Enter opens the highlighted result. Esc closes.

DeepSeek V3.1 vs GLM 5.1

GLM 5.1 leads DeepSeek V3.1 on the Artificial Analysis Intelligence Index, 26.1 to 13.7, and DeepSeek V3.1 costs 2.9x less per output token ($1.50 vs $4.40 per million). Updated October 21, 2026; 8 benchmarks have a result for both.

Replace DeepSeek V3.1 Replace GLM 5.1
DeepSeek V3.1DeepSeek
Coding
No data
Overall
13.7
Output $/M
$1.50
0
GLM 5.1Z.ai
Coding
49.2
Overall
26.1
Output $/M
$4.40
8
vs boards won of 8 shared

DeepSeek V3.1 or GLM 5.1: which to pick

Only GLM 5.1 has a coding score, 49.2 on the Vibe Coding Index; DeepSeek V3.1 has none, so the two cannot be ranked on coding.

Pick DeepSeek V3.1 for output tokens 2.9x cheaper ($1.50 vs $4.40 per million).

Model ADeepSeek V3.1DeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGLM 5.1Z.ai49.2/1003 independent benchmarks$0.60 per solved task
Shared results
8
DeepSeek V3.1 only
2
GLM 5.1 only
81
Like-for-like categories
2 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 V3.1 not benchmarked, GLM 5.1 49.2 from 3 benchmarks.
Widest category
Web design, 26.6 points apart on average over 7 shared benchmarks.
Widest single gap
Design Arena: data viz: DeepSeek V3.1 1095 against GLM 5.1 1366, 33.9 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.1 $1.50 against GLM 5.1 $4.40 per million output tokens, 2.9x apart.
Context window
DeepSeek V3.1 takes 164K tokens, GLM 5.1 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 V3.1BarsGLM 5.1Ties
Intelligence01
Web design07
All shared boards08
CodingDirectional onlySix of these boards feed the Vibe Coding Index16 boards, none shared
Coding benchmarks for DeepSeek V3.1 and GLM 5.1
BenchmarkDeepSeek V3.1GLM 5.1Leader
LMArena WebDevNot measured1508Only GLM 5.1 measured
AA Coding IndexNot measured55.8Only GLM 5.1 measured
LiveCodeBench (Vals AI)Not measured81.4%Only GLM 5.1 measured
SWE-bench Verified (Vals AI)Not measured76.4%Only GLM 5.1 measured
Vibe Code Bench (Vals AI)Not measured31.5%Only GLM 5.1 measured
Code migration (Vals AI)Not measured25.8%Only GLM 5.1 measured
ProgramBench (Vals AI)Not measured0.0%Only GLM 5.1 measured
Terminal-Bench 2.1 (Vals AI)Not measured56.9%Only GLM 5.1 measured
SciCodeNot measured44.8%Only GLM 5.1 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured43.2%Only GLM 5.1 measured
WeirdMLNot measured57.1%Only GLM 5.1 measured
ALE-BenchNot measured887.1Only GLM 5.1 measured
LMArena Text: codingNot measured1485Only GLM 5.1 measured
LMArena Text: software and ITNot measured1484Only GLM 5.1 measured
LMArena WebDev: ReactNot measured1505Only GLM 5.1 measured
LMArena WebDev: HTMLNot measured1508Only GLM 5.1 measured
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for DeepSeek V3.1 and GLM 5.1
BenchmarkDeepSeek V3.1GLM 5.1Leader
AA Intelligence Index13.726.1GLM 5.1
Epoch Capabilities IndexNot measured149.8Only GLM 5.1 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index15 boards, none shared
Agentic work benchmarks for DeepSeek V3.1 and GLM 5.1
BenchmarkDeepSeek V3.1GLM 5.1Leader
AA Agentic IndexNot measured23.9Only GLM 5.1 measured
Design Arena: agents building web appsNot measured1175Only GLM 5.1 measured
Design Arena: agents building full-stack appsNot measured1167Only GLM 5.1 measured
Design Arena: agents building mobile appsNot measured1162Only GLM 5.1 measured
Design Arena: agents building Android appsNot measured1180Only GLM 5.1 measured
Design Arena: agents building Godot gamesNot measured1053Only GLM 5.1 measured
Design Arena: agents building gamesNot measured1164Only GLM 5.1 measured
Design Arena: HTML slidesNot measured1170Only GLM 5.1 measured
Design Arena: PowerPoint slidesNot measured1188Only GLM 5.1 measured
Design Arena: spreadsheetsNot measured1315Only GLM 5.1 measured
Finance Agent (Vals AI)Not measured44.8%Only GLM 5.1 measured
Legal Research Bench (Vals AI)Not measured27.9%Only GLM 5.1 measured
τ²-Bench TelecomNot measured97.7%Only GLM 5.1 measured
APEX-AgentsNot measured40.9%Only GLM 5.1 measured
Vending-Bench 2Not measured$5,634Only GLM 5.1 measured
Neither model has a result on the other 24 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Reasoning benchmarks for DeepSeek V3.1 and GLM 5.1
BenchmarkDeepSeek V3.1GLM 5.1Leader
