Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Mistral Small 3.2 24B Instruct | Qwen2.5 VL 72B Instruct |
|---|---|---|
| GPQA Diamond | 46.1 | — |
multimodal
| Benchmark | Mistral Small 3.2 24B Instruct | Qwen2.5 VL 72B Instruct |
|---|---|---|
| MMMU | 62.5 | 70.2 |
| MMMU-Pro | — | 51.1 |
| ScreenSpot Pro | — | 43.6 |
general
| Benchmark | Mistral Small 3.2 24B Instruct | Qwen2.5 VL 72B Instruct |
|---|---|---|
| SimpleQA | 12.1 | — |
agent
| Benchmark | Mistral Small 3.2 24B Instruct | Qwen2.5 VL 72B Instruct |
|---|---|---|
| OSWorld | — | 8.8 |
Category Winners
reasoning
14.0
general
15.7
multimodal
35.7
agent
Q
Qwen2.5 VL 72B Instruct4.3