Clasificación de modelos de IA (noviembre de 2026): los mejores LLM por puntuación, precio y velocidad
Qué modelo es mejor depende de lo que necesites. Tres tablas son las clasificaciones de la comunidad de LMArena; las otras dos solo puede medirlas WayJet: puntuación por precio y velocidad con tráfico real. Los modelos que puedes llamar en WayJet tienen un botón al lado. Cómo se hacen las tablas
Chat general
Ordenada por la puntuación de texto de LMArena con control de estilo: la gente compara dos respuestas anónimas y vota la mejor.
Fuente: LMArena (CC BY 4.0), datos a 2026-11-09.
| Puesto | Modelo | Puntuación | En WayJet |
|---|---|---|---|
| 1 | Gemini 4 Carbon (High)google | 1526 | |
| 2 | Gemini 4 Argon (High)google | 1522 | |
| 3 | Muse Wonder (Max)meta | 1511 | |
| 4 | Claude Opus 5.5 (High)anthropic | 1506 | Probar |
| 5 | Claude Fable 5 (High)anthropic | 1504 | Probar |
| 6 | Claude Opus 4.6 (High)anthropic | 1503 | Probar |
| 7 | Claude Fable 5.1 (Max)anthropic | 1503 | Probar |
| 8 | Claude Opus 4.7 (High)anthropic | 1501 | Probar |
| 9 | Gemini 3.8 Flash (High)google | 1498 | Probar |
| 10 | Claude Opus 4.6anthropic | 1497 | Probar |
| 11 | Muse Spark 1.3 (Max)meta | 1496 | |
| 12 | Claude Opus 4.7anthropic | 1494 | Probar |
| 13 | Muse Spark 1.2 (xHigh)meta | 1494 | |
| 14 | Muse Spark 1.1meta | 1491 | |
| 15 | Claude Opus 5 (High)anthropic | 1490 | Probar |
| 16 | Gemini 3.7 Flash (High)google | 1489 | |
| 17 | Muse Sparkmeta | 1489 | |
| 18 | Claude Opus 5 (Max)anthropic | 1489 | Probar |
| 19 | Kimi K3 (Max)moonshot | 1487 | Probar |
| 20 | Gemini 3.1 Pro Previewgoogle | 1487 | |
| 21 | Gemini 3 Progoogle | 1486 | |
| 22 | GPT-5.6 Sol (xHigh)openai | 1485 | Probar |
| 23 | Qwen3.8-Maxalibaba | 1484 | Probar |
| 24 | Kimi K3.1 Pro (Max)moonshot | 1483 | Probar |
| 25 | Gemini 3.6 Flash (High)google | 1483 | Probar |
| 26 | GLM-5.3 (Max)zai | 1483 | |
| 27 | GPT-6.1 Sol (Max)openai | 1482 | Probar |
| 28 | Claude Opus 4.8 (High)anthropic | 1482 | Probar |
| 29 | GPT-5.5 (High)openai | 1481 | |
| 30 | MiMo-V2.6-Proxiaomi | 1480 | |
| 31 | Gemini 3.5 Flash (High)google | 1478 | |
| 32 | Gemini 3.5 Flash (Medium)google | 1476 | |
| 33 | GPT-5.5openai | 1476 | |
| 34 | GPT-5.2 Chat (20260210)openai | 1476 | Probar |
| 35 | GPT-5.4 (High)openai | 1475 | Probar |
| 36 | GLM-5.2 (Max)zai | 1475 | |
| 37 | DeepSeek-V4.1-Flash-20260910 (Max)deepseek | 1475 | |
| 38 | Grok 4.20 Beta 1xai | 1475 | |
| 39 | Claude Opus 4.8anthropic | 1474 | Probar |
| 40 | GLM-5.3-Flashzai | 1474 | |
| 41 | GPT-6 Astra (Max)openai | 1474 | Probar |
| 42 | Qwen3.7-Max-Previewalibaba | 1474 | |
| 43 | Claude Opus 4.5 (High, 32K, 20251101)anthropic | 1474 | |
| 44 | GPT-5.5 Instantopenai | 1473 | |
| 45 | Gemini 3 Flashgoogle | 1473 | |
| 46 | Claude Sonnet 5.5 (xHigh)anthropic | 1473 | Probar |
| 47 | Grok 4.20 Beta (Reasoning, 0309)xai | 1472 | |
| 48 | Claude Sonnet 4.6anthropic | 1472 | Probar |
| 49 | Grok 4.20 Multi-Agent Beta (0309)xai | 1471 | |
| 50 | Claude Opus 4.5 (20251101)anthropic | 1470 | Probar |
Programación
Ordenada por la puntuación WebDev de LMArena: los modelos crean una app web que funciona a partir de un prompt y la gente vota el resultado.