GPQA DiamondNot measured84.5%Only GLM 5.1 measured
GPQA Diamond (Artificial Analysis run)Not measured86.8%Only GLM 5.1 measured
Humanity's Last Exam (Artificial Analysis run)Not measured30.1%Only GLM 5.1 measured
GPQA Diamond (Epoch AI run)Not measured89.9%Only GLM 5.1 measured
SimpleBenchNot measured55.1%Only GLM 5.1 measured
Chess puzzlesNot measured20.0%Only GLM 5.1 measured
LMArena Text: hard promptsNot measured1473Only GLM 5.1 measured
LMArena Text: expertNot measured1478Only GLM 5.1 measured
LMArena Text: hard prompts in EnglishNot measured1482Only GLM 5.1 measured
Neither model has a result on the other 12 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Math benchmarks for DeepSeek V3.1 and GLM 5.1
BenchmarkDeepSeek V3.1GLM 5.1Leader
AIMENot measured91.9%Only GLM 5.1 measured
OTIS Mock AIMENot measured93.3%Only GLM 5.1 measured
FrontierMath, tiers 1 to 3Not measured36.8%Only GLM 5.1 measured
ProofBenchNot measured22.2%Only GLM 5.1 measured
LMArena Text: mathNot measured1473Only GLM 5.1 measured
LMArena Text: mathematical workNot measured1470Only GLM 5.1 measured
Neither model has a result on the other 7 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
Knowledge benchmarks for DeepSeek V3.1 and GLM 5.1
BenchmarkDeepSeek V3.1GLM 5.1Leader
MMLU ProNot measured86.9%Only GLM 5.1 measured
LegalBench (Vals AI)Not measured84.4%Only GLM 5.1 measured
CaseLaw (Vals AI)Not measured51.5%Only GLM 5.1 measured
CorpFin (Vals AI)Not measured64.5%Only GLM 5.1 measured
TaxEval (Vals AI)Not measured71.2%Only GLM 5.1 measured
MedCode (Vals AI)Not measured41.6%Only GLM 5.1 measured
SimpleQA VerifiedNot measured34.0%Only GLM 5.1 measured
LMArena Text: scienceNot measured1478Only GLM 5.1 measured
LMArena Text: medicine and healthcareNot measured1474Only GLM 5.1 measured
LMArena Text: legal and governmentNot measured1465Only GLM 5.1 measured
LMArena Text: business and financeNot measured1452Only GLM 5.1 measured
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for DeepSeek V3.1 and GLM 5.1
BenchmarkDeepSeek V3.1GLM 5.1Leader
Design Arena: websites11231290GLM 5.1
Design Arena: UI components10851292GLM 5.1
Design Arena: game dev10841265GLM 5.1
Design Arena: data viz10951366GLM 5.1
Design Arena: 3D10771336GLM 5.1
Design Arena: all code categories11121268GLM 5.1
Design Arena: SVG9671218GLM 5.1
Design Arena: ASCII artNot measured1142Only GLM 5.1 measured
Neither model has a result on the other 1 board here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index24 boards, none shared
General benchmarks for DeepSeek V3.1 and GLM 5.1
BenchmarkDeepSeek V3.1GLM 5.1Leader
Public Benefits Bench (Vals AI)Not measured61.8%Only GLM 5.1 measured
MedScribe (Vals AI)Not measured72.3%Only GLM 5.1 measured
IFBenchNot measured76.3%Only GLM 5.1 measured
Long context reasoning (AA-LCR)Not measured73.7%Only GLM 5.1 measured
DTBench82.7%Not measuredOnly DeepSeek V3.1 measured
LMCA24.3%Not measuredOnly DeepSeek V3.1 measured
ExploitBenchNot measured18.1%Only GLM 5.1 measured
LMArena TextNot measured1463Only GLM 5.1 measured
LMArena Text: instruction followingNot measured1453Only GLM 5.1 measured
LMArena Text: creative writingNot measured1453Only GLM 5.1 measured
LMArena Text: EnglishNot measured1476Only GLM 5.1 measured
LMArena Text: non-EnglishNot measured1448Only GLM 5.1 measured
LMArena Text: ChineseNot measured1515Only GLM 5.1 measured
LMArena Text: GermanNot measured1467Only GLM 5.1 measured
LMArena Text: JapaneseNot measured1435Only GLM 5.1 measured
LMArena Text: KoreanNot measured1424Only GLM 5.1 measured
LMArena Text: FrenchNot measured1470Only GLM 5.1 measured
LMArena Text: SpanishNot measured1468Only GLM 5.1 measured
LMArena Text: RussianNot measured1454Only GLM 5.1 measured
LMArena Text: PolishNot measured1449Only GLM 5.1 measured
LMArena Text: multi-turnNot measured1473Only GLM 5.1 measured
LMArena Text: longer queriesNot measured1467Only GLM 5.1 measured
LMArena Text: writing and languageNot measured1454Only GLM 5.1 measured
LMArena Text: entertainment and mediaNot measured1442Only GLM 5.1 measured
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 V3.1 and GLM 5.1
BenchmarkDeepSeek V3.1GLM 5.1Leader
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 V3.1$0.0013Fits in one request
GLM 5.1$0.0036Fits in one request

