AI Hub
← All models

GPT-5.3-Codex vs Phi-4-multimodal-instruct

OpenAI vs Microsoft — benchmarks, pricing, and capabilities side by side.

  • GPT-5.3-Codex has the higher intelligence index (91.5 vs 46.2)
  • Phi-4-multimodal-instruct is cheaper ($0.05 vs $1.75 per 1M input)
  • GPT-5.3-Codex is faster
  • GPT-5.3-Codex has a larger context window (400K)
GPT-5.3-CodexPhi-4-multimodal-instruct
Intelligence index91.546.2
DeveloperOpenAIMicrosoft
TypeMultimodalMultimodal
AccessAPI onlyOpen weights
Context window400,000 tokens128,000 tokens
Input price$1.75 / 1M$0.05 / 1M
Output price$14.00 / 1M$0.10 / 1M
Speed73 tok/s25 tok/s
ReleasedFebruary 24, 2026February 1, 2025
Parameters5600000000
Input modalitiesText, Image
Output modalitiesText

Shared benchmarks

GPT-5.3-Codex
Phi-4-multimodal-instruct
GPQA Diamond
91.5
31.5
Humanity’s Last Exam
39.9
4.4