Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Mistral Small 3 24B Instruct | Phi-3 Medium |
|---|---|---|
| GPQA Diamond | 45.3 | — |
| ARC-Challenge | — | 91.6 |
language
| Benchmark | Mistral Small 3 24B Instruct | Phi-3 Medium |
|---|---|---|
| HellaSwag | — | 86.8 |
| WinoGrande | — | 81.4 |
general
| Benchmark | Mistral Small 3 24B Instruct | Phi-3 Medium |
|---|---|---|
| Chatbot Arena Elo | — | 1120 |
| MMLU-Pro | — | 53.5 |
safety
| Benchmark | Mistral Small 3 24B Instruct | Phi-3 Medium |
|---|---|---|
| TruthfulQA | — | 59.1 |
coding
| Benchmark | Mistral Small 3 24B Instruct | Phi-3 Medium |
|---|---|---|
| HumanEval | — | 62.2 |
Category Winners
coding
0.5
math
6.4
reasoning
29.1
general
5.2
language
13.9
safety
22.4