Noometry

Model comparison

GLM-4.7-Flash vs Llama 3-70B

GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 28.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

GLM-4.7-Flash Z.ai (Zhipu)

38.8

Rank #180 Confirmed

Llama 3-70B Meta

28.8

Rank #323 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GLM-4.7-Flash scores higher in 8 categories and Llama 3-70B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.7-Flash leads 36.1 to 12.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 58.3% for GLM-4.7-Flash and 4.3% for Llama 3-70B.

Side by side

GLM-4.7-FlashLlama 3-70B
ProviderZ.ai (Zhipu)Meta
Noometry Index38.828.8
Released2026-01-192024-04-18
WeightsOpenOpen
Context window200K—
Max output131K—
Input $ / M tokens$0.06—
Output $ / M tokens$0.40—
Results tracked2131

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

Category by category

Coding GLM-4.7-Flash leads

GLM-4.7-Flash: 40.6 (#135), Llama 3-70B: 35.8 (#218)

BenchmarkGLM-4.7-FlashLlama 3-70B
LMArena Coding13831206
BigCodeBench Instruct—43.6%
BigCodeBench Complete—54.5%
HumanEval+—72%
MBPP+—69%

Agentic & Tool Use Not comparable

GLM-4.7-Flash: —, Llama 3-70B: 21.1 (#139)

BenchmarkGLM-4.7-FlashLlama 3-70B
Cybench—5%

Reasoning GLM-4.7-Flash leads

GLM-4.7-Flash: 20.9 (#229), Llama 3-70B: 18.0 (#288)

BenchmarkGLM-4.7-FlashLlama 3-70B
LMArena Hard Prompts13561195
Kagi LLM Benchmark—35.1%
Chess Puzzles0%—
DTBench—54.2%
Epoch Capabilities Index—122.93
ForecastBench—57.1
WinoGrande—83.5%

Math GLM-4.7-Flash leads

GLM-4.7-Flash: 36.1 (#173), Llama 3-70B: 12.8 (#305)

BenchmarkGLM-4.7-FlashLlama 3-70B
OTIS Mock AIME 2024-202558.3%4.3%
LMArena Math13551218
MATH Level 5—22.6%

Knowledge GLM-4.7-Flash leads

GLM-4.7-Flash: 35.5 (#184), Llama 3-70B: 20.8 (#277)

BenchmarkGLM-4.7-FlashLlama 3-70B
GPQA Diamond60.5%40.6%
LMArena Expert13571149
Vectara Hallucination Rate9.3%—
MMLU—79.3%

Multilingual GLM-4.7-Flash leads

GLM-4.7-Flash: 46.5 (#158), Llama 3-70B: 33.6 (#251)

BenchmarkGLM-4.7-FlashLlama 3-70B
LMArena Non-English13301142
LMArena Chinese14031114
LMArena French13321232
LMArena German13371169
LMArena Korean12831017
LMArena Russian13321159
LMArena Spanish13501241
LMArena Japanese—1017

Instruction Following GLM-4.7-Flash leads

GLM-4.7-Flash: 70.1 (#167), Llama 3-70B: 62.5 (#238)

BenchmarkGLM-4.7-FlashLlama 3-70B
LMArena Instruction Following13271194

Long Context GLM-4.7-Flash leads

GLM-4.7-Flash: 40.9 (#148), Llama 3-70B: 35.6 (#240)

BenchmarkGLM-4.7-FlashLlama 3-70B
LMArena Longer Query13451174

Writing & Preference GLM-4.7-Flash leads

GLM-4.7-Flash: 47.4 (#210), Llama 3-70B: 42.8 (#231)

BenchmarkGLM-4.7-FlashLlama 3-70B
LMArena Text13511221
LMArena Creative Writing12971210
LMArena Multi-Turn13421223
EQ-Bench Creative Writing1125—

Frequently asked questions

Is GLM-4.7-Flash better than Llama 3-70B?

GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 28.8 on the Noometry Index.

Is GLM-4.7-Flash or Llama 3-70B better for coding?

GLM-4.7-Flash scores higher on coding benchmarks: 40.6 versus 35.8 in the Noometry coding category.

How many benchmarks do GLM-4.7-Flash and Llama 3-70B share?

18 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Llama 3-70B has 31.

Related comparisons

Go deeper