7 X-ai models evaluated
| Rank | Model | Accuracy | Correct | Total | Incorrect | Errors |
|---|---|---|---|---|---|---|
| 1 | X-ai/Grok-4 |
98.9 ± 1.1% | 61 | 61 | 0 | 0 |
| 2 | X-ai/Grok-3 |
95.8 ± 3.2% | 60 | 62 | 2 | 0 |
| 3 | X-ai/Grok-3-Mini |
92.0 ± 5.1% | 53 | 57 | 4 | 0 |
| 3 | X-ai/Grok-4-Fast |
92.0 ± 5.1% | 53 | 57 | 4 | 0 |
| 4 | X-ai/Grok-3-Beta |
91.6 ± 5.4% | 50 | 54 | 4 | 0 |
| 5 | X-ai/Grok-3-Mini-Beta |
88.6 ± 6.4% | 51 | 57 | 6 | 0 |
| 6 | X-ai/Grok-Code-Fast-1 |
80.5 ± 10.2% | 31 | 38 | 5 | 2 |