Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0813 vs GLM 5.2

Updated October 21, 2026. 70 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 0813 Replace GLM 5.2
DeepSeek V4 Pro 0813DeepSeek
Coding
54.6
Overall
36.0
Output $/M
$1.98
30
GLM 5.2Z.ai
Coding
57.7
Overall
33.7
Output $/M
$7.00
39
vs boards won of 70 shared, 1 tied

Decision reading

Pick GLM 5.2 for coding: it scores 57.7 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813.

Pick DeepSeek V4 Pro 0813 when output tokens cost 3.5x less, or when a solved task costs $0.10 against $0.86.

Model ADeepSeek V4 Pro 0813DeepSeek54.6/1001 independent benchmark$0.10 per solved taskModel BGLM 5.2Z.ai57.7/1001 independent benchmark$0.86 per solved task
Shared results
70
DeepSeek V4 Pro 0813 only
8
GLM 5.2 only
27
Like-for-like categories
7 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 0813 54.6 from 1 benchmark, GLM 5.2 57.7 from 1 benchmark.
Widest category
Reasoning, 11.1 points apart on average over 11 shared benchmarks.
Widest single gap
ARC-AGI-2: DeepSeek V4 Pro 0813 61.3% against GLM 5.2 22.8%, 38.5 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0813 $1.98 against GLM 5.2 $7.00 per million output tokens, 3.5x 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 0813BarsGLM 5.2Ties
Coding881 tie
Intelligence20
Agentic work51
Reasoning65
Math33
Knowledge37
General315
All shared boards30391 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index88
Coding benchmarks for DeepSeek V4 Pro 0813 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0813GLM 5.2Leader
LMArena WebDev15821604GLM 5.2
AA Coding Index68.868.8Tie
LiveCodeBench (Vals AI)87.5%69.5%DeepSeek V4 Pro 0813
SWE-bench Verified (Vals AI)96.4%82.8%DeepSeek V4 Pro 0813
Terminal-Bench 4 (Vals AI)14.1%Not measuredOnly DeepSeek V4 Pro 0813 measured
Vibe Code Bench (Vals AI)82.3%64.0%DeepSeek V4 Pro 0813
Code migration (Vals AI)41.5%37.9%DeepSeek V4 Pro 0813
ProgramBench (Vals AI)0.0%0.5%GLM 5.2
IOI (Vals AI)51.6%Not measuredOnly DeepSeek V4 Pro 0813 measured
Terminal-Bench 2.1 (Vals AI)54.7%67.8%GLM 5.2
Vibe Code Bench 1-100 (Vals AI)17.5%Not measuredOnly DeepSeek V4 Pro 0813 measured
SkillsBench (Vals AI)53.8%45.1%DeepSeek V4 Pro 0813
CyberBench (Vals AI)72.9%Not measuredOnly DeepSeek V4 Pro 0813 measured
SciCode51.0%51.2%GLM 5.2
Terminal-Bench Hard (Artificial Analysis run)Not measured50.8%Only GLM 5.2 measured
FrontierCode28.5%24.5%DeepSeek V4 Pro 0813
WeirdML66.2%70.1%GLM 5.2
ALE-Bench1403.21047.0DeepSeek V4 Pro 0813
LMArena Text: coding14691487GLM 5.2
LMArena Text: software and IT14621486GLM 5.2
LMArena WebDev: React15881617GLM 5.2
LMArena WebDev: HTML15661565DeepSeek V4 Pro 0813
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V4 Pro 0813 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0813GLM 5.2Leader
AA Intelligence Index36.033.7DeepSeek V4 Pro 0813
Epoch Capabilities Index155.6151.9DeepSeek V4 Pro 0813
Agentic workLike-for-likePublic boards, shown as published, kept out of the index51
Agentic work benchmarks for DeepSeek V4 Pro 0813 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0813GLM 5.2Leader
AA Agentic Index41.338.4DeepSeek V4 Pro 0813
Design Arena: agents building web appsNot measured1222Only GLM 5.2 measured
Design Arena: agents building full-stack appsNot measured1241Only GLM 5.2 measured
Design Arena: agents building mobile appsNot measured1160Only GLM 5.2 measured
Design Arena: agents building Android appsNot measured1184Only GLM 5.2 measured
Design Arena: agents building Godot gamesNot measured1142Only GLM 5.2 measured
Design Arena: agents building gamesNot measured1206Only GLM 5.2 measured
Design Arena: HTML slidesNot measured1175Only GLM 5.2 measured
Design Arena: PowerPoint slidesNot measured1195Only GLM 5.2 measured
SREBench (Vals AI)1.9%0.0%DeepSeek V4 Pro 0813
Finance Agent (Vals AI)50.4%49.7%DeepSeek V4 Pro 0813
Tax Agent Bench (Vals AI)26.8%Not measuredOnly DeepSeek V4 Pro 0813 measured
Legal Research Bench (Vals AI)40.9%31.3%DeepSeek V4 Pro 0813
Harvey's Legal Agent Benchmark (Vals AI)10.8%Not measuredOnly DeepSeek V4 Pro 0813 measured
Excel Modeling Benchmark (Vals AI)52.8%61.5%GLM 5.2
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly DeepSeek V4 Pro 0813 measured
