Comparar modelos
A metric-by-metric comparison using the latest available benchmark, runtime, and pricing values. GPT-5.6 Sol (max) wins more comparable metrics.
| Metric | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | GPT-5.6 Sol (max) |
|---|---|---|
| Artificial Analysis Intelligence Index | 59,9 | 58,9 |
| Artificial Analysis Coding Index | 76,5 | 77,4 |
| LiveBench Mathematics | 96% | 96,2% |
| GPQA | 92,6% | 94,1% |
| Humanity's Last Exam | 53,3% | 47,2% |
| SciCode | 60,2% | 56,1% |
| Output Speed | 69,4 tok/s | 67,4 tok/s |
| Time to First Token | 83,88 s | 92,43 s |
| Blended Price | 20,00 US$ / 1M | 11,25 US$ / 1M |
| Input Price | 10,00 US$ / 1M | 5,00 US$ / 1M |
| Output Price | 50,00 US$ / 1M | 30,00 US$ / 1M |
| Value Index | 3 | 5,24 |
