Noometry

Model comparison

DeepSeek-V3.2-Speciale vs GLM-4.7

GLM-4.7 is the stronger model overall, scoring 42.0 to 39.7 on the Noometry Index.

Last verified . 2 shared benchmarks.

DeepSeek-V3.2-Speciale DeepSeek

39.7

Rank #162 Reported

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Summary

  • They share 2 benchmarks with published results for both. DeepSeek-V3.2-Speciale scores higher in 1 category and GLM-4.7 in 2 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GLM-4.7 leads 60.9 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-4.7.
  • GLM-4.7 accepts more context: 205K tokens versus 128K.

Side by side

DeepSeek-V3.2-SpecialeGLM-4.7
ProviderDeepSeekZ.ai (Zhipu)
Noometry Index39.742.0
Released2025-12-012025-12-22
WeightsOpenOpen
Context window128K205K
Max output128K131K
Input $ / M tokens$0.58$0.60
Output $ / M tokens$1.68$2.20
Results tracked336

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

Category by category

Coding GLM-4.7 leads

DeepSeek-V3.2-Speciale: 40.4 (#140), GLM-4.7: 44.0 (#79)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.7
LMArena WebDev—1435
SciCode—45.1%
WeirdML46.7%—
LMArena Coding—1454
ALE-Bench—399.48

Agentic & Tool Use Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.7: 26.5 (#103)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.7
Terminal-Bench—33.4%
Vending-Bench 2—2,377

Reasoning DeepSeek-V3.2-Speciale leads

DeepSeek-V3.2-Speciale: 32.9 (#73), GLM-4.7: 24.3 (#164)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.7
SimpleBench52.6%47.7%
CritPt—1.7%
Chess Puzzles—6%
LMArena Hard Prompts—1443
Epoch Capabilities Index—143.51

Math Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.7: 38.6 (#135)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.7
OTIS Mock AIME 2024-2025—83.3%
ProofBench—6%
LMArena Math—1423
FrontierMath (Feb 2025 set)—2.4%
FrontierMath Tier 4 (v1)—0%

Knowledge Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.7: 47.0 (#80)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.7
GPQA Diamond—83.3%
SimpleQA Verified—32.2%
Vectara Hallucination Rate—11.7%
LMArena Expert—1424

Multilingual Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.7: 52.8 (#79)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.7
LMArena Non-English—1417
LMArena Chinese—1495
LMArena French—1432
LMArena German—1424
LMArena Japanese—1439
LMArena Korean—1399
LMArena Russian—1423
LMArena Spanish—1434

Instruction Following Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.7: 74.4 (#95)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.7
LMArena Instruction Following—1411

Long Context Not comparable

DeepSeek-V3.2-Speciale: —, GLM-4.7: 42.8 (#116)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.7
CL-bench—15.9%
CL-bench Life—10.9%
LMArena Longer Query—1432

Writing & Preference GLM-4.7 leads

DeepSeek-V3.2-Speciale: 46.0 (#222), GLM-4.7: 60.9 (#93)

BenchmarkDeepSeek-V3.2-SpecialeGLM-4.7
EQ-Bench Creative Writing12761413
LMArena Text—1435
LMArena Creative Writing—1401
LMArena Multi-Turn—1446

Frequently asked questions

Is DeepSeek-V3.2-Speciale better than GLM-4.7?

GLM-4.7 is the stronger model overall, scoring 42.0 to 39.7 on the Noometry Index.

Which is cheaper, DeepSeek-V3.2-Speciale or GLM-4.7?

DeepSeek-V3.2-Speciale is cheaper. It lists at $0.58 per million input tokens and $1.68 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

Is DeepSeek-V3.2-Speciale or GLM-4.7 better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 40.4 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 128K.

How many benchmarks do DeepSeek-V3.2-Speciale and GLM-4.7 share?

2 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and GLM-4.7 has 36.

Related comparisons

Go deeper