LMArena Text: writing and language14471469GLM 5.3
LMArena Text: entertainment and media14311447GLM 5.3
Neither model has a result on the other 20 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 5.3
BenchmarkDeepSeek V4 Pro 0423GLM 5.3Leader
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$0.0019Fits in one request
GLM 5.3$0.0008Fits in one request

GLM 5.3 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0423$0.053Fits in one request
GLM 5.3$0.0081Fits in one request

GLM 5.3 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0423$0.210Fits in one request
GLM 5.3$0.030Fits in one request

GLM 5.3 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 5.3
SpecificationDeepSeek V4 Pro 0423Z.ai GLM 5.3
MakerDeepSeekZ.ai
WeightsOpen weightsOpen weights
ReleasedApril 24, 2026August 18, 2026
Context window1.05M1.05M
Input $/Mtok$0.9553$0.079
Output $/Mtok$1.9105$1.40
Coding index35.373.1
Independent measurements behind it12
Cost per solved task$0.57$0.36
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0423 better than GLM 5.3 for coding?

Pick GLM 5.3 for coding: it scores 73.1 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423. Pick DeepSeek V4 Pro 0423 when what matters is LiveCodeBench (Vals AI) or SkillsBench (Vals AI), where it leads.

Which is cheaper, DeepSeek V4 Pro 0423 or GLM 5.3?

DeepSeek V4 Pro 0423 costs $0.9553 per million input tokens and $1.9105 per million output tokens; GLM 5.3 costs $0.079 and $1.40. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0423 costs $0.57 and GLM 5.3 $0.36.

Which has the bigger context window, DeepSeek V4 Pro 0423 or GLM 5.3?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4 Pro 0423 vs GLM 5.3 comparison based on?

76 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0423's coding index rests on 1 independent benchmark and GLM 5.3's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next