Fuente: LMArena (CC BY 4.0), datos a 2026-11-09.
| Puesto | Modelo | Puntuación | En WayJet |
|---|---|---|---|
| 1 | Claude Opus 5.5 (Max)anthropic | 1818 | Probar |
| 2 | Claude Sonnet 5.5 (xHigh)anthropic | 1774 | Probar |
| 3 | Gemini 4 Carbon (High)google | 1768 | |
| 4 | GPT-6 Astra (Max)openai | 1767 | Probar |
| 5 | Claude Fable 5.1 (Max)anthropic | 1745 | Probar |
| 6 | GPT-6.1 Sol (Max)openai | 1743 | Probar |
| 7 | Muse Wonder Full (Max)meta | 1724 | |
| 8 | Claude Sonnet 5.5 (High)anthropic | 1713 | Probar |
| 9 | Claude Opus 5 (Max)anthropic | 1691 | Probar |
| 10 | Kimi K3.1 Pro (Max)moonshot | 1688 | Probar |
| 11 | Gemini 4 Argon (High)google | 1683 | |
| 12 | GPT-6.1 Terra (Max)openai | 1679 | Probar |
| 13 | Qwen3.8-Max (0902)alibaba | 1677 | Probar |
| 14 | GPT-6 Sol (Max)openai | 1674 | Probar |
| 15 | Qwen3.8-Maxalibaba | 1670 | Probar |
| 16 | DeepSeek-V4.1-Flash-20261017 (Max)deepseek | 1664 | |
| 17 | Kimi K3 (Max)moonshot | 1657 | Probar |
| 18 | Claude Opus 5 (High)anthropic | 1657 | Probar |
| 19 | Muse Spark 1.3 (Max)meta | 1654 | |
| 20 | Muse Wonder (Max)meta | 1650 | |
| 21 | Inkling 2 Smallthinky | 1650 | |
| 22 | Grok 4.7 (xHigh)xai | 1639 | |
| 23 | MiMo-V2.6-Flashxiaomi | 1637 | |
| 24 | Hy4 previewtencent | 1632 | |
| 25 | Claude Fable 5 (High)anthropic | 1625 | Probar |
| 26 | Qwen3.8-Flash-Nextalibaba | 1625 | |
| 27 | MiMo-V2.6-Proxiaomi | 1624 | |
| 28 | GLM-5.3 (Max)zai | 1622 | |
| 29 | DeepSeek-V4.1-Flash-20260910 (Max)deepseek | 1621 | |
| 30 | Muse Spark 1.3 (xHigh)meta | 1621 | |
| 31 | Grok 4.6 (High)xai | 1618 | |
| 32 | GPT-5.6 Sol (xHigh, Codex Harness)openai | 1615 | Probar |
| 33 | GLM-5.3-Flashzai | 1609 | |
| 34 | Muse Ember (Max)meta | 1608 | |
| 35 | GLM-5.2 (Max)zai | 1608 | |
| 36 | Claude Haiku 5.5 (High)anthropic | 1595 | Probar |
| 37 | Qwen3.8-27Balibaba | 1591 | Probar |
| 38 | Gemini 3.7 Flash (High)google | 1588 | |
| 39 | Gemini 3.8 Flash (High)google | 1584 | Probar |
| 40 | DeepSeek-V4-Flash (High)deepseek | 1582 | Probar |
| 41 | MiniMax-M3.1-Flashminimax | 1582 | Probar |
| 42 | DeepSeek-V4-Pro (High, 20260813)deepseek | 1581 | Probar |
| 43 | GPT-6 Luna (Max)openai | 1578 | Probar |
| 44 | Step 5 Preview (High)stepfun | 1573 | |
| 45 | Mistral Large 4mistral | 1562 | |
| 46 | Claude Opus 4.7 (High)anthropic | 1557 | Probar |
| 47 | Claude Opus 4.8 (High)anthropic | 1555 | Probar |
| 48 | Claude Opus 4.7anthropic | 1555 | Probar |
| 49 | Grok 4.5xai | 1552 | |
| 50 | Claude Opus 4.6 (High)anthropic | 1546 | Probar |
Visión y multimodal
Ordenada por la puntuación de visión de LMArena con control de estilo: preguntas que llegan con una imagen.
