Neura Intelligence Index
| Benchmark | IBM Granite 4.2 30B | Qwen3 VL 235B A22B Thinking |
|---|---|---|
| GPQA Diamond | 66.4 | — |
| Humanity's Last Exam | — | 13.6 |
| Benchmark | IBM Granite 4.2 30B | Qwen3 VL 235B A22B Thinking |
|---|---|---|
| AIME 2025 | 89.2 | 89.7 |
| Benchmark | IBM Granite 4.2 30B | Qwen3 VL 235B A22B Thinking |
|---|---|---|
| SWE-bench Verified | 57 | — |
| SWE-Bench Pro | 33.3 | — |
| SciCode | 38.8 | — |
| Benchmark | IBM Granite 4.2 30B | Qwen3 VL 235B A22B Thinking |
|---|---|---|
| MMMU-Pro | — | 69.3 |
| CharXiv Reasoning | — | 66.1 |
| ScreenSpot Pro | — | 61.8 |
| Benchmark | IBM Granite 4.2 30B | Qwen3 VL 235B A22B Thinking |
|---|---|---|
| SimpleQA | — | 44.4 |
| Benchmark | IBM Granite 4.2 30B | Qwen3 VL 235B A22B Thinking |
|---|---|---|
| OSWorld | — | 38.1 |