Compare Models
A metric-by-metric comparison using the latest available benchmark, runtime, and pricing values. Claude Fable 5 wins more comparable metrics.
| Metric | Claude Fable 5 | Muse Spark 1.3 (max) |
|---|---|---|
| Artificial Analysis Intelligence Index | 59.9 | 48.1 |
| Artificial Analysis Coding Index | 76.5 | 75.8 |
| GPQA | n/a | 93.5% |
| Humanity's Last Exam | n/a | 48.7% |
| SciCode | n/a | 58.8% |
| Output Speed | n/a | 247.5 tok/s |
| Time to First Token | n/a | 26.87 s |
| Blended Price | n/a | $2.00 / 1M |
| Input Price | n/a | $1.25 / 1M |
| Output Price | n/a | $4.25 / 1M |
| Value Index | n/a |
| 24.05 |
