Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Mistral Small 4 | Phi 4 Reasoning Plus |
|---|---|---|
| GPQA Diamond | 71.2 | 68.9 |
math
| Benchmark | Mistral Small 4 | Phi 4 Reasoning Plus |
|---|---|---|
| AIME 2025 | 83.8 | 78 |
multimodal
| Benchmark | Mistral Small 4 | Phi 4 Reasoning Plus |
|---|---|---|
| MMMU-Pro | 60 | — |
Category Winners
math
58.7
reasoning
56.2
multimodal
27.3