τ²-Bench TelecomNot measured99.1%Only GLM 5.2 measured
APEX-Agents47.3%45.2%DeepSeek V4 Pro 0813
PostTrainBenchNot measured31.7%Only GLM 5.2 measured
Vending-Bench 2Not measured$8,314Only GLM 5.2 measured
Neither model has a result on the other 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index65
Reasoning benchmarks for DeepSeek V4 Pro 0813 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0813GLM 5.2Leader
GPQA Diamond92.4%85.6%DeepSeek V4 Pro 0813
GPQA Diamond (Artificial Analysis run)92.8%89.5%DeepSeek V4 Pro 0813
Humanity's Last Exam (Artificial Analysis run)41.0%41.1%GLM 5.2
GPQA Diamond (Epoch AI run)91.7%91.9%GLM 5.2
ARC-AGI90.5%77.0%DeepSeek V4 Pro 0813
ARC-AGI-261.3%22.8%DeepSeek V4 Pro 0813
SimpleBenchNot measured58.8%Only GLM 5.2 measured
Chess puzzles46.0%22.0%DeepSeek V4 Pro 0813
Mystery game puzzles43.0%19.0%DeepSeek V4 Pro 0813
EBR-benchNot measured9.5%Only GLM 5.2 measured
LMArena Text: hard prompts14581481GLM 5.2
LMArena Text: expert14591487GLM 5.2
LMArena Text: hard prompts in English14631481GLM 5.2
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index33
Math benchmarks for DeepSeek V4 Pro 0813 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0813GLM 5.2Leader
OTIS Mock AIME98.6%86.4%DeepSeek V4 Pro 0813
FrontierMath, tiers 1 to 364.6%59.2%DeepSeek V4 Pro 0813
FrontierMath, tier 426.8%29.3%GLM 5.2
ProofBench50.0%35.0%DeepSeek V4 Pro 0813
LMArena Text: math14411483GLM 5.2
LMArena Text: mathematical work14431489GLM 5.2
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index37
Knowledge benchmarks for DeepSeek V4 Pro 0813 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0813GLM 5.2Leader
MMLU Pro87.0%86.7%DeepSeek V4 Pro 0813
LegalBench (Vals AI)82.4%84.1%GLM 5.2
CorpFin (Vals AI)65.4%66.1%GLM 5.2
TaxEval (Vals AI)73.1%73.3%GLM 5.2
MedCode (Vals AI)42.5%40.8%DeepSeek V4 Pro 0813
SimpleQA Verified52.9%34.2%DeepSeek V4 Pro 0813
LMArena Text: science14571489GLM 5.2
LMArena Text: medicine and healthcare14461475GLM 5.2
LMArena Text: legal and government14591486GLM 5.2
LMArena Text: business and finance14421451GLM 5.2
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for DeepSeek V4 Pro 0813 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0813GLM 5.2Leader
Design Arena: websitesNot measured1285Only GLM 5.2 measured
Design Arena: UI componentsNot measured1296Only GLM 5.2 measured
Design Arena: game devNot measured1268Only GLM 5.2 measured
Design Arena: data vizNot measured1285Only GLM 5.2 measured
Design Arena: 3DNot measured1288Only GLM 5.2 measured
Design Arena: all code categoriesNot measured1288Only GLM 5.2 measured
Design Arena: SVGNot measured1214Only GLM 5.2 measured
Design Arena: ASCII artNot measured1190Only GLM 5.2 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index315
General benchmarks for DeepSeek V4 Pro 0813 and GLM 5.2
BenchmarkDeepSeek V4 Pro 0813GLM 5.2Leader
Vals Index53.0%Not measuredOnly DeepSeek V4 Pro 0813 measured
MedScribe (Vals AI)80.2%83.5%GLM 5.2
IFBenchNot measured73.3%Only GLM 5.2 measured
Long context reasoning (AA-LCR)80.3%78.3%DeepSeek V4 Pro 0813
DTBench93.9%93.6%DeepSeek V4 Pro 0813
LMCA45.5%45.8%GLM 5.2
Surface Evolver BenchNot measured55.6%Only GLM 5.2 measured
LMArena Text14461470GLM 5.2
LMArena Text: instruction following14481466GLM 5.2
LMArena Text: creative writing14391463GLM 5.2
LMArena Text: English14571475GLM 5.2
LMArena Text: non-English14311459GLM 5.2
LMArena Text: Chinese14811522GLM 5.2
LMArena Text: GermanNot measured1470Only GLM 5.2 measured
LMArena Text: JapaneseNot measured1450Only GLM 5.2 measured
LMArena Text: Korean14491440DeepSeek V4 Pro 0813
LMArena Text: French14461479GLM 5.2
LMArena Text: Spanish14351478GLM 5.2
LMArena Text: Russian14481468GLM 5.2
LMArena Text: PolishNot measured1456Only GLM 5.2 measured
LMArena Text: multi-turn14541469GLM 5.2
LMArena Text: longer queries14581480GLM 5.2
LMArena Text: writing and language14431463GLM 5.2
LMArena Text: entertainment and media14241450GLM 5.2
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 5.2
BenchmarkDeepSeek V4 Pro 0813GLM 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 0813$0.0016Fits in one request
GLM 5.2$0.0035Fits 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 5.2$0.023Fits in one request

