Comparar modelos
A metric-by-metric comparison using the latest available benchmark, runtime, and pricing values. Grok 4.5 (high) wins more comparable metrics.
| Metric | Grok 4.5 (high) | Gemini 3.5 Flash (high) |
|---|---|---|
| Artificial Analysis Intelligence Index | 53,8 | 50,2 |
| Artificial Analysis Coding Index | 72,4 | 70,1 |
| LiveBench Mathematics | 90,8% | 88,2% |
| GPQA | 93,1% | 92,2% |
| Humanity's Last Exam | 40,3% | 41% |
| SciCode | 54,1% | 53,1% |
| Output Speed | 122,8 tok/s | 241,2 tok/s |
| Time to First Token | 11,63 s | 10,42 s |
| Blended Price | US$ 3,00 / 1M | US$ 3,38 / 1M |
| Input Price | US$ 2,00 / 1M | US$ 1,50 / 1M |
| Output Price | US$ 6,00 / 1M | US$ 9,00 / 1M |
| Value Index | 17,93 | 14,87 |
