Enter opens the highlighted result. Esc closes.

DeepSeek V3.1 vs GLM 5

GLM 5 leads DeepSeek V3.1 on the Artificial Analysis Intelligence Index, 27.9 to 13.7, and DeepSeek V3.1 costs 2.1x less per output token ($1.50 vs $3.20 per million). Updated October 21, 2026; 8 benchmarks have a result for both.

Replace DeepSeek V3.1 Replace GLM 5
DeepSeek V3.1DeepSeek
Coding
No data
Overall
13.7
Output $/M
$1.50
0
GLM 5Z.ai
Coding
41.7
Overall
27.9
Output $/M
$3.20
8
vs boards won of 8 shared

DeepSeek V3.1 or GLM 5: which to pick

Only GLM 5 has a coding score, 41.7 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 2.1x cheaper ($1.50 vs $3.20 per million).

Model ADeepSeek V3.1DeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGLM 5Z.ai41.7/1003 independent benchmarks$0.63 per solved task
Shared results
8
DeepSeek V3.1 only
2
GLM 5 only
67
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 41.7 from 3 benchmarks.
Widest category
Web design, 18.6 points apart on average over 7 shared benchmarks.
Widest single gap
Design Arena: SVG: DeepSeek V3.1 967 against GLM 5 1168, 25.1 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.1 $1.50 against GLM 5 $3.20 per million output tokens, 2.1x apart.
Context window
DeepSeek V3.1 takes 164K tokens, GLM 5 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 5Ties
Intelligence01
Web design07
All shared boards08
CodingDirectional onlySix of these boards feed the Vibe Coding Index14 boards, none shared
Coding benchmarks for DeepSeek V3.1 and GLM 5
BenchmarkDeepSeek V3.1GLM 5Leader
SWE-bench VerifiedNot measured72.8%Only GLM 5 measured
SWE-bench MultilingualNot measured69.7%Only GLM 5 measured
LMArena WebDevNot measured1435Only GLM 5 measured
LiveCodeBench (Vals AI)Not measured81.9%Only GLM 5 measured
SWE-bench Verified (Vals AI)Not measured71.4%Only GLM 5 measured
Vibe Code Bench (Vals AI)Not measured23.4%Only GLM 5 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured43.2%Only GLM 5 measured
Terminal-BenchNot measured52.4%Only GLM 5 measured
WeirdMLNot measured48.2%Only GLM 5 measured
ALE-BenchNot measured765.6Only GLM 5 measured
LMArena Text: codingNot measured1461Only GLM 5 measured
LMArena Text: software and ITNot measured1460Only GLM 5 measured
LMArena WebDev: ReactNot measured1424Only GLM 5 measured
LMArena WebDev: HTMLNot measured1450Only GLM 5 measured
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for DeepSeek V3.1 and GLM 5
BenchmarkDeepSeek V3.1GLM 5Leader
AA Intelligence Index13.727.9GLM 5
Epoch Capabilities IndexNot measured145.8Only GLM 5 measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Agentic work benchmarks for DeepSeek V3.1 and GLM 5
BenchmarkDeepSeek V3.1GLM 5Leader
Design Arena: agents building full-stack appsNot measured1123Only GLM 5 measured
Design Arena: agents building mobile appsNot measured1136Only GLM 5 measured
Design Arena: agents building Android appsNot measured1146Only GLM 5 measured
Design Arena: agents building Godot gamesNot measured1144Only GLM 5 measured
Design Arena: HTML slidesNot measured1148Only GLM 5 measured
τ²-Bench TelecomNot measured98.2%Only GLM 5 measured
Vending-Bench 2Not measured$4,432Only GLM 5 measured
Neither model has a result on the other 32 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
Reasoning benchmarks for DeepSeek V3.1 and GLM 5
BenchmarkDeepSeek V3.1GLM 5Leader
GPQA DiamondNot measured83.3%Only GLM 5 measured
GPQA Diamond (Artificial Analysis run)Not measured82.0%Only GLM 5 measured
Humanity's Last Exam (Artificial Analysis run)Not measured29.3%Only GLM 5 measured
GPQA Diamond (Epoch AI run)Not measured87.8%Only GLM 5 measured
ARC-AGINot measured44.7%Only GLM 5 measured
ARC-AGI-2Not measured4.9%Only GLM 5 measured
SimpleBenchNot measured53.2%Only GLM 5 measured
LMArena Text: hard promptsNot measured1452Only GLM 5 measured
LMArena Text: expertNot measured1454Only GLM 5 measured
LMArena Text: hard prompts in EnglishNot measured1460Only GLM 5 measured
Neither model has a result on the other 11 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Math benchmarks for DeepSeek V3.1 and GLM 5
BenchmarkDeepSeek V3.1GLM 5Leader
AIMENot measured91.7%Only GLM 5 measured
OTIS Mock AIMENot measured80.0%Only GLM 5 measured
