Grok-4 Heavy vs Mistral Medium 3.1
xAI vs Mistral AI — benchmarks, pricing, and capabilities side by side.
- •Grok-4 Heavy has the higher intelligence index (89.3 vs 51.5)
| Grok-4 Heavy | Mistral Medium 3.1 | |
|---|---|---|
| Intelligence index | 89.3 | 51.5 |
| Developer | xAI | Mistral AI |
| Type | Multimodal | Multimodal |
| Access | API only | API only |
| Context window | — | 131,072 tokens |
| Input price | — | $0.40 / 1M |
| Output price | — | $2.00 / 1M |
| Speed | — | 47 tok/s |
| Released | July 9, 2025 | August 13, 2025 |
| Parameters | — | — |
| Input modalities | — | Text, Image |
| Output modalities | — | Text |
Shared benchmarks
Grok-4 Heavy
Mistral Medium 3.1
AIME 2025
100
38.3
GPQA Diamond
88.4
58.8
Humanity’s Last Exam
50.7
4.4
LiveCodeBench
79.4
40.6