Noometry

Model comparison

Claude Sonnet 4.5 vs GLM-4.5

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 42.0 on the Noometry Index. GLM-4.5 costs 6.0× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Last verified . 24 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

GLM-4.5 Z.ai (Zhipu)

42.0

Rank #122 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 6 categories and GLM-4.5 in 2 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Claude Sonnet 4.5 leads 48.4 to 35.9.
  • The biggest single-benchmark swing is SWE-bench Verified (bash only): 71.4% for Claude Sonnet 4.5 and 54.2% for GLM-4.5.
  • GLM-4.5 is cheaper at $0.60 / $2.20 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • Claude Sonnet 4.5 accepts more context: 200K tokens versus 131K.
  • GLM-4.5 has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.5GLM-4.5
ProviderAnthropicZ.ai (Zhipu)
Noometry Index44.142.0
Released2025-09-292025-07-27
WeightsProprietaryOpen
Context window200K131K
Max output64K98K
Input $ / M tokens$3$0.60
Output $ / M tokens$15$2.20
Results tracked7327

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

Category by category

Coding Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 47.3 (#61), GLM-4.5: 41.4 (#125)

BenchmarkClaude Sonnet 4.5GLM-4.5
SWE-bench Verified (bash only)71.4%54.2%
WeirdML47.7%40.6%
LMArena Coding14891434
ALE-Bench796.15344.82
AlgoTune1.521.52
SWE-bench Verified71.3%—
LMArena WebDev1393—
SWE-bench Multilingual67%—
SciCode44.7%—
GSO14.7%—

Agentic & Tool Use Not comparable

Claude Sonnet 4.5: 38.3 (#32), GLM-4.5: —

BenchmarkClaude Sonnet 4.5GLM-4.5
Terminal-Bench46.5%—
Berkeley Function Calling Leaderboard73.2%—
GDPval42.5%—
Remote Labor Index2.1%—
τ²-bench Airline72%—
τ²-bench Banking25.3%—
τ²-bench Retail72.4%—
τ²-bench Telecom84.9%—
Cybench60%—
DeepResearch Bench52.6%—
OSWorld62.9%—
LMArena Search1159—
METR Time Horizons67.4%—
Vending-Bench 23,839—

Reasoning GLM-4.5 leads

Claude Sonnet 4.5: 26.9 (#125), GLM-4.5: 28.6 (#100)

BenchmarkClaude Sonnet 4.5GLM-4.5
Kagi LLM Benchmark57.9%57.9%
LMArena Hard Prompts14621429
ARC-AGI-213.6%—
SimpleBench54.3%—
NYT Connections (extended)37.3%—
ARC-AGI-163.7%—
CritPt1.1%—
Chess Puzzles12%—
EnigmaEval6%—
EBR-Bench2.4%—
Mystery Game Puzzles17%—
DTBench83.2%—
LMCA38.8%—
Epoch Capabilities Index146.84—
ForecastBench61.9—

Math GLM-4.5 leads

Claude Sonnet 4.5: 32.3 (#216), GLM-4.5: 39.0 (#116)

BenchmarkClaude Sonnet 4.5GLM-4.5
LMArena Math14491427
FrontierMath (Tiers 1-3)23.9%—
FrontierMath Tier 42.4%—
OTIS Mock AIME 2024-202577.8%—
ProofBench19%—
Omni-MATH55.3%—
MATH Level 597.7%—
FrontierMath (Feb 2025 set)15.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 48.4 (#76), GLM-4.5: 35.9 (#179)

BenchmarkClaude Sonnet 4.5GLM-4.5
Humanity's Last Exam13.7%8.3%
LMArena Expert14821433
GPQA Diamond82.3%—
SimpleQA Verified30.7%—
MMLU-Pro86.9%—
Confabulations—11.3%
Vectara Hallucination Rate12%—
GPQA (HELM)68.6%—

Multimodal Not comparable

Claude Sonnet 4.5: 34.8 (#89), GLM-4.5: —

BenchmarkClaude Sonnet 4.5GLM-4.5
VPCT39.8%—
LMArena Document1450—

Multilingual Too close to call

Claude Sonnet 4.5: 53.4 (#69), GLM-4.5: 52.8 (#77)

BenchmarkClaude Sonnet 4.5GLM-4.5
LMArena Non-English14251417
LMArena Chinese14591465
LMArena French14581418
LMArena German14271407
LMArena Japanese13901415
LMArena Korean14031380
LMArena Russian14371414
LMArena Spanish14571454

Instruction Following Too close to call

Claude Sonnet 4.5: 75.0 (#78), GLM-4.5: 74.1 (#104)

BenchmarkClaude Sonnet 4.5GLM-4.5
LMArena Instruction Following14591404
IFEval85%—

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#46), GLM-4.5: 38.2 (#201)

BenchmarkClaude Sonnet 4.5GLM-4.5
LMArena Longer Query14761412
Fiction.LiveBench—58.3%

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.5 (#34), GLM-4.5: 57.5 (#127)

BenchmarkClaude Sonnet 4.5GLM-4.5
LMArena Text14391430
LMArena Creative Writing14421395
EQ-Bench Creative Writing16781343
LMArena Multi-Turn14651415
Short-Story Creative Writing—73.4%
WildBench85.4%—

Frequently asked questions

Is Claude Sonnet 4.5 better than GLM-4.5?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 42.0 on the Noometry Index. GLM-4.5 costs 6.0× less per token, which makes it the better buy when Claude Sonnet 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 4.5 or GLM-4.5?

GLM-4.5 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.

Is Claude Sonnet 4.5 or GLM-4.5 better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 41.4 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.5 does, with 200K tokens against 131K.

How many benchmarks do Claude Sonnet 4.5 and GLM-4.5 share?

24 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and GLM-4.5 has 27.

Related comparisons

Go deeper