Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | DeepSeek-V3 | Phi 4 Mini Reasoning |
|---|---|---|
| GPQA Diamond | 59.1 | 52 |
coding
| Benchmark | DeepSeek-V3 | Phi 4 Mini Reasoning |
|---|---|---|
| SWE-bench Verified | 42 | — |
general
| Benchmark | DeepSeek-V3 | Phi 4 Mini Reasoning |
|---|---|---|
| SimpleQA | 24.9 | — |
Category Winners
coding
7.1
reasoning
32.6
general
30.5