Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Gemini 2.5 Pro | Mercury 2 |
|---|---|---|
| GPQA Diamond | 83 | 74 |
| Humanity's Last Exam | 17.8 | — |
| ARC-AGI v2 | 4.9 | — |
math
| Benchmark | Gemini 2.5 Pro | Mercury 2 |
|---|---|---|
| AIME 2025 | 83 | 91.1 |
coding
| Benchmark | Gemini 2.5 Pro | Mercury 2 |
|---|---|---|
| SWE-bench Verified | 63.2 | — |
| SciCode | — | 38 |
multimodal
| Benchmark | Gemini 2.5 Pro | Mercury 2 |
|---|---|---|
| MMMU | 79.6 | — |
general
| Benchmark | Gemini 2.5 Pro | Mercury 2 |
|---|---|---|
| SimpleQA | 50.8 | — |
Category Winners
coding
44.6
math
I
Mercury 271.8
reasoning
I
Mercury 262.5
general
69.1
multimodal
80.0