Noometry

Model comparison

DeepSeek-V3.2-Speciale vs GLM-4.6

GLM-4.6 is the stronger model overall, scoring 41.4 to 39.7 on the Noometry Index.

Last verified . 1 shared benchmarks.

DeepSeek-V3.2-Speciale DeepSeek

39.7

Rank #162 Reported

GLM-4.6 Z.ai (Zhipu)

41.4

Rank #135 Confirmed

Summary

  • They share 1 benchmark with published results for both. DeepSeek-V3.2-Speciale scores higher in 2 categories and GLM-4.6 in 1 category; 2 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GLM-4.6 leads 61.1 to 46.0.
  • DeepSeek-V3.2-Speciale is cheaper at $0.58 / $1.68 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
  • GLM-4.6 accepts more context: 205K tokens versus 128K.

Side by side

DeepSeek-V3.2-SpecialeGLM-4.6
ProviderDeepSeekZ.ai (Zhipu)
Noometry Index39.741.4
Released2025-12-012025-09-30
WeightsOpenOpen
Context window128K205K
Max output128K131K
Input $ / M tokens$0.58$0.60
Output $ / M tokens$1.68$2.20
Results tracked329

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Too close to call

DeepSeek-V3.2-Speciale: 40.4 (#140), GLM-4.6: 40.1 (#148)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
SWE-bench Verified (bash only)—55.4%
LMArena WebDev—1340
SciCode—38.4%
WeirdML46.7%—
LMArena Coding—1449
ALE-Bench—340.82

Agentic & Tool Use Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.6: 32.3 (#66)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
Terminal-Bench—24.5%
Berkeley Function Calling Leaderboard—72.4%

Reasoning DeepSeek-V3.2-Speciale leads

DeepSeek-V3.2-Speciale: 32.9 (#73), GLM-4.6: 23.7 (#172)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
SimpleBench52.6%—
Kagi LLM Benchmark—47.4%
CritPt—1.1%
LMArena Hard Prompts—1440

Math Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.6: 39.1 (#111)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
LMArena Math—1432
FrontierMath (Feb 2025 set)—3.8%
FrontierMath Tier 4 (v1)—2.1%

Knowledge Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.6: 40.2 (#124)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
Vectara Hallucination Rate—9.5%
LMArena Expert—1431

Multilingual Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.6: 53.5 (#66)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
LMArena Non-English—1426
LMArena Chinese—1499
LMArena French—1459
LMArena German—1447
LMArena Japanese—1393
LMArena Korean—1400
LMArena Russian—1419
LMArena Spanish—1436

Instruction Following Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.6: 74.3 (#98)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
LMArena Instruction Following—1410

Long Context Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.6: 43.4 (#94)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
LMArena Longer Query—1422

Writing & Preference GLM-4.6 leads

DeepSeek-V3.2-Speciale: 46.0 (#222), GLM-4.6: 61.1 (#90)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
EQ-Bench Creative Writing12761411
LMArena Text—1440
LMArena Creative Writing—1411
LMArena Multi-Turn—1427

Frequently asked questions

Is DeepSeek-V3.2-Speciale better than GLM-4.6?

GLM-4.6 is the stronger model overall, scoring 41.4 to 39.7 on the Noometry Index.

Which is cheaper, DeepSeek-V3.2-Speciale or GLM-4.6?

DeepSeek-V3.2-Speciale is cheaper. It lists at $0.58 per million input tokens and $1.68 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.

Is DeepSeek-V3.2-Speciale or GLM-4.6 better for coding?

They score almost the same on coding (40.4 vs 40.1); test both on your own repository before choosing.

Which has the bigger context window?

GLM-4.6 does, with 205K tokens against 128K.

How many benchmarks do DeepSeek-V3.2-Speciale and GLM-4.6 share?

1 benchmark has published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and GLM-4.6 has 29.

Related comparisons

Go deeper