Noometry

Model comparison

GLM-5.2 vs GPT-4.5

GLM-5.2 is the stronger model overall, scoring 51.1 to 37.2 on the Noometry Index.

Last verified . 24 shared benchmarks.

GLM-5.2 Z.ai (Zhipu)

51.1

Rank #44 Confirmed

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Summary

  • They share 24 benchmarks with published results for both. GLM-5.2 scores higher in 9 categories and GPT-4.5 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GLM-5.2 leads 42.3 to 13.9.
  • The biggest single-benchmark swing is ARC-AGI-1: 77% for GLM-5.2 and 10.3% for GPT-4.5.
  • GLM-5.2 has downloadable open weights; the other is API-only.

Side by side

GLM-5.2GPT-4.5
ProviderZ.ai (Zhipu)OpenAI
Noometry Index51.137.2
Released2026-06-132025-02-27
WeightsOpenProprietary
Context window1M—
Max output131K—
Input $ / M tokens$1.40—
Output $ / M tokens$4.40—
Results tracked5142

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

Category by category

Coding GLM-5.2 leads

GLM-5.2: 51.3 (#41), GPT-4.5: 42.2 (#109)

BenchmarkGLM-5.2GPT-4.5
WeirdML70.1%39.4%
LMArena Coding14851396
SWE-bench Verified78.7%—
DeepSWE43.8%—
FrontierCode24.5%—
Aider Polyglot—44.9%
LMArena WebDev1603—
SciCode50.5%—
LiveBench Coding—75.2%
ALE-Bench1,047—

Agentic & Tool Use GLM-5.2 leads

GLM-5.2: 32.4 (#63), GPT-4.5: 27.9 (#97)

BenchmarkGLM-5.2GPT-4.5
APEX-Agents45.2%—
τ²-bench Banking37.1%—
Cybench—17.5%
PostTrainBench31.7%—
GBAEval0%—
Vending-Bench 28,314—

Reasoning GLM-5.2 leads

GLM-5.2: 42.3 (#52), GPT-4.5: 13.9 (#330)

BenchmarkGLM-5.2GPT-4.5
ARC-AGI-222.8%0.8%
SimpleBench58.8%34.5%
ARC-AGI-177%10.3%
LMArena Hard Prompts14801403
Epoch Capabilities Index151.78136.74
Kagi LLM Benchmark62.6%—
NYT Connections (extended)74.3%—
CritPt20.9%—
Chess Puzzles21%—
EnigmaEval—3.2%
EBR-Bench9.5%—
LiveBench Reasoning—71.1%
Mystery Game Puzzles19%—
DTBench93.6%—
LiveBench Data Analysis—64.3%
LMCA45.8%—
Surface Evolver Bench55.6%—
ForecastBench—61.7
LiveBench—69%

Math GLM-5.2 leads

GLM-5.2: 55.7 (#43), GPT-4.5: 32.6 (#211)

BenchmarkGLM-5.2GPT-4.5
OTIS Mock AIME 2024-202586.4%37.8%
LMArena Math14821412
FrontierMath (Tiers 1-3)59.2%—
FrontierMath Tier 429.3%—
MathArena Final-Answer Competitions67.6%—
ProofBench35%—
LiveBench Math—69.3%
MATH Level 5—78.6%

Knowledge GLM-5.2 leads

GLM-5.2: 57.1 (#40), GPT-4.5: 32.5 (#211)

BenchmarkGLM-5.2GPT-4.5
GPQA Diamond91.9%68.7%
LMArena Expert14861394
Humanity's Last Exam—5.4%
SimpleQA Verified34.2%—
Confabulations—13.6%

Multimodal Not comparable

GLM-5.2: —, GPT-4.5: 37.6 (#71)

BenchmarkGLM-5.2GPT-4.5
LMArena Vision—1195
VPCT—45%

Multilingual GLM-5.2 leads

GLM-5.2: 55.8 (#26), GPT-4.5: 52.5 (#83)

BenchmarkGLM-5.2GPT-4.5
LMArena Non-English14591413
LMArena Chinese15191421
LMArena French14791418
LMArena German14681457
LMArena Japanese14511416
LMArena Korean14451392
LMArena Russian14661419
LMArena Spanish1477—

Instruction Following GLM-5.2 leads

GLM-5.2: 76.9 (#34), GPT-4.5: 72.6 (#134)

BenchmarkGLM-5.2GPT-4.5
LMArena Instruction Following14651404
LiveBench Instruction Following—72.3%

Long Context GLM-5.2 leads

GLM-5.2: 45.3 (#43), GPT-4.5: 40.4 (#155)

BenchmarkGLM-5.2GPT-4.5
LMArena Longer Query14791406
Fiction.LiveBench—63.9%

Writing & Preference GLM-5.2 leads

GLM-5.2: 70.4 (#21), GPT-4.5: 56.9 (#134)

BenchmarkGLM-5.2GPT-4.5
LMArena Text14701417
LMArena Creative Writing14621394
EQ-Bench Creative Writing17571258
LMArena Multi-Turn14691444
Short-Story Creative Writing—75.6%
EQ-Bench 41222—
LiveBench Language—61.5%

Frequently asked questions

Is GLM-5.2 better than GPT-4.5?

GLM-5.2 is the stronger model overall, scoring 51.1 to 37.2 on the Noometry Index.

Is GLM-5.2 or GPT-4.5 better for coding?

GLM-5.2 scores higher on coding benchmarks: 51.3 versus 42.2 in the Noometry coding category.

How many benchmarks do GLM-5.2 and GPT-4.5 share?

24 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and GPT-4.5 has 42.

Related comparisons

Go deeper