Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Llama 3.3 70B Instruct | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 50.5 | — |
| ARC-Challenge | — | 91.3 |
general
| Benchmark | Llama 3.3 70B Instruct | Mixtral 8x22B |
|---|---|---|
| Chatbot Arena Elo | — | 1146 |
| MMLU-Pro | — | 56.8 |
| IFEval | — | 72.4 |
safety
| Benchmark | Llama 3.3 70B Instruct | Mixtral 8x22B |
|---|---|---|
| TruthfulQA | — | 55.2 |
language
| Benchmark | Llama 3.3 70B Instruct | Mixtral 8x22B |
|---|---|---|
| HellaSwag | — | 88.5 |
| WinoGrande | — | 82.1 |
coding
| Benchmark | Llama 3.3 70B Instruct | Mixtral 8x22B |
|---|---|---|
| HumanEval | — | 79.3 |
Category Winners
coding
26.8
math
16.4
reasoning
26.2
general
8.0
language
22.6
safety
8.2