Noometry

Model comparison

DeepSeek-V3.1 vs GLM-4.7

DeepSeek-V3.1 and GLM-4.7 score almost the same on the Noometry Index (42.2 vs 41.7), so choose on price, context window or the category you care about most.

Last verified . 21 shared benchmarks.

DeepSeek-V3.1 DeepSeek

42.2

Rank #106 Confirmed

GLM-4.7 Z.ai (Zhipu)

41.7

Rank #117 Confirmed

Summary

  • They share 21 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 1 category and GLM-4.7 in 7 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in long context, where GLM-4.7 leads 42.8 to 36.3.
  • The biggest single-benchmark swing is SimpleBench: 40% for DeepSeek-V3.1 and 47.7% for GLM-4.7.
  • DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
  • GLM-4.7 accepts more context: 205K tokens versus 164K.

Side by side

DeepSeek-V3.1GLM-4.7
ProviderDeepSeekZ.ai (Zhipu)
Noometry Index42.241.7
Released2025-08-212025-12-22
WeightsOpenOpen
Context window164K205K
Max output8K131K
Input $ / M tokens$0.25$0.60
Output $ / M tokens$0.95$2.20
Results tracked2736

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

Category by category

Coding GLM-4.7 leads

DeepSeek-V3.1: 39.8 (#140), GLM-4.7: 43.6 (#74)

BenchmarkDeepSeek-V3.1GLM-4.7
LMArena Coding14171454
LMArena WebDev—1435
SciCode—45.1%
WeirdML38.4%—
ALE-Bench—399.48

Agentic & Tool Use Not comparable

DeepSeek-V3.1: —, GLM-4.7: 26.4 (#96)

BenchmarkDeepSeek-V3.1GLM-4.7
Terminal-Bench—33.4%
Vending-Bench 2—2,377

Reasoning DeepSeek-V3.1 leads

DeepSeek-V3.1: 27.3 (#109), GLM-4.7: 23.7 (#161)

BenchmarkDeepSeek-V3.1GLM-4.7
SimpleBench40%47.7%
LMArena Hard Prompts14171443
Epoch Capabilities Index139.92143.53
Kagi LLM Benchmark53.2%—
CritPt—1.7%
Chess Puzzles—6%
DTBench82.7%—
LMCA24.3%—
ForecastBench58—

Math GLM-4.7 leads

DeepSeek-V3.1: 36.1 (#125), GLM-4.7: 37.7 (#92)

BenchmarkDeepSeek-V3.1GLM-4.7
LMArena Math14201423
OTIS Mock AIME 2024-2025—83.3%
ProofBench—6%
FrontierMath (Feb 2025 set)—2.4%
FrontierMath Tier 4 (v1)—0%

Knowledge GLM-4.7 leads

DeepSeek-V3.1: 43.0 (#86), GLM-4.7: 47.0 (#74)

BenchmarkDeepSeek-V3.1GLM-4.7
Vectara Hallucination Rate5.5%11.7%
LMArena Expert14031424
GPQA Diamond—83.3%
SimpleQA Verified—32.2%

Multilingual GLM-4.7 leads

DeepSeek-V3.1: 51.8 (#100), GLM-4.7: 53.0 (#75)

BenchmarkDeepSeek-V3.1GLM-4.7
LMArena Non-English14001417
LMArena Chinese14701495
LMArena French14471432
LMArena German14121426
LMArena Japanese13741439
LMArena Korean13371401
LMArena Russian14051423
LMArena Spanish14291433

Instruction Following Too close to call

DeepSeek-V3.1: 74.1 (#105), GLM-4.7: 74.6 (#90)

BenchmarkDeepSeek-V3.1GLM-4.7
LMArena Instruction Following14001411

Long Context GLM-4.7 leads

DeepSeek-V3.1: 36.3 (#227), GLM-4.7: 42.8 (#111)

BenchmarkDeepSeek-V3.1GLM-4.7
LMArena Longer Query14221432
Fiction.LiveBench52.8%—
CL-bench—15.9%
CL-bench Life—10.9%

Writing & Preference Too close to call

DeepSeek-V3.1: 60.5 (#93), GLM-4.7: 61.1 (#89)

BenchmarkDeepSeek-V3.1GLM-4.7
LMArena Text14201436
LMArena Creative Writing14011401
EQ-Bench Creative Writing14361413
LMArena Multi-Turn14081446

Frequently asked questions

Is DeepSeek-V3.1 better than GLM-4.7?

DeepSeek-V3.1 and GLM-4.7 score almost the same on the Noometry Index (42.2 vs 41.7), so choose on price, context window or the category you care about most.

Which is cheaper, DeepSeek-V3.1 or GLM-4.7?

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

Is DeepSeek-V3.1 or GLM-4.7 better for coding?

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 39.8 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 164K.

How many benchmarks do DeepSeek-V3.1 and GLM-4.7 share?

21 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and GLM-4.7 has 36.

Related comparisons

Go deeper