Enter opens the highlighted result. Esc closes.

DeepSeek V3.1 Terminus vs GLM 4.5 Air

DeepSeek V3.1 Terminus leads GLM 4.5 Air on the Artificial Analysis Intelligence Index, 14.8 to 11.1, at about the same output price ($1.0142 vs $1.10 per million). Updated October 22, 2026; 39 benchmarks have a result for both.

Replace DeepSeek V3.1 Terminus Replace GLM 4.5 Air
DeepSeek V3.1 TerminusDeepSeek
Coding
No data
Overall
No data
Output $/M
$1.0142
36
GLM 4.5 AirZ.ai
Coding
No data
Overall
No data
Output $/M
$1.10
3
vs boards won of 39 shared

DeepSeek V3.1 Terminus or GLM 4.5 Air: which to pick

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

Pick DeepSeek V3.1 Terminus for output tokens 1.1x cheaper ($1.0142 vs $1.10 per million) and a larger context window (164K against 131K tokens).

Model ADeepSeek V3.1 TerminusDeepSeekNot benchmarkedNo coding benchmarkNo cost per solved taskModel BGLM 4.5 AirZ.aiNot benchmarkedNo coding benchmarkNo cost per solved task
Shared results
39
DeepSeek V3.1 Terminus only
6
GLM 4.5 Air only
9
Like-for-like categories
8 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 Terminus not benchmarked, GLM 4.5 Air not benchmarked.
Widest category
General, 10.2 points apart on average over 13 shared benchmarks.
Widest single gap
Long context reasoning (AA-LCR): DeepSeek V3.1 Terminus 69.3% against GLM 4.5 Air 46.7%, 22.7 points apart on a 0 to 100 scale.
Output price
DeepSeek V3.1 Terminus $1.0142 against GLM 4.5 Air $1.10 per million output tokens, 1.1x apart.
Context window
DeepSeek V3.1 Terminus takes 164K tokens, GLM 4.5 Air 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 V3.1 TerminusBarsGLM 4.5 AirTies
Coding40
Intelligence10
Agentic work01
Reasoning50
Math30
Knowledge50
Web design52
General130
All shared boards363
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
Coding benchmarks for DeepSeek V3.1 Terminus and GLM 4.5 Air
BenchmarkDeepSeek V3.1 TerminusGLM 4.5 AirLeader
AA Coding Index43.5Not measuredOnly DeepSeek V3.1 Terminus measured
LiveCodeBench (Artificial Analysis run)79.8%68.4%DeepSeek V3.1 Terminus
SciCode38.0%Not measuredOnly DeepSeek V3.1 Terminus measured
Terminal-Bench Hard (Artificial Analysis run)31.8%20.5%DeepSeek V3.1 Terminus
GSO-BenchNot measured2.9%Only GLM 4.5 Air measured
ALE-Bench745.2Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text: coding14251397DeepSeek V3.1 Terminus
LMArena Text: software and IT14261401DeepSeek V3.1 Terminus
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 Terminus and GLM 4.5 Air
BenchmarkDeepSeek V3.1 TerminusGLM 4.5 AirLeader
AA Intelligence Index14.811.1DeepSeek V3.1 Terminus
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for DeepSeek V3.1 Terminus and GLM 4.5 Air
BenchmarkDeepSeek V3.1 TerminusGLM 4.5 AirLeader
AA Agentic Index6.8Not measuredOnly DeepSeek V3.1 Terminus measured
τ²-Bench Telecom37.1%46.5%GLM 4.5 Air
Neither model has a result on the other 39 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
Reasoning benchmarks for DeepSeek V3.1 Terminus and GLM 4.5 Air
BenchmarkDeepSeek V3.1 TerminusGLM 4.5 AirLeader
GPQA Diamond (Artificial Analysis run)79.2%73.3%DeepSeek V3.1 Terminus
Humanity's Last Exam (Artificial Analysis run)16.4%7.0%DeepSeek V3.1 Terminus
LMArena Text: hard prompts14261379DeepSeek V3.1 Terminus
LMArena Text: expertNot measured1370Only GLM 4.5 Air measured
LMArena Text: hard prompts in English14321388DeepSeek V3.1 Terminus
Kagi LLM Benchmark57.4%43.0%DeepSeek V3.1 Terminus
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index30
Math benchmarks for DeepSeek V3.1 Terminus and GLM 4.5 Air
BenchmarkDeepSeek V3.1 TerminusGLM 4.5 AirLeader
AA Math Index89.780.7DeepSeek V3.1 Terminus
AIME 2025 (Artificial Analysis run)89.7%80.7%DeepSeek V3.1 Terminus
LMArena Text: math14021396DeepSeek V3.1 Terminus
LMArena Text: mathematical workNot measured1396Only GLM 4.5 Air measured
Neither model has a result on the other 9 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
Knowledge benchmarks for DeepSeek V3.1 Terminus and GLM 4.5 Air
BenchmarkDeepSeek V3.1 TerminusGLM 4.5 AirLeader
MMLU Pro (Artificial Analysis run)85.1%81.5%DeepSeek V3.1 Terminus
LMArena Text: science14511407DeepSeek V3.1 Terminus
LMArena Text: medicine and healthcare14681402DeepSeek V3.1 Terminus
LMArena Text: legal and government14571382DeepSeek V3.1 Terminus
LMArena Text: business and finance14141371DeepSeek V3.1 Terminus
Neither model has a result on the other 13 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index52
Web design benchmarks for DeepSeek V3.1 Terminus and GLM 4.5 Air
BenchmarkDeepSeek V3.1 TerminusGLM 4.5 AirLeader
Design Arena: websites11871146DeepSeek V3.1 Terminus
Design Arena: UI components11821120DeepSeek V3.1 Terminus
Design Arena: game dev11311094DeepSeek V3.1 Terminus
Design Arena: data viz11681186GLM 4.5 Air
Design Arena: 3D11411122DeepSeek V3.1 Terminus
Design Arena: all code categories11751137DeepSeek V3.1 Terminus
Design Arena: SVG10651071GLM 4.5 Air
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
General benchmarks for DeepSeek V3.1 Terminus and GLM 4.5 Air
BenchmarkDeepSeek V3.1 TerminusGLM 4.5 AirLeader
IFBench57.0%37.6%DeepSeek V3.1 Terminus
Long context reasoning (AA-LCR)69.3%46.7%DeepSeek V3.1 Terminus
DTBench81.3%Not measuredOnly DeepSeek V3.1 Terminus measured
LMCA28.6%Not measuredOnly DeepSeek V3.1 Terminus measured
LMArena Text14191384DeepSeek V3.1 Terminus
LMArena Text: instruction following14041354DeepSeek V3.1 Terminus
LMArena Text: creative writing14031343DeepSeek V3.1 Terminus
LMArena Text: English14291397DeepSeek V3.1 Terminus
LMArena Text: non-English14081366DeepSeek V3.1 Terminus
LMArena Text: ChineseNot measured1426Only GLM 4.5 Air measured
LMArena Text: GermanNot measured1377Only GLM 4.5 Air measured
LMArena Text: JapaneseNot measured1348Only GLM 4.5 Air measured
LMArena Text: KoreanNot measured1308Only GLM 4.5 Air measured
LMArena Text: FrenchNot measured1400Only GLM 4.5 Air measured
LMArena Text: SpanishNot measured1385Only GLM 4.5 Air measured
LMArena Text: Russian14351373DeepSeek V3.1 Terminus
LMArena Text: Polish14271368DeepSeek V3.1 Terminus
LMArena Text: multi-turn14111371DeepSeek V3.1 Terminus
LMArena Text: longer queries14221366DeepSeek V3.1 Terminus
LMArena Text: writing and language14091354DeepSeek V3.1 Terminus
LMArena Text: entertainment and media13911339DeepSeek V3.1 Terminus
Neither model has a result on the other 25 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V3.1 Terminus and GLM 4.5 Air
BenchmarkDeepSeek V3.1 TerminusGLM 4.5 AirLeader
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 Terminus$0.0008Fits in one request
GLM 4.5 Air$0.0008Fits in one request

