Noometry

Model comparison

Claude 3 Sonnet vs GLM-5.3

GLM-5.3 is the stronger model overall, scoring 54.8 to 29.0 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

GLM-5.3 Z.ai (Zhipu)

54.8

Rank #26 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and GLM-5.3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-5.3 leads 62.3 to 10.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 91.1% for GLM-5.3.
  • GLM-5.3 has downloadable open weights; the other is API-only.

Side by side

Claude 3 SonnetGLM-5.3
ProviderAnthropicZ.ai (Zhipu)
Noometry Index29.054.8
Released2024-02-292026-08-14
WeightsProprietaryOpen
Context window—1M
Max output—131K
Input $ / M tokens—$1.40
Output $ / M tokens—$4.40
Results tracked3042

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

Category by category

Coding GLM-5.3 leads

Claude 3 Sonnet: 29.6 (#302), GLM-5.3: 59.5 (#14)

BenchmarkClaude 3 SonnetGLM-5.3
WeirdML10.2%75.4%
LMArena Coding12231496
DeepSWE—69%
FrontierCode—40.1%
CursorBench—42.6%
LMArena WebDev—1622
FrontierSWE—30.2%
SciCode—59%
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
ALE-Bench—1,317
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, GLM-5.3: 36.4 (#38)

BenchmarkClaude 3 SonnetGLM-5.3
APEX-Agents—56.6%
Vending-Bench 2—8,164

Reasoning GLM-5.3 leads

Claude 3 Sonnet: 20.5 (#237), GLM-5.3: 46.1 (#46)

BenchmarkClaude 3 SonnetGLM-5.3
LMArena Hard Prompts11971489
DTBench53.6%87.7%
Epoch Capabilities Index120.7155.61
NYT Connections (extended)—74.2%
CritPt—19.1%
Chess Puzzles—21%
Mystery Game Puzzles—33%
LMCA—55.5%
Bench to the Future 3—0.15
WinoGrande75.1%—

Math GLM-5.3 leads

Claude 3 Sonnet: 10.7 (#310), GLM-5.3: 62.3 (#33)

BenchmarkClaude 3 SonnetGLM-5.3
OTIS Mock AIME 2024-20252.5%91.1%
LMArena Math12131489
FrontierMath (Tiers 1-3)—68.8%
FrontierMath Tier 4—29.3%
ProofBench—49%
MATH Level 518.2%—

Knowledge GLM-5.3 leads

Claude 3 Sonnet: 21.1 (#276), GLM-5.3: 58.3 (#37)

BenchmarkClaude 3 SonnetGLM-5.3
GPQA Diamond40.6%90.9%
LMArena Expert11731516
SimpleQA Verified—41%
MMLU75.9%—

Multimodal Not comparable

Claude 3 Sonnet: 25.2 (#125), GLM-5.3: —

BenchmarkClaude 3 SonnetGLM-5.3
LMArena Vision984—

Multilingual GLM-5.3 leads

Claude 3 Sonnet: 37.8 (#234), GLM-5.3: 55.7 (#28)

BenchmarkClaude 3 SonnetGLM-5.3
LMArena Non-English12051457
LMArena Chinese11891528
LMArena French12291499
LMArena German12041499
LMArena Japanese11311453
LMArena Korean11281472
LMArena Russian12271463
LMArena Spanish12041460

Instruction Following GLM-5.3 leads

Claude 3 Sonnet: 62.8 (#235), GLM-5.3: 77.5 (#23)

BenchmarkClaude 3 SonnetGLM-5.3
LMArena Instruction Following11991477

Long Context GLM-5.3 leads

Claude 3 Sonnet: 36.7 (#228), GLM-5.3: 45.4 (#41)

BenchmarkClaude 3 SonnetGLM-5.3
LMArena Longer Query12111482

Writing & Preference GLM-5.3 leads

Claude 3 Sonnet: 42.1 (#238), GLM-5.3: 75.7 (#6)

BenchmarkClaude 3 SonnetGLM-5.3
LMArena Text12181471
LMArena Creative Writing11861457
LMArena Multi-Turn12271472
EQ-Bench Creative Writing—2075

Frequently asked questions

Is Claude 3 Sonnet better than GLM-5.3?

GLM-5.3 is the stronger model overall, scoring 54.8 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or GLM-5.3 better for coding?

GLM-5.3 scores higher on coding benchmarks: 59.5 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and GLM-5.3 share?

22 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and GLM-5.3 has 42.

Related comparisons

Go deeper