Mejor IA para salud
Las clasificaciones combinan varias puntuaciones de benchmarks ponderadas según su relevancia para cada caso de uso. Actualizado agosto 2026.
Respuesta rápida
1. Claude Mythos Preview (Anthropic, Puntuación: 90.6), 2. Gemini 3.1 Pro (Google, Puntuación: 80.4), 3. Claude Fable 5.1 (Anthropic, Puntuación: 77.1).
| # | Modelo | Proveedor | Puntuación | Velocidad | Precio (salida) |
|---|---|---|---|---|---|
| 1 | Claude Mythos Preview | Anthropic | 90.6 | 80 t/s | $15/M |
| 2 | Gemini 3.1 Pro | 80.4 | 136 t/s | $12/M | |
| 3 | Claude Fable 5.1 | Anthropic | 77.1 | 85 t/s | $15/M |
| 4 | Claude Mythos 5 | Anthropic | 73.6 | 50 t/s | $50/M |
| 5 | Claude Opus 5.5 | Anthropic | 72.3 | 68 t/s | $25/M |
| 6 | Claude Fable 5.1 (XHigh) | Anthropic | 70.1 | 78 t/s | $15/M |
| 7 | Claude Fable 5.1 (High) | Anthropic | 70.1 | 92 t/s | $15/M |
| 8 | Claude Fable 5.1 (Medium) | Anthropic | 70.1 | 104 t/s | $15/M |
| 9 | Claude Fable 5.1 (Low) | Anthropic | 70.1 | 118 t/s | $15/M |
| 10 | Claude Opus 5.5 (XHigh) | Anthropic | 69.4 | 62 t/s | $25/M |
| 11 | Claude Opus 5.5 (High) | Anthropic | 69.4 | 74 t/s | $25/M |
| 12 | Claude Opus 5.5 (Medium) | Anthropic | 69.4 | 82 t/s | $25/M |
| 13 | Claude Opus 5.5 (Low) | Anthropic | 69.4 | 92 t/s | $25/M |
| 14 | Claude Sonnet 4.6 (max) | Anthropic | 68.6 | 50 t/s | $15/M |
| 15 | GPT-6 Astra (xhigh) | OpenAI | 68.3 | 76 t/s | $50/M |
Claude Mythos Preview
Gemini 3.1 Pro
GPT-6 Astra (xhigh)