Grok-4 Heavy
by xAI
Grok-4 Heavy is a model from xAI, released on July 9, 2025. It ranks #45 of 220 models by Intelligence Score with a score of 40.6.
Grok 4 Heavy is the multi-agent version of Grok 4, released alongside the standard model in summer 2025. This system spawns multiple Grok 4 agents in parallel that work independently on problems and then collaborate by comparing their solutions, similar to a study group. The agents share insights and tricks they discover, with the system intelligently combining their work rather than simply using majority voting. Grok 4 Heavy uses approximately 10x more test-time compute than regular Grok 4, enabling it to solve significantly more complex problems. On the Humanities Last Exam, it achieves over 50% accuracy on text-only problems, and it scored a perfect result on the AIME 2025 mathematics competition. The system represents a major advancement in multi-agent AI collaboration and reasoning capabilities.
Key specs
| Provider | xAI |
|---|---|
| Release date | 2025-07-09 |
| License | proprietary |
| Intelligence Score | 40.6 |
| Coding index | 17.6 |
Quick answers
Is Grok-4 Heavy open source?
No. Grok-4 Heavy is a proprietary model from xAI (proprietary license).
When was Grok-4 Heavy released?
xAI released Grok-4 Heavy on July 9, 2025.
How does Grok-4 Heavy compare to Claude Opus 5.5 (Reasoning)?
Grok-4 Heavy scores 40.6 on the Intelligence Score versus 60.5 for Claude Opus 5.5 (Reasoning), the current #1.
Compare on the AI leaderboard · All AI models
More models from xAI
- Grok 4.7 (Reasoning) — xAI
- Grok 4.6 (Reasoning) — xAI
- Grok-4.20 Beta Reasoning (Reasoning) — xAI
- Grok-4.1 — xAI
- Grok-4.1 Thinking (Reasoning) — xAI
- Grok-2 mini — xAI