Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | GPT-4.1 nano | Phi-3 Medium |
|---|---|---|
| GPQA Diamond | 50.3 | — |
| ARC-Challenge | — | 91.6 |
multimodal
| Benchmark | GPT-4.1 nano | Phi-3 Medium |
|---|---|---|
| MMMU | 55.4 | — |
| CharXiv Reasoning | 40.5 | — |
general
| Benchmark | GPT-4.1 nano | Phi-3 Medium |
|---|---|---|
| MMMLU | 66.9 | — |
| Chatbot Arena Elo | — | 1120 |
| MMLU-Pro | — | 53.5 |
agent
| Benchmark | GPT-4.1 nano | Phi-3 Medium |
|---|---|---|
| TAU-Bench Retail | 22.6 | — |
language
| Benchmark | GPT-4.1 nano | Phi-3 Medium |
|---|---|---|
| HellaSwag | — | 86.8 |
| WinoGrande | — | 81.4 |
safety
| Benchmark | GPT-4.1 nano | Phi-3 Medium |
|---|---|---|
| TruthfulQA | — | 59.1 |
coding
| Benchmark | GPT-4.1 nano | Phi-3 Medium |
|---|---|---|
| HumanEval | — | 62.2 |
Category Winners
coding
0.5
math
6.4
reasoning
29.1
general
5.2
language
13.9
multimodal
9.6
safety
22.4
agent