Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Gemini 2.5 Pro | Laguna S 2.1 |
|---|---|---|
| GPQA Diamond | 83 | — |
| Humanity's Last Exam | 17.8 | — |
| ARC-AGI v2 | 4.9 | — |
math
| Benchmark | Gemini 2.5 Pro | Laguna S 2.1 |
|---|---|---|
| AIME 2025 | 83 | — |
coding
| Benchmark | Gemini 2.5 Pro | Laguna S 2.1 |
|---|---|---|
| SWE-bench Verified | 63.2 | — |
| SWE-Bench Pro | — | 59.4 |
multimodal
| Benchmark | Gemini 2.5 Pro | Laguna S 2.1 |
|---|---|---|
| MMMU | 79.6 | — |
general
| Benchmark | Gemini 2.5 Pro | Laguna S 2.1 |
|---|---|---|
| SimpleQA | 50.8 | — |
agent
| Benchmark | Gemini 2.5 Pro | Laguna S 2.1 |
|---|---|---|
| Toolathlon | — | 49.7 |
Category Winners
coding
P
Laguna S 2.155.5
math
57.2
reasoning
35.5
general
69.1
multimodal
79.3
agent
P
Laguna S 2.141.9