Noometry

Model comparison

GLM-4.5 vs GPT-4 Turbo

GLM-4.5 is the stronger model overall, scoring 42.0 to 30.5 on the Noometry Index.

Last verified . 19 shared benchmarks.

GLM-4.5 Z.ai (Zhipu)

42.0

Rank #122 Confirmed

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GLM-4.5 scores higher in 8 categories and GPT-4 Turbo in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.5 leads 39.0 to 9.0.
  • The biggest single-benchmark swing is WeirdML: 40.6% for GLM-4.5 and 18% for GPT-4 Turbo.
  • GLM-4.5 is cheaper at $0.60 / $2.20 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • GLM-4.5 accepts more context: 131K tokens versus 128K.
  • GLM-4.5 has downloadable open weights; the other is API-only.

Side by side

GLM-4.5GPT-4 Turbo
ProviderZ.ai (Zhipu)OpenAI
Noometry Index42.030.5
Released2025-07-272023-11-06
WeightsOpenProprietary
Context window131K128K
Max output98K4K
Input $ / M tokens$0.60$10
Output $ / M tokens$2.20$30
Results tracked2736

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

Category by category

Coding GLM-4.5 leads

GLM-4.5: 41.4 (#125), GPT-4 Turbo: 33.8 (#249)

BenchmarkGLM-4.5GPT-4 Turbo
WeirdML40.6%18%
LMArena Coding14341268
SWE-bench Verified (bash only)54.2%—
BigCodeBench Instruct—48.2%
BigCodeBench Complete—58.2%
ALE-Bench344.82—
AlgoTune1.52—
HumanEval+—86.6%
MBPP+—73.3%

Agentic & Tool Use Not comparable

GLM-4.5: —, GPT-4 Turbo: —

BenchmarkGLM-4.5GPT-4 Turbo
METR Time Horizons—36.7%

Reasoning GLM-4.5 leads

GLM-4.5: 28.6 (#100), GPT-4 Turbo: 15.3 (#317)

BenchmarkGLM-4.5GPT-4 Turbo
LMArena Hard Prompts14291251
SimpleBench—25.1%
Kagi LLM Benchmark57.9%—
Chess Puzzles—6%
DTBench—61.6%
LMCA—9.8%
Epoch Capabilities Index—127.25
ForecastBench—59.4

Math GLM-4.5 leads

GLM-4.5: 39.0 (#116), GPT-4 Turbo: 9.0 (#322)

BenchmarkGLM-4.5GPT-4 Turbo
LMArena Math14271272
FrontierMath (Tiers 1-3)—0.7%
OTIS Mock AIME 2024-2025—6.7%
MATH Level 5—46.7%

Knowledge GLM-4.5 leads

GLM-4.5: 35.9 (#179), GPT-4 Turbo: 24.3 (#268)

BenchmarkGLM-4.5GPT-4 Turbo
Confabulations11.3%28.4%
LMArena Expert14331223
GPQA Diamond—46.6%
Humanity's Last Exam8.3%—
MMLU—81.3%

Multimodal Not comparable

GLM-4.5: —, GPT-4 Turbo: 30.6 (#110)

BenchmarkGLM-4.5GPT-4 Turbo
LMArena Vision—1090

Multilingual GLM-4.5 leads

GLM-4.5: 52.8 (#77), GPT-4 Turbo: 40.5 (#216)

BenchmarkGLM-4.5GPT-4 Turbo
LMArena Non-English14171245
LMArena Chinese14651242
LMArena French14181276
LMArena German14071259
LMArena Japanese14151194
LMArena Korean13801187
LMArena Russian14141259
LMArena Spanish14541260

Instruction Following GLM-4.5 leads

GLM-4.5: 74.1 (#104), GPT-4 Turbo: 65.8 (#216)

BenchmarkGLM-4.5GPT-4 Turbo
LMArena Instruction Following14041249

Long Context Too close to call

GLM-4.5: 38.2 (#201), GPT-4 Turbo: 38.0 (#206)

BenchmarkGLM-4.5GPT-4 Turbo
LMArena Longer Query14121254
Fiction.LiveBench58.3%—

Writing & Preference GLM-4.5 leads

GLM-4.5: 57.5 (#127), GPT-4 Turbo: 47.7 (#206)

BenchmarkGLM-4.5GPT-4 Turbo
LMArena Text14301272
LMArena Creative Writing13951269
LMArena Multi-Turn14151267
Short-Story Creative Writing73.4%—
EQ-Bench Creative Writing1343—

Frequently asked questions

Is GLM-4.5 better than GPT-4 Turbo?

GLM-4.5 is the stronger model overall, scoring 42.0 to 30.5 on the Noometry Index.

Which is cheaper, GLM-4.5 or GPT-4 Turbo?

GLM-4.5 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-4 Turbo lists at $10 and $30.

Is GLM-4.5 or GPT-4 Turbo better for coding?

GLM-4.5 scores higher on coding benchmarks: 41.4 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

GLM-4.5 does, with 131K tokens against 128K.

How many benchmarks do GLM-4.5 and GPT-4 Turbo share?

19 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and GPT-4 Turbo has 36.

Related comparisons

Go deeper