Grok-3 vs Grok-4 Heavy
xAI vs xAI — benchmarks, pricing, and capabilities side by side.
- •Grok-4 Heavy has the higher intelligence index (89.3 vs 82.6)
| Grok-3 | Grok-4 Heavy | |
|---|---|---|
| Intelligence index | 82.6 | 89.3 |
| Developer | xAI | xAI |
| Type | Multimodal | Multimodal |
| Access | API only | API only |
| Context window | 128,000 tokens | — |
| Input price | $3.00 / 1M | — |
| Output price | $15.00 / 1M | — |
| Speed | 100 tok/s | — |
| Released | February 17, 2025 | July 9, 2025 |
| Parameters | — | — |
| Input modalities | Text, Image | — |
| Output modalities | Text | — |
Shared benchmarks
Grok-3
Grok-4 Heavy
AIME 2025
93.3
100
GPQA Diamond
84.6
88.4
Humanity’s Last Exam
5.1
50.7
LiveCodeBench
79.4
79.4