GPT-5.1 vs Phi 4
OpenAI vs Microsoft — benchmarks, pricing, and capabilities side by side.
- •GPT-5.1 has the higher intelligence index (89 vs 47.6)
- •Phi 4 is cheaper ($0.07 vs $1.25 per 1M input)
- •GPT-5.1 is faster
- •GPT-5.1 has a larger context window (400K)
| GPT-5.1 | Phi 4 | |
|---|---|---|
| Intelligence index | 89 | 47.6 |
| Developer | OpenAI | Microsoft |
| Type | LLM | LLM |
| Access | API only | Open weights |
| Context window | 400,000 tokens | 16,384 tokens |
| Input price | $1.25 / 1M | $0.07 / 1M |
| Output price | $10.00 / 1M | $0.14 / 1M |
| Speed | 115 tok/s | 33 tok/s |
| Released | November 12, 2025 | January 10, 2025 |
| Parameters | — | — |
| Input modalities | Text, Image | Text |
| Output modalities | Text | Text |
Shared benchmarks
GPT-5.1
Phi 4
AIME 2025
94
18
GPQA Diamond
88.1
56.1
Humanity’s Last Exam
26.5
4.1
LiveCodeBench
86.8
23.1
MMLU-Pro
87
70.4