Noometry

Model comparison

GLM-5.1 vs GPT-4.5

GLM-5.1 is the stronger model overall, scoring 47.8 to 37.2 on the Noometry Index.

Last verified . 22 shared benchmarks.

GLM-5.1 Z.ai (Zhipu)

47.8

Rank #59 Confirmed

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and GPT-4.5 in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 13.9.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 37.8% for GPT-4.5.
  • GLM-5.1 has downloadable open weights; the other is API-only.

Side by side

GLM-5.1GPT-4.5
ProviderZ.ai (Zhipu)OpenAI
Noometry Index47.837.2
Released2026-04-072025-02-27
WeightsOpenProprietary
Context window200K—
Max output131K—
Input $ / M tokens$1.40—
Output $ / M tokens$4.40—
Results tracked4142

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

Category by category

Coding GLM-5.1 leads

GLM-5.1: 48.7 (#55), GPT-4.5: 42.2 (#109)

BenchmarkGLM-5.1GPT-4.5
WeirdML57.1%39.4%
LMArena Coding14851396
SWE-bench Verified74.2%—
Aider Polyglot—44.9%
LMArena WebDev1508—
SciCode43.8%—
LiveBench Coding—75.2%
ALE-Bench887.1—

Agentic & Tool Use GPT-4.5 leads

GLM-5.1: 24.9 (#113), GPT-4.5: 27.9 (#97)

BenchmarkGLM-5.1GPT-4.5
APEX-Agents40.9%—
Cybench—17.5%
ExploitBench18.1%—
GBAEval0%—
Vending-Bench 25,634—

Reasoning GLM-5.1 leads

GLM-5.1: 39.1 (#60), GPT-4.5: 13.9 (#330)

BenchmarkGLM-5.1GPT-4.5
SimpleBench55.1%34.5%
LMArena Hard Prompts14721403
Epoch Capabilities Index149.84136.74
ARC-AGI-2—0.8%
NYT Connections (extended)77.7%—
ARC-AGI-1—10.3%
CritPt4.6%—
Chess Puzzles19%—
EnigmaEval—3.2%
Thematic Generalization69.8%—
LiveBench Reasoning—71.1%
LiveBench Data Analysis—64.3%
ForecastBench—61.7
LiveBench—69%

Math GLM-5.1 leads

GLM-5.1: 49.7 (#60), GPT-4.5: 32.6 (#211)

BenchmarkGLM-5.1GPT-4.5
OTIS Mock AIME 2024-202593.3%37.8%
LMArena Math14731412
FrontierMath (Tiers 1-3)36.8%—
MathArena Final-Answer Competitions67.1%—
ProofBench22.2%—
LiveBench Math—69.3%
MATH Level 5—78.6%
FrontierMath (Feb 2025 set)33.4%—
FrontierMath Tier 4 (v1)12.5%—

Knowledge GLM-5.1 leads

GLM-5.1: 54.9 (#50), GPT-4.5: 32.5 (#211)

BenchmarkGLM-5.1GPT-4.5
GPQA Diamond89.9%68.7%
LMArena Expert14761394
Humanity's Last Exam—5.4%
SimpleQA Verified34%—
Confabulations—13.6%

Multimodal Not comparable

GLM-5.1: —, GPT-4.5: 37.6 (#71)

BenchmarkGLM-5.1GPT-4.5
LMArena Vision—1195
VPCT—45%

Multilingual GLM-5.1 leads

GLM-5.1: 55.0 (#36), GPT-4.5: 52.5 (#83)

BenchmarkGLM-5.1GPT-4.5
LMArena Non-English14471413
LMArena Chinese15151421
LMArena French14741418
LMArena German14651457
LMArena Japanese14341416
LMArena Korean14181392
LMArena Russian14541419
LMArena Spanish1469—

Instruction Following GLM-5.1 leads

GLM-5.1: 76.3 (#42), GPT-4.5: 72.6 (#134)

BenchmarkGLM-5.1GPT-4.5
LMArena Instruction Following14511404
LiveBench Instruction Following—72.3%

Long Context GLM-5.1 leads

GLM-5.1: 44.9 (#53), GPT-4.5: 40.4 (#155)

BenchmarkGLM-5.1GPT-4.5
LMArena Longer Query14661406
Fiction.LiveBench—63.9%

Writing & Preference GLM-5.1 leads

GLM-5.1: 66.9 (#31), GPT-4.5: 56.9 (#134)

BenchmarkGLM-5.1GPT-4.5
LMArena Text14611417
LMArena Creative Writing14531394
EQ-Bench Creative Writing15921258
LMArena Multi-Turn14721444
Short-Story Creative Writing—75.6%
LiveBench Language—61.5%

Frequently asked questions

Is GLM-5.1 better than GPT-4.5?

GLM-5.1 is the stronger model overall, scoring 47.8 to 37.2 on the Noometry Index.

Is GLM-5.1 or GPT-4.5 better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.7 versus 42.2 in the Noometry coding category.

How many benchmarks do GLM-5.1 and GPT-4.5 share?

22 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and GPT-4.5 has 42.

Related comparisons

Go deeper