Fuente: LMArena (CC BY 4.0), datos a 2026-11-09.
| Puesto | Modelo | Puntuación | En WayJet |
|---|---|---|---|
| 1 | Claude Fable 5 (High)anthropic | 1309 | Probar |
| 2 | Claude Opus 4.7anthropic | 1300 | Probar |
| 3 | Qwen3.8-Maxalibaba | 1299 | Probar |
| 4 | Claude Opus 4.6 (High)anthropic | 1299 | Probar |
| 5 | Claude Opus 4.7 (High)anthropic | 1298 | Probar |
| 6 | Claude Opus 5.5 (High)anthropic | 1295 | Probar |
| 7 | Muse Sparkmeta | 1294 | |
| 8 | Gemini 3.7 Flash (High)google | 1294 | |
| 9 | Muse Spark 1.2 (xHigh)meta | 1294 | |
| 10 | Claude Opus 4.6anthropic | 1293 | Probar |
| 11 | Gemini 3.8 Flash (High)google | 1293 | Probar |
| 12 | GPT-6.1 Sol (Max)openai | 1293 | Probar |
| 13 | Muse Spark 1.3 (Max)meta | 1292 | |
| 14 | Gemini 3 Progoogle | 1289 | |
| 15 | Claude Fable 5.1 (Max)anthropic | 1289 | Probar |
| 16 | GPT-5.6 Sol (xHigh)openai | 1288 | Probar |
| 17 | Muse Spark 1.3 (xHigh)meta | 1288 | |
| 18 | Claude Opus 4.8 (High)anthropic | 1286 | Probar |
| 19 | Claude Opus 5 (High)anthropic | 1285 | Probar |
| 20 | GPT-5.5openai | 1285 | |
| 21 | GPT-6 Astra (Max)openai | 1283 | Probar |
| 22 | GPT-5.5 (High)openai | 1283 | |
| 23 | GPT-5.4 (High)openai | 1282 | Probar |
| 24 | Gemini 3.5 Flash (Medium)google | 1282 | |
| 25 | Gemini 3.5 Flash (High)google | 1281 | |
| 26 | Grok 4.5xai | 1280 | |
| 27 | Gemini 3.1 Pro Previewgoogle | 1280 | |
| 28 | Gemini 3.6 Flash (High)google | 1280 | Probar |
| 29 | Muse Spark 1.1meta | 1279 | |
| 30 | Claude Opus 4.8anthropic | 1279 | Probar |
| 31 | GPT-5.4openai | 1278 | Probar |
| 32 | GPT-5.2 Chat (20260210)openai | 1278 | Probar |
| 33 | GPT-5.5 Instantopenai | 1277 | |
| 34 | Claude Sonnet 4.6anthropic | 1275 | Probar |
| 35 | Gemini 3 Flashgoogle | 1272 | |
| 36 | GLM-5.3-Flashzai | 1272 | |
| 37 | GPT-5.6 Terra (xHigh)openai | 1266 | Probar |
| 38 | Gemini 3.5 Flash-Litegoogle | 1266 | |
| 39 | Gemma 4 31Bgoogle | 1265 | |
| 40 | Kimi K2.6moonshot | 1265 | Probar |
| 41 | Grok 4.6 (High)xai | 1263 | |
| 42 | DeepSeek-V4.1-Flash-20260910 (Max)deepseek | 1263 | |
| 43 | Claude Sonnet 5.5 (xHigh)anthropic | 1263 | Probar |
| 44 | Qwen3.7-Plusalibaba | 1262 | Probar |
| 45 | Claude Sonnet 5 (High)anthropic | 1261 | Probar |
| 46 | Gemini 3 Flash (Minimal)google | 1260 | |
| 47 | GPT-6 Sol (Max)openai | 1258 | Probar |
| 48 | Dola Seed 2.0 Probytedance | 1256 | |
| 49 | Grok 4.20 Beta (Reasoning, 0309)xai | 1256 | |
| 50 | GPT-5.6 Luna (xHigh)openai | 1255 | Probar |
Puntuación por precio
La puntuación general dividida entre lo que cuesta el modelo en WayJet por millón de tokens, entrada y salida ponderadas 3:1. Solo modelos que puedes llamar en WayJet.