DeepSeek V3.1 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.1$0.032Fits in one request
GLM 5.1$0.083Fits in one request

DeepSeek V3.1 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.1$0.125Exceeds the context window
GLM 5.1$0.324Exceeds the context window

DeepSeek V3.1 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 V3.1 and GLM 5.1
SpecificationDeepSeek V3.1Z.ai GLM 5.1
MakerDeepSeekZ.ai
WeightsOpen weightsOpen weights
ReleasedAugust 21, 2025April 7, 2026
Context window164K205K
Input $/Mtok$0.55$1.40
Output $/Mtok$1.50$4.40
Coding indexNot benchmarked49.2
Independent measurements behind it03
Cost per solved taskNot computable$0.60
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.1 better than GLM 5.1 for coding?

Only GLM 5.1 has a coding score, 49.2 on the Vibe Coding Index; DeepSeek V3.1 has none, so the two cannot be ranked on coding. Pick DeepSeek V3.1 for output tokens 2.9x cheaper ($1.50 vs $4.40 per million).

Which is cheaper, DeepSeek V3.1 or GLM 5.1?

DeepSeek V3.1 costs $0.55 per million input tokens and $1.50 per million output tokens; GLM 5.1 costs $1.40 and $4.40. Cost per solved task is known for GLM 5.1 only.

Which has the bigger context window, DeepSeek V3.1 or GLM 5.1?

GLM 5.1, with 205K tokens against 164K.

How many benchmarks is the DeepSeek V3.1 vs GLM 5.1 comparison based on?

8 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.1's coding index rests on 0 independent benchmarks and GLM 5.1's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next