Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Gemini 3 Pro | o1-pro |
|---|---|---|
| GPQA Diamond | 91.9 | 79 |
| Humanity's Last Exam | 45.8 | — |
| ARC-AGI v2 | 31.1 | — |
math
| Benchmark | Gemini 3 Pro | o1-pro |
|---|---|---|
| AIME 2025 | 100 | — |
coding
| Benchmark | Gemini 3 Pro | o1-pro |
|---|---|---|
| SWE-bench Verified | 76.2 | — |
multimodal
| Benchmark | Gemini 3 Pro | o1-pro |
|---|---|---|
| MMMU-Pro | 81 | — |
| CharXiv Reasoning | 81.4 | — |
| ScreenSpot Pro | 72.7 | — |
Category Winners
coding
74.3
math
84.0
reasoning
73.1
general
65.1
multimodal
77.2