Neura Intelligence Index
Category Comparison
Benchmark-by-Benchmark
reasoning
| Benchmark | Claude Opus 4.6 | Muse Spark 1.1 |
|---|---|---|
| GPQA Diamond | 91.3 | — |
| Humanity's Last Exam | 53.1 | 62.1 |
| ARC-AGI v2 | 68.8 | — |
math
| Benchmark | Claude Opus 4.6 | Muse Spark 1.1 |
|---|---|---|
| AIME 2025 | 99.8 | — |
coding
| Benchmark | Claude Opus 4.6 | Muse Spark 1.1 |
|---|---|---|
| SWE-bench Verified | 80.8 | — |
| SWE-Bench Pro | — | 61.5 |
multimodal
| Benchmark | Claude Opus 4.6 | Muse Spark 1.1 |
|---|---|---|
| MMMU-Pro | 77.3 | — |
| CharXiv Reasoning | 77.4 | 88.4 |
agent
| Benchmark | Claude Opus 4.6 | Muse Spark 1.1 |
|---|---|---|
| OSWorld | 72.7 | — |
| BrowseComp | 84 | — |
| MCP Atlas | 62.7 | 88.1 |
| Toolathlon | — | 75.6 |
Category Winners
coding
82.4
math
83.8
reasoning
M
Muse Spark 1.196.3
general
84.8
multimodal
M
Muse Spark 1.185.7
agent
M
Muse Spark 1.196.2