Noometry

Model comparison

GLM-4.7-Flash vs Llama 3.2 3B

GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 28.9 on the Noometry Index.

Last verified . 14 shared benchmarks.

GLM-4.7-Flash Z.ai (Zhipu)

38.8

Rank #180 Confirmed

Llama 3.2 3B Meta

28.9

Rank #321 Confirmed

Summary

  • They share 14 benchmarks with published results for both. GLM-4.7-Flash scores higher in 7 categories and Llama 3.2 3B in 1 category; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GLM-4.7-Flash leads 47.4 to 24.7.
  • Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $0.06 / $0.40 for GLM-4.7-Flash.
  • GLM-4.7-Flash accepts more context: 200K tokens versus 131K.

Side by side

GLM-4.7-FlashLlama 3.2 3B
ProviderZ.ai (Zhipu)Meta
Noometry Index38.828.9
Released2026-01-192024-09-24
WeightsOpenOpen
Context window200K131K
Max output131K118K
Input $ / M tokens$0.06$0.05
Output $ / M tokens$0.40$0.33
Results tracked2118

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 3.2 3B: 27.6 (#319)

BenchmarkGLM-4.7-FlashLlama 3.2 3B
LMArena Coding13831098
BigCodeBench Instruct—23.4%
BigCodeBench Complete—28.3%

Agentic & Tool Use Not comparable

GLM-4.7-Flash: —, Llama 3.2 3B: 20.1 (#143)

BenchmarkGLM-4.7-FlashLlama 3.2 3B
Berkeley Function Calling Leaderboard—21.9%
BALROG—10.1%

Reasoning Too close to call

GLM-4.7-Flash: 20.9 (#229), Llama 3.2 3B: 21.0 (#228)

BenchmarkGLM-4.7-FlashLlama 3.2 3B
LMArena Hard Prompts13561095
Chess Puzzles0%—

Math GLM-4.7-Flash leads

GLM-4.7-Flash: 36.1 (#173), Llama 3.2 3B: 32.4 (#214)

BenchmarkGLM-4.7-FlashLlama 3.2 3B
LMArena Math13551126
OTIS Mock AIME 2024-202558.3%—

Knowledge GLM-4.7-Flash leads

GLM-4.7-Flash: 35.5 (#184), Llama 3.2 3B: 29.7 (#235)

BenchmarkGLM-4.7-FlashLlama 3.2 3B
LMArena Expert13571090
GPQA Diamond60.5%—
Vectara Hallucination Rate9.3%—

Multilingual GLM-4.7-Flash leads

GLM-4.7-Flash: 46.5 (#158), Llama 3.2 3B: 26.2 (#281)

BenchmarkGLM-4.7-FlashLlama 3.2 3B
LMArena Non-English13301019
LMArena Chinese14031017
LMArena German13371056
LMArena Russian1332949
LMArena French1332—
LMArena Korean1283—
LMArena Spanish1350—

Instruction Following GLM-4.7-Flash leads

GLM-4.7-Flash: 70.1 (#167), Llama 3.2 3B: 56.0 (#275)

BenchmarkGLM-4.7-FlashLlama 3.2 3B
LMArena Instruction Following13271089

Long Context GLM-4.7-Flash leads

GLM-4.7-Flash: 40.9 (#148), Llama 3.2 3B: 33.4 (#261)

BenchmarkGLM-4.7-FlashLlama 3.2 3B
LMArena Longer Query13451100

Writing & Preference GLM-4.7-Flash leads

GLM-4.7-Flash: 47.4 (#210), Llama 3.2 3B: 24.7 (#307)

BenchmarkGLM-4.7-FlashLlama 3.2 3B
LMArena Text13511110
LMArena Creative Writing12971094
EQ-Bench Creative Writing1125595
LMArena Multi-Turn13421105

Frequently asked questions

Is GLM-4.7-Flash better than Llama 3.2 3B?

GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 28.9 on the Noometry Index.

Which is cheaper, GLM-4.7-Flash or Llama 3.2 3B?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; GLM-4.7-Flash lists at $0.06 and $0.40.

Is GLM-4.7-Flash or Llama 3.2 3B better for coding?

GLM-4.7-Flash scores higher on coding benchmarks: 40.6 versus 27.6 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7-Flash does, with 200K tokens against 131K.

How many benchmarks do GLM-4.7-Flash and Llama 3.2 3B share?

14 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Llama 3.2 3B has 18.

Related comparisons

Go deeper