GLM 4.5 Air costs less

Repository review

50K input + 3K output tokens

DeepSeek V3.1 Terminus$0.018Fits in one request
GLM 4.5 Air$0.013Fits in one request

GLM 4.5 Air costs less

Agent loop

200K input + 10K output tokens

DeepSeek V3.1 Terminus$0.071Exceeds the context window
GLM 4.5 Air$0.051Exceeds the context window

GLM 4.5 Air 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 Terminus and GLM 4.5 Air
SpecificationDeepSeek V3.1 TerminusZ.ai GLM 4.5 Air
MakerDeepSeekZ.ai
WeightsOpen weightsOpen weights
ReleasedSeptember 22, 2025July 25, 2025
Context window164K131K
Input $/Mtok$0.3063$0.20
Output $/Mtok$1.0142$1.10
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

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

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.1 Terminus for output tokens 1.1x cheaper ($1.0142 vs $1.10 per million) and a larger context window (164K against 131K tokens).

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

DeepSeek V3.1 Terminus costs $0.3063 per million input tokens and $1.0142 per million output tokens; GLM 4.5 Air costs $0.20 and $1.10. Cost per solved task is known for neither of them.

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

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

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

39 benchmarks have a result for both models as of October 22, 2026. DeepSeek V3.1 Terminus's coding index rests on 0 independent benchmarks and GLM 4.5 Air's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next