Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
math
| Benchmark | GPT-5.1 Medium | Grok-4 Heavy |
|---|---|---|
| AIME 2025 | 98.4 | 100 |
reasoning
| Benchmark | GPT-5.1 Medium | Grok-4 Heavy |
|---|---|---|
| GPQA Diamond | — | 88.4 |
| Humanity's Last Exam | — | 50.7 |
Category Winners
math
X
Grok-4 Heavy84.0
reasoning
X
Grok-4 Heavy86.7