Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0813 vs GLM 5.3

GLM 5.3 leads DeepSeek V4 Pro 0813 on coding, 70.6 to 56.1 on the Vibe Coding Index, and DeepSeek V4 Pro 0813 costs 2.2x less per output token ($1.98 vs $4.40 per million). Updated October 21, 2026; 75 benchmarks have a result for both.

Replace DeepSeek V4 Pro 0813 Replace GLM 5.3
DeepSeek V4 Pro 0813DeepSeek
Coding
56.1
Overall
60.8
Output $/M
$1.98
18
GLM 5.3Z.ai
Coding
70.6
Overall
67.9
Output $/M
$4.40
57
vs boards won of 75 shared

DeepSeek V4 Pro 0813 or GLM 5.3: which to pick

Pick GLM 5.3 for coding: it scores 70.6 on the Vibe Coding Index against 56.1 for DeepSeek V4 Pro 0813.

Pick DeepSeek V4 Pro 0813 for output tokens 2.2x cheaper ($1.98 vs $4.40 per million) and a lower cost per solved task ($0.10 against $0.36).

Model ADeepSeek V4 Pro 0813DeepSeek56.1/1005 independent benchmarks$0.10 per solved taskModel BGLM 5.3Z.ai70.6/1006 independent benchmarks$0.36 per solved task
Shared results
75
DeepSeek V4 Pro 0813 only
3
GLM 5.3 only
25
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
DeepSeek V4 Pro 0813 56.1 from 5 benchmarks, GLM 5.3 70.6 from 6 benchmarks.
Widest category
Coding, 7.6 points apart on average over 21 shared benchmarks.
Widest single gap
Terminal-Bench 4 (Vals AI): DeepSeek V4 Pro 0813 14.1% against GLM 5.3 38.9%, 33.0 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0813 $1.98 against GLM 5.3 $4.40 per million output tokens, 2.2x 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 0813BarsGLM 5.3Ties
Coding615
Intelligence02
Agentic work09
Reasoning54
Math24
Knowledge36
General217
All shared boards1857
CodingLike-for-likeSix of these boards feed the Vibe Coding Index615
Coding benchmarks for DeepSeek V4 Pro 0813 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0813GLM 5.3Leader
LiveBench codingNot measured82.8%Only GLM 5.3 measured
LMArena WebDev15821621GLM 5.3
AA Coding Index68.874.8GLM 5.3
LiveCodeBench (Vals AI)87.5%80.5%DeepSeek V4 Pro 0813
SWE-bench Verified (Vals AI)96.4%95.4%DeepSeek V4 Pro 0813
Terminal-Bench 4 (Vals AI)14.1%38.9%GLM 5.3
Vibe Code Bench (Vals AI)82.3%78.1%DeepSeek V4 Pro 0813
Code migration (Vals AI)41.5%44.2%GLM 5.3
ProgramBench (Vals AI)0.0%1.5%GLM 5.3
IOI (Vals AI)51.6%68.4%GLM 5.3
Terminal-Bench 2.1 (Vals AI)54.7%71.5%GLM 5.3
Vibe Code Bench 1-100 (Vals AI)17.5%20.0%GLM 5.3
SkillsBench (Vals AI)53.8%47.5%DeepSeek V4 Pro 0813
CyberBench (Vals AI)72.9%72.1%DeepSeek V4 Pro 0813
SciCode51.0%59.0%GLM 5.3
FrontierCode28.5%40.1%GLM 5.3
FrontierSWENot measured30.2%Only GLM 5.3 measured
WeirdML66.2%75.4%GLM 5.3
ALE-Bench1403.21317.4DeepSeek V4 Pro 0813
LMArena Text: coding14691497GLM 5.3
LMArena Text: software and IT14621493GLM 5.3
LMArena WebDev: React15881641GLM 5.3
LMArena WebDev: HTML15661595GLM 5.3
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for DeepSeek V4 Pro 0813 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0813GLM 5.3Leader
AA Intelligence Index36.044.8GLM 5.3
Epoch Capabilities Index155.6156.0GLM 5.3
Agentic workLike-for-likePublic boards, shown as published, kept out of the index09
Agentic work benchmarks for DeepSeek V4 Pro 0813 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0813GLM 5.3Leader
AA Agentic Index41.353.1GLM 5.3
Design Arena: agents building mobile appsNot measured1194Only GLM 5.3 measured
Design Arena: HTML slidesNot measured1189Only GLM 5.3 measured
Design Arena: PowerPoint slidesNot measured1254Only 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)1.9%9.2%GLM 5.3
Finance Agent (Vals AI)50.4%55.8%GLM 5.3
Tax Agent Bench (Vals AI)26.8%39.7%GLM 5.3
Legal Research Bench (Vals AI)40.9%49.0%GLM 5.3
Harvey's Legal Agent Benchmark (Vals AI)10.8%14.6%GLM 5.3
Excel Modeling Benchmark (Vals AI)52.8%56.3%GLM 5.3
Terminal-Bench-Science (Vals AI)4.3%5.7%GLM 5.3
APEX-Agents47.3%56.6%GLM 5.3
Vending-Bench 2Not measured$8,164Only GLM 5.3 measured
Neither model has a result on the other 25 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index54
