AI Hub
← All models

GLM 4.7 vs Llama 3 70B Instruct

Zhipu AI vs Meta — benchmarks, pricing, and capabilities side by side.

  • GLM 4.7 has the higher intelligence index (89 vs 40.8)
  • GLM 4.7 is cheaper ($0.40 vs $0.51 per 1M input)
  • GLM 4.7 is faster
  • GLM 4.7 has a larger context window (203K)
GLM 4.7Llama 3 70B Instruct
Intelligence index8940.8
DeveloperZhipu AIMeta
TypeLLMLLM
AccessOpen weightsOpen weights
Context window202,752 tokens8,192 tokens
Input price$0.40 / 1M$0.51 / 1M
Output price$1.75 / 1M$0.74 / 1M
Speed98 tok/s45 tok/s
ReleasedDecember 22, 2025April 18, 2024
Parameters
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

GLM 4.7
Llama 3 70B Instruct
GPQA Diamond
85.9
37.9
Humanity’s Last Exam
25.1
4.4
LiveCodeBench
89.4
19.8
MMLU-Pro
85.6
57.4