Comparar modelos
A metric-by-metric comparison using the latest available benchmark, runtime, and pricing values. Tie wins more comparable metrics.
| Metric | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Muse Spark 1.1 (xhigh) |
|---|---|---|
| Artificial Analysis Intelligence Index | 59,9 | 50,6 |
| Artificial Analysis Coding Index | 76,5 | 71,3 |
| LiveBench Mathematics | 96% | 87,1% |
| GPQA | 92,6% | 89,8% |
| Humanity's Last Exam | 53,3% | 45,1% |
| SciCode | 60,2% | 58,2% |
| Output Speed | 69,4 tok/s | 124,3 tok/s |
| Time to First Token | 83,88 s | 0,83 s |
| Blended Price | US$ 20,00 / 1M | US$ 2,00 / 1M |
| Input Price | US$ 10,00 / 1M | US$ 1,25 / 1M |
| Output Price | US$ 50,00 / 1M | US$ 4,25 / 1M |
| Value Index | 3 | 25,3 |
