xAI
Grok 4
At launch, open to SuperGrok and Premium+ subscribers and through the API.
- Announced
- Access
- Public
Benchmark scores
| Test | Score | Best on the tracker | How it was measured |
|---|---|---|---|
| GPQA DiamondPhD-level science questionsPhD experts: 70%Saturated | 87% | Gemini 4 Argon 96% | Independentdefault settings (grok-4-0709) |
| ARC-AGI-2visual puzzles, model aloneAverage person: 60%Saturated | 16% | GPT-6 Astra 95% | IndependentARC Prize config "Grok 4 (Thinking)" (grok-4-0709) |
| OTIS Mock AIMEcompetition mathsSaturated | 84% | GPT-5.5 100% | Independentdefault settings (grok-4-0709) |
Also on these charts
Sources
- Grok 4xAI · Official · x.ai
- xAI API release notesxAI · Official · docs.x.ai
- Epoch AI Benchmarking Hub (model release dates and runs)Epoch AI · Dataset · 9 Nov 2026 · epoch.ai