| Benchmark | Claude 4 Opus | Muse Spark 1.1 |
|---|---|---|
| AA Intelligence | 31.7 | 53.2 |
| AA-LCR | 40 | 81.3 |
| Artificial Analysis Coding Index | 34 | 71.3 |
| Fortress | 27.6 | 12.4 |
| GPQA Diamond | 79.6 | 89.8 |
| HLE | 12.3 | 62.1 |
| multichallenge | 58.6 | 75.3 |
| MultiNRC | 33.9 | 65.6 |
| scicode | 40.9 | 58.2 |
Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.