Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
language
| Benchmark | GPT-4o | MiMo-V2-Flash |
|---|---|---|
| HellaSwag | 96.4 | — |
| WinoGrande | 85.7 | — |
general
| Benchmark | GPT-4o | MiMo-V2-Flash |
|---|---|---|
| IFEval | 83.6 | — |
| MMLU-Pro | 74.5 | — |
| Chatbot Arena Elo | 1285 | — |
safety
| Benchmark | GPT-4o | MiMo-V2-Flash |
|---|---|---|
| TruthfulQA | 73.5 | — |
reasoning
| Benchmark | GPT-4o | MiMo-V2-Flash |
|---|---|---|
| GPQA Diamond | 53.6 | 83.7 |
| ARC-Challenge | 96.4 | — |
| BigBench-Hard | 87.3 | — |
| Humanity's Last Exam | — | 22.1 |
coding
| Benchmark | GPT-4o | MiMo-V2-Flash |
|---|---|---|
| HumanEval | 90.2 | — |
| SWE-bench Verified | 33.2 | 73.4 |
| TerminalBench | — | 30.5 |
multimodal
| Benchmark | GPT-4o | MiMo-V2-Flash |
|---|---|---|
| MMMU | 69.1 | — |
agent
| Benchmark | GPT-4o | MiMo-V2-Flash |
|---|---|---|
| BrowseComp | — | 58.3 |
Category Winners
coding
X
MiMo-V2-Flash51.5
math
X
MiMo-V2-Flash76.2
reasoning
X
MiMo-V2-Flash56.1
general
70.5
language
79.9
multimodal
54.5
safety
94.3
agent
X
MiMo-V2-Flash37.8