Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Mistral Small 3 24B Instruct | Qwen3 VL 8B Instruct |
|---|---|---|
| GPQA Diamond | 45.3 | — |
math
| Benchmark | Mistral Small 3 24B Instruct | Qwen3 VL 8B Instruct |
|---|---|---|
| AIME 2025 | — | 45.9 |
multimodal
| Benchmark | Mistral Small 3 24B Instruct | Qwen3 VL 8B Instruct |
|---|---|---|
| MMMU-Pro | — | 55.9 |
| CharXiv Reasoning | — | 46.4 |
| ScreenSpot Pro | — | 54.6 |
agent
| Benchmark | Mistral Small 3 24B Instruct | Qwen3 VL 8B Instruct |
|---|---|---|
| OSWorld | — | 33.9 |
Category Winners
math
Q
Qwen3 VL 8B Instruct5.7
reasoning
14.2
multimodal
Q
Qwen3 VL 8B Instruct17.4
agent
Q
Qwen3 VL 8B Instruct28.8