AI Hub
← All models

GLM 4.7 vs Phi 4 Mini Instruct

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

  • GLM 4.7 has the higher intelligence index (89 vs 32.6)
  • Phi 4 Mini Instruct is cheaper ($0.08 vs $0.40 per 1M input)
  • GLM 4.7 has a larger context window (203K)
GLM 4.7Phi 4 Mini Instruct
Intelligence index8932.6
DeveloperZhipu AIMicrosoft
TypeLLMLLM
AccessOpen weightsOpen weights
Context window202,752 tokens131,072 tokens
Input price$0.40 / 1M$0.08 / 1M
Output price$1.75 / 1M$0.35 / 1M
Speed98 tok/s
ReleasedDecember 22, 2025October 17, 2025
Parameters
Input modalitiesTextText
Output modalitiesTextText

Shared benchmarks

GLM 4.7
Phi 4 Mini Instruct
AIME 2025
95
6.7
GPQA Diamond
85.9
33.1
Humanity’s Last Exam
25.1
4.2
LiveCodeBench
89.4
12.6
MMLU-Pro
85.6
46.5