Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
math
| Benchmark | Command A+ | Gemini 2.5 Flash |
|---|---|---|
| AIME 2025 | 90 | 72 |
multimodal
| Benchmark | Command A+ | Gemini 2.5 Flash |
|---|---|---|
| MMMU | 75.1 | 79.7 |
| MMMU-Pro | 63 | — |
| CharXiv Reasoning | 52.7 | — |
coding
| Benchmark | Command A+ | Gemini 2.5 Flash |
|---|---|---|
| SciCode | 38 | — |
| SWE-bench Verified | — | 60.4 |
reasoning
| Benchmark | Command A+ | Gemini 2.5 Flash |
|---|---|---|
| GPQA Diamond | — | 82.8 |
| Humanity's Last Exam | — | 11 |
general
| Benchmark | Command A+ | Gemini 2.5 Flash |
|---|---|---|
| SimpleQA | — | 26.9 |
Category Winners
coding
36.9
math
69.9
reasoning
44.5
general
33.3
multimodal
79.5