Noometry

Model comparison

Claude 3 Opus vs GLM-4.7

GLM-4.7 is the stronger model overall, scoring 42.0 to 29.5 on the Noometry Index.

Last verified . 23 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and GLM-4.7 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.7 leads 38.6 to 14.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 83.3% for GLM-4.7.
  • GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusGLM-4.7
ProviderAnthropicZ.ai (Zhipu)
Noometry Index29.542.0
Released2024-02-292025-12-22
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.60
Output $ / M tokens—$2.20
Results tracked4636

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

Category by category

Coding GLM-4.7 leads

Claude 3 Opus: 32.9 (#267), GLM-4.7: 44.0 (#79)

BenchmarkClaude 3 OpusGLM-4.7
LMArena Coding12641454
LMArena WebDev—1435
SciCode—45.1%
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
ALE-Bench—399.48
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use GLM-4.7 leads

Claude 3 Opus: 24.6 (#116), GLM-4.7: 26.5 (#103)

BenchmarkClaude 3 OpusGLM-4.7
Terminal-Bench—33.4%
Cybench10%—
METR Time Horizons29.5%—
Vending-Bench 2—2,377

Reasoning GLM-4.7 leads

Claude 3 Opus: 14.6 (#324), GLM-4.7: 24.3 (#164)

BenchmarkClaude 3 OpusGLM-4.7
SimpleBench23.5%47.7%
Chess Puzzles5%6%
LMArena Hard Prompts12451443
Epoch Capabilities Index126.91143.51
CritPt—1.7%
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
DTBench61.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math GLM-4.7 leads

Claude 3 Opus: 14.8 (#299), GLM-4.7: 38.6 (#135)

BenchmarkClaude 3 OpusGLM-4.7
OTIS Mock AIME 2024-20254.7%83.3%
LMArena Math12731423
ProofBench—6%
LiveBench Math43.6%—
MATH Level 537.5%—
FrontierMath (Feb 2025 set)—2.4%
FrontierMath Tier 4 (v1)—0%

Knowledge GLM-4.7 leads

Claude 3 Opus: 24.5 (#267), GLM-4.7: 47.0 (#80)

BenchmarkClaude 3 OpusGLM-4.7
GPQA Diamond47.2%83.3%
SimpleQA Verified12.6%32.2%
LMArena Expert12231424
Confabulations22.7%—
Vectara Hallucination Rate—11.7%
MMLU84.6%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), GLM-4.7: —

BenchmarkClaude 3 OpusGLM-4.7
LMArena Vision1023—

Multilingual GLM-4.7 leads

Claude 3 Opus: 41.4 (#207), GLM-4.7: 52.8 (#79)

BenchmarkClaude 3 OpusGLM-4.7
LMArena Non-English12581417
LMArena Chinese12481495
LMArena French12751432
LMArena German12581424
LMArena Japanese12041439
LMArena Korean11871399
LMArena Russian12801423
LMArena Spanish12461434

Instruction Following GLM-4.7 leads

Claude 3 Opus: 64.1 (#228), GLM-4.7: 74.4 (#95)

BenchmarkClaude 3 OpusGLM-4.7
LMArena Instruction Following12481411
LiveBench Instruction Following63.9%—

Long Context GLM-4.7 leads

Claude 3 Opus: 38.2 (#202), GLM-4.7: 42.8 (#116)

BenchmarkClaude 3 OpusGLM-4.7
LMArena Longer Query12591432
CL-bench—15.9%
CL-bench Life—10.9%

Writing & Preference GLM-4.7 leads

Claude 3 Opus: 47.2 (#213), GLM-4.7: 60.9 (#93)

BenchmarkClaude 3 OpusGLM-4.7
LMArena Text12621435
LMArena Creative Writing12351401
LMArena Multi-Turn12751446
EQ-Bench Creative Writing—1413
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than GLM-4.7?

GLM-4.7 is the stronger model overall, scoring 42.0 to 29.5 on the Noometry Index.

Is Claude 3 Opus or GLM-4.7 better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and GLM-4.7 share?

23 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and GLM-4.7 has 36.

Related comparisons

Go deeper