Enter opens the highlighted result. Esc closes.

DeepSeek V3.1 vs GLM 4.5

DeepSeek V3.1 leads GLM 4.5 on the Artificial Analysis Intelligence Index, 13.7 to 12.8, and DeepSeek V3.1 costs 1.5x less per output token ($1.50 vs $2.20 per million). Updated October 21, 2026; 9 benchmarks have a result for both.

Replace DeepSeek V3.1 Replace GLM 4.5
DeepSeek V3.1DeepSeek
Coding
No data
Overall
No data
Output $/M
$1.50
1
GLM 4.5Z.ai
Coding
No data
Overall
No data
Output $/M
$2.20
8
vs boards won of 9 shared

DeepSeek V3.1 or GLM 4.5: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick DeepSeek V3.1 for output tokens 1.5x cheaper ($1.50 vs $2.20 per million) and a larger context window (164K against 131K tokens).

Model ADeepSeek V3.1DeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGLM 4.5Z.aiNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
9
DeepSeek V3.1 only
2
GLM 4.5 only
52
Like-for-like categories
3 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 4.5 not benchmarked.
Widest category
Web design, 9.0 points apart on average over 7 shared benchmarks.
Widest single gap
Design Arena: SVG: DeepSeek V3.1 967 against GLM 4.5 1096, 16.1 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.1 $1.50 against GLM 4.5 $2.20 per million output tokens, 1.5x apart.
Context window
DeepSeek V3.1 takes 164K tokens, GLM 4.5 131K.

