Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
general
| Benchmark | GPT-4o | Ministral 3 (14B Reasoning 2512) |
|---|---|---|
| MMLU-Pro | 74.5 | — |
| IFEval | 83.6 | — |
| Chatbot Arena Elo | 1285 | — |
reasoning
| Benchmark | GPT-4o | Ministral 3 (14B Reasoning 2512) |
|---|---|---|
| GPQA Diamond | 53.6 | 71.2 |
| BigBench-Hard | 87.3 | — |
| ARC-Challenge | 96.4 | — |
coding
| Benchmark | GPT-4o | Ministral 3 (14B Reasoning 2512) |
|---|---|---|
| HumanEval | 90.2 | — |
| SWE-bench Verified | 33.2 | — |
language
| Benchmark | GPT-4o | Ministral 3 (14B Reasoning 2512) |
|---|---|---|
| WinoGrande | 85.7 | — |
| HellaSwag | 96.4 | — |
multimodal
| Benchmark | GPT-4o | Ministral 3 (14B Reasoning 2512) |
|---|---|---|
| MMMU | 69.1 | — |
safety
| Benchmark | GPT-4o | Ministral 3 (14B Reasoning 2512) |
|---|---|---|
| TruthfulQA | 73.5 | — |
Category Winners
coding
38.2
math
61.1
reasoning
57.1
general
70.5
language
79.9
multimodal
54.0
safety
94.3