Noometry

Model comparison

Claude 3 Opus vs GLM-4.7-Flash

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 29.3 on the Noometry Index.

Last verified . 19 shared benchmarks.

Claude 3 Opus Anthropic

29.3

Rank #300 Confirmed

GLM-4.7-Flash Z.ai (Zhipu)

38.4

Rank #175 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and GLM-4.7-Flash in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.7-Flash leads 34.4 to 13.9.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.7% for Claude 3 Opus and 58.3% for GLM-4.7-Flash.
  • GLM-4.7-Flash has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusGLM-4.7-Flash
ProviderAnthropicZ.ai (Zhipu)
Noometry Index29.338.4
Released2024-02-292026-01-19
WeightsProprietaryOpen
Context window—200K
Max output—131K
Input $ / M tokens—$0.06
Output $ / M tokens—$0.40
Results tracked4621

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

Category by category

Coding GLM-4.7-Flash leads

Claude 3 Opus: 32.4 (#261), GLM-4.7-Flash: 40.0 (#133)

BenchmarkClaude 3 OpusGLM-4.7-Flash
LMArena Coding12641383
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

Claude 3 Opus: 24.3 (#110), GLM-4.7-Flash: —

BenchmarkClaude 3 OpusGLM-4.7-Flash
Cybench10%—
METR Time Horizons29.5%—

Reasoning GLM-4.7-Flash leads

Claude 3 Opus: 14.2 (#318), GLM-4.7-Flash: 20.2 (#224)

BenchmarkClaude 3 OpusGLM-4.7-Flash
Chess Puzzles5%0%
LMArena Hard Prompts12461356
SimpleBench23.5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
DTBench61.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
Epoch Capabilities Index126.91—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math GLM-4.7-Flash leads

Claude 3 Opus: 13.9 (#293), GLM-4.7-Flash: 34.4 (#159)

BenchmarkClaude 3 OpusGLM-4.7-Flash
OTIS Mock AIME 2024-20254.7%58.3%
LMArena Math12731354
LiveBench Math43.6%—
MATH Level 537.5%—

Knowledge GLM-4.7-Flash leads

Claude 3 Opus: 24.5 (#262), GLM-4.7-Flash: 35.4 (#177)

BenchmarkClaude 3 OpusGLM-4.7-Flash
GPQA Diamond47.2%60.5%
LMArena Expert12231357
SimpleQA Verified12.6%—
Confabulations22.7%—
Vectara Hallucination Rate—9.3%
MMLU84.6%—

Multimodal Not comparable

Claude 3 Opus: 26.6 (#112), GLM-4.7-Flash: —

BenchmarkClaude 3 OpusGLM-4.7-Flash
LMArena Vision1023—

Multilingual GLM-4.7-Flash leads

Claude 3 Opus: 41.6 (#202), GLM-4.7-Flash: 46.8 (#152)

BenchmarkClaude 3 OpusGLM-4.7-Flash
LMArena Non-English12581331
LMArena Chinese12481403
LMArena French12741332
LMArena German12581336
LMArena Korean11871284
LMArena Russian12801333
LMArena Spanish12461351
LMArena Japanese1204—

Instruction Following GLM-4.7-Flash leads

Claude 3 Opus: 64.3 (#223), GLM-4.7-Flash: 70.3 (#162)

BenchmarkClaude 3 OpusGLM-4.7-Flash
LMArena Instruction Following12481327
LiveBench Instruction Following63.9%—

Long Context GLM-4.7-Flash leads

Claude 3 Opus: 38.2 (#197), GLM-4.7-Flash: 40.9 (#143)

BenchmarkClaude 3 OpusGLM-4.7-Flash
LMArena Longer Query12591345

Writing & Preference Too close to call

Claude 3 Opus: 47.4 (#208), GLM-4.7-Flash: 47.7 (#206)

BenchmarkClaude 3 OpusGLM-4.7-Flash
LMArena Text12621351
LMArena Creative Writing12351297
LMArena Multi-Turn12751342
EQ-Bench Creative Writing—1125
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than GLM-4.7-Flash?

GLM-4.7-Flash is the stronger model overall, scoring 38.4 to 29.3 on the Noometry Index.

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

GLM-4.7-Flash scores higher on coding benchmarks: 40.0 versus 32.4 in the Noometry coding category.

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

19 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and GLM-4.7-Flash has 21.

Related comparisons

Go deeper