Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Nova 2 Pro | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 81.4 | 90.4 |
| Humanity's Last Exam | — | 28.8 |
math
| Benchmark | Nova 2 Pro | Qwen3.6 Plus |
|---|---|---|
| AIME 2025 | 92.3 | — |
coding
| Benchmark | Nova 2 Pro | Qwen3.6 Plus |
|---|---|---|
| SWE-bench Verified | 70 | 78.8 |
| TerminalBench | 41.3 | — |
| SWE-Bench Pro | — | 56.6 |
multimodal
| Benchmark | Nova 2 Pro | Qwen3.6 Plus |
|---|---|---|
| MMMU-Pro | 63.5 | 78.8 |
| MMMU | — | 86 |
| CharXiv Reasoning | — | 81.5 |
| ScreenSpot Pro | — | 68.2 |
general
| Benchmark | Nova 2 Pro | Qwen3.6 Plus |
|---|---|---|
| MMMLU | — | 89.5 |
agent
| Benchmark | Nova 2 Pro | Qwen3.6 Plus |
|---|---|---|
| Toolathlon | — | 39.8 |
| MCP Atlas | — | 74.1 |
Category Winners
coding
Nova 2 Pro66.8
math
Nova 2 Pro74.0
reasoning
Nova 2 Pro74.2
general
Q
Qwen3.6 Plus74.3
multimodal
Q
Qwen3.6 Plus73.4
agent
Q
Qwen3.6 Plus39.5