Neura Intelligence Index
| Benchmark | Grok-4 | Qwen3-Coder 480B A35B Instruct |
|---|---|---|
| GPQA Diamond | 87.5 | — |
| Humanity's Last Exam | 40 | — |
| ARC-AGI v2 | 15.9 | — |
| Benchmark | Grok-4 | Qwen3-Coder 480B A35B Instruct |
|---|---|---|
| AIME 2025 | 91.7 | — |
| Benchmark | Grok-4 | Qwen3-Coder 480B A35B Instruct |
|---|---|---|
| SWE-bench Verified | — | 69.6 |
| Benchmark | Grok-4 | Qwen3-Coder 480B A35B Instruct |
|---|---|---|
| TAU-Bench Retail | — | 77.5 |