Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Llama 3.1 Nemotron Ultra 253B v1 | Qwen3 VL 235B A22B Instruct |
|---|---|---|
| GPQA Diamond | 76.0 | — |
math
| Benchmark | Llama 3.1 Nemotron Ultra 253B v1 | Qwen3 VL 235B A22B Instruct |
|---|---|---|
| AIME 2025 | 72.5 | 74.7 |
multimodal
| Benchmark | Llama 3.1 Nemotron Ultra 253B v1 | Qwen3 VL 235B A22B Instruct |
|---|---|---|
| MMMU-Pro | — | 68.1 |
| CharXiv Reasoning | — | 62.1 |
| ScreenSpot Pro | — | 62 |
general
| Benchmark | Llama 3.1 Nemotron Ultra 253B v1 | Qwen3 VL 235B A22B Instruct |
|---|---|---|
| SimpleQA | — | 51.9 |
agent
| Benchmark | Llama 3.1 Nemotron Ultra 253B v1 | Qwen3 VL 235B A22B Instruct |
|---|---|---|
| OSWorld | — | 66.7 |
Category Winners
math
Q
Qwen3 VL 235B A22B Instruct41.5
reasoning
66.3
general
Q
Qwen3 VL 235B A22B Instruct70.6
multimodal
Q
Qwen3 VL 235B A22B Instruct37.4
agent
Q
Qwen3 VL 235B A22B Instruct83.0