Neura Intelligence Index
| Benchmark | Nemotron 3 Ultra (550B A55B) | Qwen3 VL 32B Thinking |
|---|---|---|
| GPQA Diamond | 87 | 73.1 |
| Humanity's Last Exam | 37.4 | — |
| Benchmark | Nemotron 3 Ultra (550B A55B) | Qwen3 VL 32B Thinking |
|---|---|---|
| SWE-bench Verified | 70.7 | — |
| SciCode | 44.6 | — |
| Benchmark | Nemotron 3 Ultra (550B A55B) | Qwen3 VL 32B Thinking |
|---|---|---|
| BrowseComp | 44.4 | — |
| OSWorld | — | 41 |
| Benchmark | Nemotron 3 Ultra (550B A55B) | Qwen3 VL 32B Thinking |
|---|---|---|
| AIME 2025 | — | 83.7 |
| Benchmark | Nemotron 3 Ultra (550B A55B) | Qwen3 VL 32B Thinking |
|---|---|---|
| MMMU-Pro | — | 68.1 |
| CharXiv Reasoning | — | 65.2 |
| ScreenSpot Pro | — | 57.1 |
| Benchmark | Nemotron 3 Ultra (550B A55B) | Qwen3 VL 32B Thinking |
|---|---|---|
| SimpleQA | — | 55.4 |