Noometry

Model comparison

GLM-5 vs GPT-4.5

GLM-5 is the stronger model overall, scoring 46.1 to 37.2 on the Noometry Index.

Last verified . 25 shared benchmarks.

GLM-5 Z.ai (Zhipu)

46.1

Rank #66 Confirmed

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Summary

  • They share 25 benchmarks with published results for both. GLM-5 scores higher in 9 categories and GPT-4.5 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-5 leads 52.3 to 32.5.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for GLM-5 and 37.8% for GPT-4.5.
  • GLM-5 has downloadable open weights; the other is API-only.

Side by side

GLM-5GPT-4.5
ProviderZ.ai (Zhipu)OpenAI
Noometry Index46.137.2
Released2026-02-112025-02-27
WeightsOpenProprietary
Context window205K—
Max output131K—
Input $ / M tokens$1—
Output $ / M tokens$3.20—
Results tracked4542

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

Category by category

Coding GLM-5 leads

GLM-5: 49.0 (#52), GPT-4.5: 42.2 (#109)

BenchmarkGLM-5GPT-4.5
WeirdML48.2%39.4%
LMArena Coding14611396
SWE-bench Verified72.1%—
SWE-bench Verified (bash only)72.8%—
Aider Polyglot—44.9%
LMArena WebDev1434—
SWE-bench Multilingual69.7%—
LiveBench Coding—75.2%
ALE-Bench765.62—

Agentic & Tool Use GLM-5 leads

GLM-5: 31.1 (#71), GPT-4.5: 27.9 (#97)

BenchmarkGLM-5GPT-4.5
Terminal-Bench52.4%—
τ²-bench Airline82.5%—
τ²-bench Banking9.8%—
τ²-bench Retail73.7%—
τ²-bench Telecom86.8%—
Cybench—17.5%
Vending-Bench 24,432—

Reasoning GLM-5 leads

GLM-5: 27.6 (#116), GPT-4.5: 13.9 (#330)

BenchmarkGLM-5GPT-4.5
ARC-AGI-24.9%0.8%
SimpleBench53.2%34.5%
ARC-AGI-144.7%10.3%
LMArena Hard Prompts14521403
Epoch Capabilities Index145.83136.74
ForecastBench6161.7
Kagi LLM Benchmark75%—
NYT Connections (extended)74.8%—
Chess Puzzles10%—
EnigmaEval—3.2%
LiveBench Reasoning—71.1%
LiveBench Data Analysis—64.3%
LiveBench—69%

Math GLM-5 leads

GLM-5: 46.4 (#71), GPT-4.5: 32.6 (#211)

BenchmarkGLM-5GPT-4.5
OTIS Mock AIME 2024-202580%37.8%
LMArena Math14401412
MathArena Final-Answer Competitions65.7%—
LiveBench Math—69.3%
MATH Level 5—78.6%
FrontierMath (Feb 2025 set)16.4%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GLM-5 leads

GLM-5: 52.3 (#64), GPT-4.5: 32.5 (#211)

BenchmarkGLM-5GPT-4.5
GPQA Diamond87.8%68.7%
LMArena Expert14541394
Humanity's Last Exam—5.4%
Confabulations—13.6%
Vectara Hallucination Rate10.1%—

Multimodal Not comparable

GLM-5: —, GPT-4.5: 37.6 (#71)

BenchmarkGLM-5GPT-4.5
LMArena Vision—1195
VPCT—45%

Multilingual GLM-5 leads

GLM-5: 53.7 (#58), GPT-4.5: 52.5 (#83)

BenchmarkGLM-5GPT-4.5
LMArena Non-English14301413
LMArena Chinese15111421
LMArena French14551418
LMArena German14451457
LMArena Japanese14161416
LMArena Korean14231392
LMArena Russian14361419
LMArena Spanish1454—

Instruction Following GLM-5 leads

GLM-5: 75.2 (#67), GPT-4.5: 72.6 (#134)

BenchmarkGLM-5GPT-4.5
LMArena Instruction Following14281404
LiveBench Instruction Following—72.3%

Long Context GLM-5 leads

GLM-5: 44.7 (#60), GPT-4.5: 40.4 (#155)

BenchmarkGLM-5GPT-4.5
LMArena Longer Query14461406
Fiction.LiveBench—63.9%
CL-bench18.7%—

Writing & Preference GLM-5 leads

GLM-5: 66.0 (#38), GPT-4.5: 56.9 (#134)

BenchmarkGLM-5GPT-4.5
LMArena Text14461417
LMArena Creative Writing14391394
EQ-Bench Creative Writing16011258
LMArena Multi-Turn14561444
Short-Story Creative Writing—75.6%
LiveBench Language—61.5%

Frequently asked questions

Is GLM-5 better than GPT-4.5?

GLM-5 is the stronger model overall, scoring 46.1 to 37.2 on the Noometry Index.

Is GLM-5 or GPT-4.5 better for coding?

GLM-5 scores higher on coding benchmarks: 49.0 versus 42.2 in the Noometry coding category.

How many benchmarks do GLM-5 and GPT-4.5 share?

25 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and GPT-4.5 has 42.

Related comparisons

Go deeper