Neura Intelligence Index
| Benchmark | Muse Spark | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 89.5 | 90.4 |
| Humanity's Last Exam | 58.4 | 28.8 |
| ARC-AGI v2 | 42.5 | — |
| Benchmark | Muse Spark | Qwen3.6 Plus |
|---|---|---|
| SWE-bench Verified | 77.4 | 78.8 |
| SWE-Bench Pro | 52.4 | 56.6 |
| Benchmark | Muse Spark | Qwen3.6 Plus |
|---|---|---|
| MMMU-Pro | 80.4 | 78.8 |
| CharXiv Reasoning | 86.4 | 81.5 |
| ScreenSpot Pro | 84.1 | 68.2 |
| MMMU | — | 86 |
| Benchmark | Muse Spark | Qwen3.6 Plus |
|---|---|---|
| MMMLU | — | 89.5 |
| Benchmark | Muse Spark | Qwen3.6 Plus |
|---|---|---|
| Toolathlon | — | 39.8 |
| MCP Atlas | — | 74.1 |