LMArena Text: mathNot measured1440Only GLM 5 measured
LMArena Text: mathematical workNot measured1451Only GLM 5 measured
Neither model has a result on the other 9 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
Knowledge benchmarks for DeepSeek V3.1 and GLM 5
BenchmarkDeepSeek V3.1GLM 5Leader
MMLU ProNot measured86.0%Only GLM 5 measured
LegalBench (Vals AI)Not measured84.1%Only GLM 5 measured
CaseLaw (Vals AI)Not measured52.5%Only GLM 5 measured
CorpFin (Vals AI)Not measured62.9%Only GLM 5 measured
TaxEval (Vals AI)Not measured70.0%Only GLM 5 measured
MedQA (Vals AI)Not measured94.3%Only GLM 5 measured
LMArena Text: scienceNot measured1460Only GLM 5 measured
LMArena Text: medicine and healthcareNot measured1455Only GLM 5 measured
LMArena Text: legal and governmentNot measured1453Only GLM 5 measured
LMArena Text: business and financeNot measured1430Only GLM 5 measured
Neither model has a result on the other 7 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
BenchmarkDeepSeek V3.1GLM 5Leader
Design Arena: websites11231247GLM 5
Design Arena: UI components10851230GLM 5
Design Arena: game dev10841234GLM 5
Design Arena: data viz10951228GLM 5
Design Arena: 3D10771229GLM 5
Design Arena: all code categories11121246GLM 5
Design Arena: SVG9671168GLM 5
Design Arena: ASCII artNot measured1147Only GLM 5 measured
Neither model has a result on the other 1 board here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index22 boards, none shared
General benchmarks for DeepSeek V3.1 and GLM 5
BenchmarkDeepSeek V3.1GLM 5Leader
IFBenchNot measured72.3%Only GLM 5 measured
Long context reasoning (AA-LCR)Not measured75.7%Only GLM 5 measured
DTBench82.7%Not measuredOnly DeepSeek V3.1 measured
LMCA24.3%Not measuredOnly DeepSeek V3.1 measured
CL-benchNot measured18.7%Only GLM 5 measured
LMArena TextNot measured1446Only GLM 5 measured
LMArena Text: instruction followingNot measured1428Only GLM 5 measured
LMArena Text: creative writingNot measured1438Only GLM 5 measured
LMArena Text: EnglishNot measured1458Only GLM 5 measured
LMArena Text: non-EnglishNot measured1430Only GLM 5 measured
LMArena Text: ChineseNot measured1511Only GLM 5 measured
LMArena Text: GermanNot measured1447Only GLM 5 measured
LMArena Text: JapaneseNot measured1416Only GLM 5 measured
LMArena Text: KoreanNot measured1423Only GLM 5 measured
LMArena Text: FrenchNot measured1456Only GLM 5 measured
LMArena Text: SpanishNot measured1454Only GLM 5 measured
LMArena Text: RussianNot measured1436Only GLM 5 measured
LMArena Text: PolishNot measured1434Only GLM 5 measured
LMArena Text: multi-turnNot measured1456Only GLM 5 measured
LMArena Text: longer queriesNot measured1446Only GLM 5 measured
LMArena Text: writing and languageNot measured1437Only GLM 5 measured
LMArena Text: entertainment and mediaNot measured1426Only GLM 5 measured
Neither model has a result on the other 24 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
BenchmarkDeepSeek V3.1GLM 5Leader
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$0.0026Fits 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$0.060Fits 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$0.232Exceeds 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
SpecificationDeepSeek V3.1Z.ai GLM 5
MakerDeepSeekZ.ai
WeightsOpen weightsOpen weights
ReleasedAugust 21, 2025February 11, 2026
Context window164K205K
Input $/Mtok$0.55$1.00
Output $/Mtok$1.50$3.20
Coding indexNot benchmarked41.7
Independent measurements behind it03
Cost per solved taskNot computable$0.63
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.1 better than GLM 5 for coding?

Only GLM 5 has a coding score, 41.7 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 2.1x cheaper ($1.50 vs $3.20 per million).

Which is cheaper, DeepSeek V3.1 or GLM 5?

DeepSeek V3.1 costs $0.55 per million input tokens and $1.50 per million output tokens; GLM 5 costs $1.00 and $3.20. Cost per solved task is known for GLM 5 only.

Which has the bigger context window, DeepSeek V3.1 or GLM 5?

GLM 5, with 205K tokens against 164K.

How many benchmarks is the DeepSeek V3.1 vs GLM 5 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's on 3. Where only one model has a result, the page says so instead of naming a winner.

Compare next