Reasoning benchmarks for DeepSeek V4 Pro 0813 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0813GLM 5.3Leader
GPQA Diamond92.4%88.1%DeepSeek V4 Pro 0813
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)92.8%91.7%DeepSeek V4 Pro 0813
Humanity's Last Exam (Artificial Analysis run)41.0%42.3%GLM 5.3
GPQA Diamond (Epoch AI run)91.7%90.9%DeepSeek V4 Pro 0813
ARC-AGI90.5%Not measuredOnly DeepSeek V4 Pro 0813 measured
ARC-AGI-261.3%Not measuredOnly DeepSeek V4 Pro 0813 measured
Chess puzzles46.0%37.0%DeepSeek V4 Pro 0813
Mystery game puzzles43.0%33.0%DeepSeek V4 Pro 0813
LMArena Text: hard prompts14581490GLM 5.3
LMArena Text: expert14591514GLM 5.3
LMArena Text: hard prompts in English14631496GLM 5.3
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index24
Math benchmarks for DeepSeek V4 Pro 0813 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0813GLM 5.3Leader
OTIS Mock AIME98.6%91.1%DeepSeek V4 Pro 0813
FrontierMath, tiers 1 to 364.6%68.8%GLM 5.3
FrontierMath, tier 426.8%29.3%GLM 5.3
ProofBench50.0%49.0%DeepSeek V4 Pro 0813
LMArena Text: math14411495GLM 5.3
LMArena Text: mathematical work14431497GLM 5.3
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index36
Knowledge benchmarks for DeepSeek V4 Pro 0813 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0813GLM 5.3Leader
MMLU Pro87.0%86.8%DeepSeek V4 Pro 0813
LegalBench (Vals AI)82.4%84.8%GLM 5.3
CorpFin (Vals AI)65.4%Not measuredOnly DeepSeek V4 Pro 0813 measured
TaxEval (Vals AI)73.1%72.4%DeepSeek V4 Pro 0813
MedCode (Vals AI)42.5%42.9%GLM 5.3
SimpleQA Verified52.9%41.0%DeepSeek V4 Pro 0813
LMArena Text: science14571498GLM 5.3
LMArena Text: medicine and healthcare14461481GLM 5.3
LMArena Text: legal and government14591473GLM 5.3
LMArena Text: business and finance14421459GLM 5.3
Neither model has a result on the other 8 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for DeepSeek V4 Pro 0813 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0813GLM 5.3Leader
Design Arena: websitesNot measured1295Only GLM 5.3 measured
Design Arena: UI componentsNot measured1314Only GLM 5.3 measured
Design Arena: game devNot measured1311Only GLM 5.3 measured
Design Arena: data vizNot measured1259Only GLM 5.3 measured
Design Arena: 3DNot measured1332Only GLM 5.3 measured
Design Arena: all code categoriesNot measured1304Only GLM 5.3 measured
Design Arena: SVGNot measured1293Only GLM 5.3 measured
Design Arena: ASCII artNot measured1213Only GLM 5.3 measured
LiveBench designNot measured77.3%Only GLM 5.3 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index217
General benchmarks for DeepSeek V4 Pro 0813 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0813GLM 5.3Leader
Vals Index53.0%59.7%GLM 5.3
LiveBench data analysisNot measured70.2%Only GLM 5.3 measured
Public Benefits Bench (Vals AI)Not measured68.5%Only GLM 5.3 measured
MedScribe (Vals AI)80.2%88.8%GLM 5.3
Long context reasoning (AA-LCR)80.3%79.7%DeepSeek V4 Pro 0813
DTBench93.9%87.7%DeepSeek V4 Pro 0813
LMCA45.5%55.5%GLM 5.3
LMArena Text14461474GLM 5.3
LMArena Text: instruction following14481479GLM 5.3
LMArena Text: creative writing14391458GLM 5.3
LMArena Text: English14571482GLM 5.3
LMArena Text: non-English14311459GLM 5.3
LMArena Text: Chinese14811532GLM 5.3
LMArena Text: GermanNot measured1488Only GLM 5.3 measured
LMArena Text: JapaneseNot measured1460Only GLM 5.3 measured
LMArena Text: Korean14491460GLM 5.3
LMArena Text: French14461503GLM 5.3
LMArena Text: Spanish14351462GLM 5.3
LMArena Text: Russian14481469GLM 5.3
LMArena Text: PolishNot measured1466Only GLM 5.3 measured
LMArena Text: multi-turn14541472GLM 5.3
LMArena Text: longer queries14581483GLM 5.3
LMArena Text: writing and language14431469GLM 5.3
LMArena Text: entertainment and media14241447GLM 5.3
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 DeepSeek V4 Pro 0813 and GLM 5.3
BenchmarkDeepSeek V4 Pro 0813GLM 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 0813$0.0016Fits in one request
GLM 5.3$0.0036Fits in one request

