Comparar modelos
A metric-by-metric comparison using the latest available benchmark, runtime, and pricing values. Tie wins more comparable metrics.
| Metric | GPT-5.6 Sol (max) | Grok 4.5 (high) |
|---|---|---|
| Artificial Analysis Intelligence Index | 58,9 | 53,8 |
| Artificial Analysis Coding Index | 77,4 | 72,4 |
| LiveBench Mathematics | 96,2% | 90,8% |
| GPQA | 94,1% | 93,1% |
| Humanity's Last Exam | 47,2% | 40,3% |
| SciCode | 56,1% | 54,1% |
| Output Speed | 67,4 tok/s | 122,8 tok/s |
| Time to First Token | 92,43 s | 11,63 s |
| Blended Price | 11,25 US$ / 1M | 3,00 US$ / 1M |
| Input Price | 5,00 US$ / 1M | 2,00 US$ / 1M |
| Output Price |
| 30,00 US$ / 1M |
| 6,00 US$ / 1M |
| Value Index | 5,24 | 17,93 |
