Grok 4.3 vs Phi-3.5-MoE-instruct
xAI vs Microsoft — benchmarks, pricing, and capabilities side by side.
- •Grok 4.3 has the higher intelligence index (90.1 vs 49.8)
| Grok 4.3 | Phi-3.5-MoE-instruct | |
|---|---|---|
| Intelligence index | 90.1 | 49.8 |
| Developer | xAI | Microsoft |
| Type | LLM | LLM |
| Access | API only | Open weights |
| Context window | 1,000,000 tokens | — |
| Input price | $1.25 / 1M | — |
| Output price | $2.50 / 1M | — |
| Speed | 88 tok/s | — |
| Released | May 6, 2026 | August 23, 2024 |
| Parameters | — | 60000000000 |
| Input modalities | Text, Image | — |
| Output modalities | Text | — |
Shared benchmarks
Grok 4.3
Phi-3.5-MoE-instruct
GPQA Diamond
90.1
36.8