Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
general
| Benchmark | GPT-4o | MiMo-V2.5-Pro |
|---|---|---|
| MMLU-Pro | 74.5 | — |
| IFEval | 83.6 | — |
| Chatbot Arena Elo | 1285 | — |
reasoning
| Benchmark | GPT-4o | MiMo-V2.5-Pro |
|---|---|---|
| GPQA Diamond | 53.6 | 66.7 |
| BigBench-Hard | 87.3 | — |
| ARC-Challenge | 96.4 | — |
| Humanity's Last Exam | — | 34 |
coding
| Benchmark | GPT-4o | MiMo-V2.5-Pro |
|---|---|---|
| HumanEval | 90.2 | — |
| SWE-bench Verified | 33.2 | 78.9 |
| SWE-Bench Pro | — | 57.2 |
language
| Benchmark | GPT-4o | MiMo-V2.5-Pro |
|---|---|---|
| WinoGrande | 85.7 | — |
| HellaSwag | 96.4 | — |
multimodal
| Benchmark | GPT-4o | MiMo-V2.5-Pro |
|---|---|---|
| MMMU | 69.1 | — |
safety
| Benchmark | GPT-4o | MiMo-V2.5-Pro |
|---|---|---|
| TruthfulQA | 73.5 | — |
Category Winners
coding
X
MiMo-V2.5-Pro65.1
math
54.5
reasoning
54.3
general
70.5
language
79.9
multimodal
54.0
safety
94.3