GLM 5.2 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0813$0.152Fits in one request
GLM 5.2$0.077Fits in one request

GLM 5.2 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 5.2
SpecificationDeepSeek V4 Pro 0813Z.ai GLM 5.2
MakerDeepSeekZ.ai
WeightsOpen weightsOpen weights
ReleasedAugust 12, 2026June 16, 2026
Context window1.05M1.05M
Input $/Mtok$0.66$0.0341
Output $/Mtok$1.98$7.00
Coding index54.657.7
Independent measurements behind it11
Cost per solved task$0.10$0.86
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0813 better than GLM 5.2 for coding?

Pick GLM 5.2 for coding: it scores 57.7 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813. Pick DeepSeek V4 Pro 0813 when output tokens cost 3.5x less, or when a solved task costs $0.10 against $0.86.

Which is cheaper, DeepSeek V4 Pro 0813 or GLM 5.2?

DeepSeek V4 Pro 0813 costs $0.66 per million input tokens and $1.98 per million output tokens; GLM 5.2 costs $0.0341 and $7.00. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0813 costs $0.10 and GLM 5.2 $0.86.

Which has the bigger context window, DeepSeek V4 Pro 0813 or GLM 5.2?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4 Pro 0813 vs GLM 5.2 comparison based on?

70 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0813's coding index rests on 1 independent benchmark and GLM 5.2's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next