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 4.5Ties
Intelligence10
Reasoning01
Web design07
All shared boards18
CodingDirectional onlySix of these boards feed the Vibe Coding Index8 boards, none shared
Coding benchmarks for DeepSeek V3.1 and GLM 4.5
BenchmarkDeepSeek V3.1GLM 4.5Leader
SWE-bench VerifiedNot measured64.2%Only GLM 4.5 measured
LiveCodeBench (Vals AI)Not measured67.5%Only GLM 4.5 measured
LiveCodeBench (Artificial Analysis run)Not measured73.8%Only GLM 4.5 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured22.0%Only GLM 4.5 measured
WeirdMLNot measured40.6%Only GLM 4.5 measured
ALE-BenchNot measured344.8Only GLM 4.5 measured
LMArena Text: codingNot measured1434Only GLM 4.5 measured
LMArena Text: software and ITNot measured1440Only GLM 4.5 measured
Neither model has a result on the other 31 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for DeepSeek V3.1 and GLM 4.5
BenchmarkDeepSeek V3.1GLM 4.5Leader
AA Intelligence Index13.712.8DeepSeek V3.1
Neither model has a result on the other 1 board here
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Agentic work benchmarks for DeepSeek V3.1 and GLM 4.5
BenchmarkDeepSeek V3.1GLM 4.5Leader
τ²-Bench TelecomNot measured43.0%Only GLM 4.5 measured
Neither model has a result on the other 40 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
Reasoning benchmarks for DeepSeek V3.1 and GLM 4.5
BenchmarkDeepSeek V3.1GLM 4.5Leader
GPQA DiamondNot measured72.2%Only GLM 4.5 measured
GPQA Diamond (Artificial Analysis run)Not measured78.2%Only GLM 4.5 measured
Humanity's Last Exam (Artificial Analysis run)Not measured13.0%Only GLM 4.5 measured
LMArena Text: hard promptsNot measured1429Only GLM 4.5 measured
LMArena Text: expertNot measured1433Only GLM 4.5 measured
LMArena Text: hard prompts in EnglishNot measured1429Only GLM 4.5 measured
Kagi LLM Benchmark53.2%57.9%GLM 4.5
Neither model has a result on the other 15 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Math benchmarks for DeepSeek V3.1 and GLM 4.5
BenchmarkDeepSeek V3.1GLM 4.5Leader
AIMENot measured86.7%Only GLM 4.5 measured
MATH 500 (Vals AI)Not measured94.0%Only GLM 4.5 measured
MGSM (Vals AI)Not measured90.8%Only GLM 4.5 measured
AA Math IndexNot measured73.7Only GLM 4.5 measured
AIME 2025 (Artificial Analysis run)Not measured73.7%Only GLM 4.5 measured
LMArena Text: mathNot measured1427Only GLM 4.5 measured
LMArena Text: mathematical workNot measured1430Only GLM 4.5 measured
Neither model has a result on the other 6 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
Knowledge benchmarks for DeepSeek V3.1 and GLM 4.5
BenchmarkDeepSeek V3.1GLM 4.5Leader
MMLU ProNot measured81.2%Only GLM 4.5 measured
LegalBench (Vals AI)Not measured75.6%Only GLM 4.5 measured
CorpFin (Vals AI)Not measured61.0%Only GLM 4.5 measured
TaxEval (Vals AI)Not measured72.4%Only GLM 4.5 measured
MedQA (Vals AI)Not measured90.0%Only GLM 4.5 measured
MMLU Pro (Artificial Analysis run)Not measured83.5%Only GLM 4.5 measured
LMArena Text: scienceNot measured1444Only GLM 4.5 measured
LMArena Text: medicine and healthcareNot measured1455Only GLM 4.5 measured
LMArena Text: legal and governmentNot measured1438Only GLM 4.5 measured
LMArena Text: business and financeNot measured1420Only GLM 4.5 measured
Neither model has a result on the other 8 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for DeepSeek V3.1 and GLM 4.5
BenchmarkDeepSeek V3.1GLM 4.5Leader
Design Arena: websites11231170GLM 4.5
Design Arena: UI components10851144GLM 4.5
Design Arena: game dev10841145GLM 4.5
Design Arena: data viz10951159GLM 4.5
Design Arena: 3D10771170GLM 4.5
Design Arena: all code categories11121165GLM 4.5
Design Arena: SVG9671096GLM 4.5
Neither model has a result on the other 2 boards here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index22 boards, none shared
General benchmarks for DeepSeek V3.1 and GLM 4.5
BenchmarkDeepSeek V3.1GLM 4.5Leader
IFBenchNot measured44.1%Only GLM 4.5 measured
Long context reasoning (AA-LCR)Not measured52.7%Only GLM 4.5 measured
DTBench82.7%Not measuredOnly DeepSeek V3.1 measured
LMCA24.3%Not measuredOnly DeepSeek V3.1 measured
Creative writing (Lech Mazur)Not measured73.4%Only GLM 4.5 measured
LMArena TextNot measured1430Only GLM 4.5 measured
LMArena Text: instruction followingNot measured1404Only GLM 4.5 measured
LMArena Text: creative writingNot measured1395Only GLM 4.5 measured
LMArena Text: EnglishNot measured1437Only GLM 4.5 measured
LMArena Text: non-EnglishNot measured1417Only GLM 4.5 measured
LMArena Text: ChineseNot measured1465Only GLM 4.5 measured
LMArena Text: GermanNot measured1407Only GLM 4.5 measured
LMArena Text: JapaneseNot measured1415Only GLM 4.5 measured
LMArena Text: KoreanNot measured1380Only GLM 4.5 measured
LMArena Text: FrenchNot measured1418Only GLM 4.5 measured
LMArena Text: SpanishNot measured1454Only GLM 4.5 measured
LMArena Text: RussianNot measured1413Only GLM 4.5 measured
LMArena Text: PolishNot measured1422Only GLM 4.5 measured
LMArena Text: multi-turnNot measured1415Only GLM 4.5 measured
LMArena Text: longer queriesNot measured1412Only GLM 4.5 measured
LMArena Text: writing and languageNot measured1403Only GLM 4.5 measured
LMArena Text: entertainment and mediaNot measured1404Only GLM 4.5 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 4.5
BenchmarkDeepSeek V3.1GLM 4.5Leader
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 4.5$0.0017Fits in one request

DeepSeek V3.1 costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.1$0.032Fits in one request
GLM 4.5$0.037Fits in one request

DeepSeek V3.1 costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.1$0.125Exceeds the context window
GLM 4.5$0.142Exceeds 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 4.5
SpecificationDeepSeek V3.1Z.ai GLM 4.5
MakerDeepSeekZ.ai
WeightsOpen weightsOpen weights
ReleasedAugust 21, 2025July 25, 2025
Context window164K131K
Input $/Mtok$0.55$0.60
Output $/Mtok$1.50$2.20
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V3.1 better than GLM 4.5 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.1 for output tokens 1.5x cheaper ($1.50 vs $2.20 per million) and a larger context window (164K against 131K tokens).

Which is cheaper, DeepSeek V3.1 or GLM 4.5?

DeepSeek V3.1 costs $0.55 per million input tokens and $1.50 per million output tokens; GLM 4.5 costs $0.60 and $2.20. Cost per solved task is known for neither of them.

Which has the bigger context window, DeepSeek V3.1 or GLM 4.5?

DeepSeek V3.1, with 164K tokens against 131K.

How many benchmarks is the DeepSeek V3.1 vs GLM 4.5 comparison based on?

9 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 4.5's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next