Grok 4.7
- Made by
- SpaceXAI
- Weights
- Closed
- Released
- Sep 21, 2026
- Context
- 500K
- Price per 1M tokens
- $2 input, $6 output
| Benchmark | Score | Type | Measured by |
|---|---|---|---|
| Intelligence Index v5.0.1 (xhigh) | 35.5 | Independent | Artificial Analysis |
| Cost per test task | $7.77 | Independent | Artificial Analysis |
| HLE-Diamond | 23.2% | Independent | Artificial Analysis |
| Terminal-Bench 4.0 | 25.8% | Independent | Artificial Analysis |
| FrontierCode 2.0 | 28.7% | Independent | Artificial Analysis |
| CritPt v2 (Hard Subset) | 33.5% | Independent | Artificial Analysis |
Scores as of Nov 8, 2026. The Intelligence Index is a combined score from 9 tests that compares selected abilities, not overall usefulness. Scores from different test versions are not comparable, and makers sometimes publish different numbers from their own runs.
Sources: artificialanalysis.ai