Neura Intelligence Index
| Benchmark | Muse Spark | Qwen3.5-27B |
|---|---|---|
| GPQA Diamond | 89.5 | 85.5 |
| Humanity's Last Exam | 58.4 | 48.5 |
| ARC-AGI v2 | 42.5 | — |
| Benchmark | Muse Spark | Qwen3.5-27B |
|---|---|---|
| SWE-bench Verified | 77.4 | 72.4 |
| SWE-Bench Pro | 52.4 | — |
| Benchmark | Muse Spark | Qwen3.5-27B |
|---|---|---|
| MMMU-Pro | 80.4 | 75 |
| CharXiv Reasoning | 86.4 | 79.5 |
| ScreenSpot Pro | 84.1 | 70.3 |
| MMMU | — | 82.3 |
| Benchmark | Muse Spark | Qwen3.5-27B |
|---|---|---|
| MMMLU | — | 85.9 |
| Benchmark | Muse Spark | Qwen3.5-27B |
|---|---|---|
| BrowseComp | — | 61 |