Noometry

Model comparison

Claude Sonnet 4.5 vs GLM-4.7

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 42.0 on the Noometry Index. GLM-4.7 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 . 34 shared benchmarks.

Claude Sonnet 4.5 Anthropic

44.1

Rank #81 Confirmed

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 8 categories and GLM-4.7 in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Sonnet 4.5 leads 38.3 to 26.5.
  • The biggest single-benchmark swing is Terminal-Bench: 46.5% for Claude Sonnet 4.5 and 33.4% for GLM-4.7.
  • GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
  • GLM-4.7 accepts more context: 205K tokens versus 200K.
  • GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.5GLM-4.7
ProviderAnthropicZ.ai (Zhipu)
Noometry Index44.142.0
Released2025-09-292025-12-22
WeightsProprietaryOpen
Context window200K205K
Max output64K131K
Input $ / M tokens$3$0.60
Output $ / M tokens$15$2.20
Results tracked7336

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-4.7: 44.0 (#79)

BenchmarkClaude Sonnet 4.5GLM-4.7
LMArena WebDev13931435
SciCode44.7%45.1%
LMArena Coding14891454
ALE-Bench796.15399.48
SWE-bench Verified71.3%—
SWE-bench Verified (bash only)71.4%—
SWE-bench Multilingual67%—
GSO14.7%—
WeirdML47.7%—
AlgoTune1.52—

Agentic & Tool Use Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 38.3 (#32), GLM-4.7: 26.5 (#103)

BenchmarkClaude Sonnet 4.5GLM-4.7
Terminal-Bench46.5%33.4%
Vending-Bench 23,8392,377
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%—

Reasoning Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 26.9 (#125), GLM-4.7: 24.3 (#164)

BenchmarkClaude Sonnet 4.5GLM-4.7
SimpleBench54.3%47.7%
CritPt1.1%1.7%
Chess Puzzles12%6%
LMArena Hard Prompts14621443
Epoch Capabilities Index146.84143.51
ARC-AGI-213.6%—
Kagi LLM Benchmark57.9%—
NYT Connections (extended)37.3%—
ARC-AGI-163.7%—
EnigmaEval6%—
EBR-Bench2.4%—
Mystery Game Puzzles17%—
DTBench83.2%—
LMCA38.8%—
ForecastBench61.9—

Math GLM-4.7 leads

Claude Sonnet 4.5: 32.3 (#216), GLM-4.7: 38.6 (#135)

BenchmarkClaude Sonnet 4.5GLM-4.7
OTIS Mock AIME 2024-202577.8%83.3%
ProofBench19%6%
LMArena Math14491423
FrontierMath (Feb 2025 set)15.2%2.4%
FrontierMath Tier 4 (v1)4.2%0%
FrontierMath (Tiers 1-3)23.9%—
FrontierMath Tier 42.4%—
Omni-MATH55.3%—
MATH Level 597.7%—

Knowledge Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 48.4 (#76), GLM-4.7: 47.0 (#80)

BenchmarkClaude Sonnet 4.5GLM-4.7
GPQA Diamond82.3%83.3%
SimpleQA Verified30.7%32.2%
Vectara Hallucination Rate12%11.7%
LMArena Expert14821424
Humanity's Last Exam13.7%—
MMLU-Pro86.9%—
GPQA (HELM)68.6%—

Multimodal Not comparable

Claude Sonnet 4.5: 34.8 (#89), GLM-4.7: —

BenchmarkClaude Sonnet 4.5GLM-4.7
VPCT39.8%—
LMArena Document1450—

Multilingual Too close to call

Claude Sonnet 4.5: 53.4 (#69), GLM-4.7: 52.8 (#79)

BenchmarkClaude Sonnet 4.5GLM-4.7
LMArena Non-English14251417
LMArena Chinese14591495
LMArena French14581432
LMArena German14271424
LMArena Japanese13901439
LMArena Korean14031399
LMArena Russian14371423
LMArena Spanish14571434

Instruction Following Too close to call

Claude Sonnet 4.5: 75.0 (#78), GLM-4.7: 74.4 (#95)

BenchmarkClaude Sonnet 4.5GLM-4.7
LMArena Instruction Following14591411
IFEval85%—

Long Context Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 45.2 (#46), GLM-4.7: 42.8 (#116)

BenchmarkClaude Sonnet 4.5GLM-4.7
LMArena Longer Query14761432
CL-bench—15.9%
CL-bench Life—10.9%

Writing & Preference Claude Sonnet 4.5 leads

Claude Sonnet 4.5: 66.5 (#34), GLM-4.7: 60.9 (#93)

BenchmarkClaude Sonnet 4.5GLM-4.7
LMArena Text14391435
LMArena Creative Writing14421401
EQ-Bench Creative Writing16781413
LMArena Multi-Turn14651446
WildBench85.4%—

Frequently asked questions

Is Claude Sonnet 4.5 better than GLM-4.7?

Claude Sonnet 4.5 is the stronger model overall, scoring 44.1 to 42.0 on the Noometry Index. GLM-4.7 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-4.7?

GLM-4.7 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-4.7 better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.3 versus 44.0 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 200K.

How many benchmarks do Claude Sonnet 4.5 and GLM-4.7 share?

34 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and GLM-4.7 has 36.

Related comparisons

Go deeper