Noometry

Model comparison

DeepSeek-V3.2-Speciale vs GLM-4.6

GLM-4.6 is the stronger model overall, scoring 40.9 to 39.1 on the Noometry Index.

Last verified . 1 shared benchmarks.

DeepSeek-V3.2-Speciale DeepSeek

39.1

Rank #159 Reported

GLM-4.6 Z.ai (Zhipu)

40.9

Rank #132 Confirmed

Summary

  • They share 1 benchmark with published results for both. DeepSeek-V3.2-Speciale scores higher in 1 category and GLM-4.6 in 2 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GLM-4.6 leads 61.3 to 46.1.
  • 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 Index39.140.9
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: 39.9 (#136), GLM-4.6: 39.9 (#137)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
SWE-bench Verified (bash only)—55.4%
LMArena WebDev—1339
SciCode—38.4%
WeirdML46.7%—
LMArena Coding—1449
ALE-Bench—340.82

Agentic & Tool Use Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.6: 32.1 (#60)

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: 32.1 (#65), GLM-4.6: 23.1 (#168)

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: 36.4 (#115)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
LMArena Math—1431
FrontierMath (Feb 2025 set)—3.8%
FrontierMath Tier 4 (v1)—2.1%

Knowledge Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.6: 39.6 (#118)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
Vectara Hallucination Rate—9.5%
LMArena Expert—1432

Multilingual Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.6: 53.6 (#62)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
LMArena Non-English—1426
LMArena Chinese—1500
LMArena French—1459
LMArena German—1447
LMArena Japanese—1394
LMArena Korean—1401
LMArena Russian—1418
LMArena Spanish—1436

Instruction Following Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.6: 74.5 (#93)

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

Long Context Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.6: 43.4 (#91)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.6
LMArena Longer Query—1423

Writing & Preference GLM-4.6 leads

DeepSeek-V3.2-Speciale: 46.1 (#217), GLM-4.6: 61.3 (#86)

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 40.9 to 39.1 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 (39.9 vs 39.9); 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