GPT-5 Codex vs Phi-4-multimodal-instruct
OpenAI vs Microsoft — benchmarks, pricing, and capabilities side by side.
- •GPT-5 Codex has the higher intelligence index (87.1 vs 46.2)
- •Phi-4-multimodal-instruct is cheaper ($0.05 vs $1.25 per 1M input)
- •GPT-5 Codex is faster
- •GPT-5 Codex has a larger context window (400K)
| GPT-5 Codex | Phi-4-multimodal-instruct | |
|---|---|---|
| Intelligence index | 87.1 | 46.2 |
| Developer | OpenAI | Microsoft |
| Type | Multimodal | Multimodal |
| Access | API only | Open weights |
| Context window | 400,000 tokens | 128,000 tokens |
| Input price | $1.25 / 1M | $0.05 / 1M |
| Output price | $10.00 / 1M | $0.10 / 1M |
| Speed | 180 tok/s | 25 tok/s |
| Released | September 23, 2025 | February 1, 2025 |
| Parameters | — | 5600000000 |
| Input modalities | Text, Image | — |
| Output modalities | Text | — |
Shared benchmarks
GPT-5 Codex
Phi-4-multimodal-instruct
GPQA Diamond
83.7
31.5
Humanity’s Last Exam
25.6
4.4
LiveCodeBench
84
13.1
MMLU-Pro
86.5
48.5