| Benchmark | Claude 4 Opus | Muse Spark |
|---|---|---|
| AA Intelligence | 31.7 | 44.3 |
| AA-LCR | 40 | 77 |
| ARC-AGI-2 | 8.6 | 42.5 |
| arena_vision | 1207 | 1295 |
| Artificial Analysis Coding Index | 34 | 58.6 |
| Fortress | 27.6 | 20.2 |
| frontiermath_tier_4 | 4.2 | 14.6 |
| GPQA Diamond | 79.6 | 89.5 |
| HLE | 12.3 | 58.4 |
| IFBench | 53.7 | 75.9 |
| multichallenge | 58.6 | 75.5 |
| MultiNRC | 33.9 | 59 |
| scicode | 40.9 | 51.5 |
| SWE-bench Verified | 79.4 | 77.4 |
| Terminal-Bench Hard | 31.1 | 45.5 |
| τ²-Bench Telecom (AA run) | 73.4 | 91.5 |
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.