Neura Intelligence Index
| Benchmark | Mixtral 8x22B | Phi 4 Mini Reasoning |
|---|---|---|
| Chatbot Arena Elo | 1146 | — |
| MMLU-Pro | 56.8 | — |
| IFEval | 72.4 | — |
| Benchmark | Mixtral 8x22B | Phi 4 Mini Reasoning |
|---|---|---|
| TruthfulQA | 55.2 | — |
| Benchmark | Mixtral 8x22B | Phi 4 Mini Reasoning |
|---|---|---|
| ARC-Challenge | 91.3 | — |
| GPQA Diamond | — | 52 |
| Benchmark | Mixtral 8x22B | Phi 4 Mini Reasoning |
|---|---|---|
| HellaSwag | 88.5 | — |
| WinoGrande | 82.1 | — |
| Benchmark | Mixtral 8x22B | Phi 4 Mini Reasoning |
|---|---|---|
| HumanEval | 79.3 | — |