DeepSeek V4 Pro 0813 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0813$0.039Fits in one request
GLM 5.3$0.083Fits in one request

DeepSeek V4 Pro 0813 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0813$0.152Fits in one request
GLM 5.3$0.324Fits in one request

DeepSeek V4 Pro 0813 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 0813 and GLM 5.3
SpecificationDeepSeek V4 Pro 0813Z.ai GLM 5.3
MakerDeepSeekZ.ai
WeightsOpen weightsOpen weights
ReleasedAugust 12, 2026August 18, 2026
Context window1.05M1.05M
Input $/Mtok$0.66$1.40
Output $/Mtok$1.98$4.40
Coding index56.170.6
Independent measurements behind it56
Cost per solved task$0.10$0.36
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0813 better than GLM 5.3 for coding?

Pick GLM 5.3 for coding: it scores 70.6 on the Vibe Coding Index against 56.1 for DeepSeek V4 Pro 0813. Pick DeepSeek V4 Pro 0813 for output tokens 2.2x cheaper ($1.98 vs $4.40 per million) and a lower cost per solved task ($0.10 against $0.36).

Which is cheaper, DeepSeek V4 Pro 0813 or GLM 5.3?

DeepSeek V4 Pro 0813 costs $0.66 per million input tokens and $1.98 per million output tokens; GLM 5.3 costs $1.40 and $4.40. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0813 costs $0.10 and GLM 5.3 $0.36.

Which has the bigger context window, DeepSeek V4 Pro 0813 or GLM 5.3?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4 Pro 0813 vs GLM 5.3 comparison based on?

75 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0813's coding index rests on 5 independent benchmarks and GLM 5.3's on 6. 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-0813-vs-glm-5-3" title="DeepSeek V4 Pro 0813 vs GLM 5.3, 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-0813-vs-glm-5-3">LLMBenchmark.ai, DeepSeek V4 Pro 0813 vs GLM 5.3</a></p>