Fuente: LMArena (CC BY 4.0), datos a 2026-11-09; precios: WayJet, el día en que se generó esta página.
| Puesto | Modelo | Precio / 1M de tokens | Puntos por $ | En WayJet |
|---|---|---|---|---|
| 1 | google.gemma-3-4b-itgoogle | $0.05 | 26,065 | Probar |
| 2 | gpt-5-nanoopenai | $0.14 | 9,728 | Probar |
| 3 | google.gemma-3-12b-itgoogle | $0.14 | 9,584 | Probar |
| 4 | qwen3-30b-a3b-instruct-2507alibaba | $0.15 | 9,277 | Probar |
| 5 | zai.glm-4.7-flashzai | $0.15 | 8,947 | Probar |
| 6 | qwen3.5-flashalibaba | $0.17 | 7,977 | Probar |
| 7 | gpt-4.1-nanoopenai | $0.17 | 7,556 | Probar |
| 8 | gpt-6-lunaopenai | $0.20 | 7,204 | Probar |
| 9 | claude-haiku-5-5anthropic | $0.20 | 7,112 | Probar |
| 10 | deepseek-v4-flashdeepseek | $0.26 | 5,470 | Probar |
| 11 | google.gemma-3-27b-itgoogle | $0.27 | 5,104 | Probar |
| 12 | gpt-4o-miniopenai | $0.26 | 5,020 | Probar |
| 13 | qwen.qwen3-next-80b-a3balibaba | $0.41 | 3,391 | Probar |
| 14 | gpt-5.6-lunaopenai | $0.45 | 3,229 | Probar |
| 15 | qwen3-235b-a22b-instruct-2507alibaba | $0.50 | 2,826 | Probar |
| 16 | MiniMax-M3minimax | $0.53 | 2,735 | Probar |
| 17 | MiniMax-M2.7minimax | $0.53 | 2,695 | Probar |
| 18 | MiniMax-M2.5minimax | $0.53 | 2,649 | Probar |
| 19 | MiniMax-M2minimax | $0.53 | 2,559 | Probar |
| 20 | qwen3.7-plusalibaba | $0.70 | 2,079 | Probar |
| 21 | qwen3.5-35b-a3balibaba | $0.69 | 2,028 | Probar |
| 22 | gpt-5-miniopenai | $0.69 | 2,022 | Probar |
| 23 | gpt-4.1-miniopenai | $0.70 | 1,976 | Probar |
| 24 | qwen3.8-27balibaba | $0.78 | 1,850 | Probar |
| 25 | qwen3.5-27balibaba | $0.82 | 1,707 | Probar |
| 26 | gemini-2.5-flashgoogle | $0.85 | 1,658 | Probar |
| 27 | gpt-3.5-turboopenai | $0.75 | 1,634 | Probar |
| 28 | deepseek.v3.2deepseek | $0.93 | 1,536 | Probar |
| 29 | deepseek-v4-prodeepseek | $0.99 | 1,479 | Probar |
| 30 | zai.glm-4.7zai | $1.00 | 1,441 | Probar |
| 31 | qwen.qwen3-vl-235b-a22balibaba | $1.06 | 1,330 | Probar |
| 32 | qwen3.5-122b-a10balibaba | $1.10 | 1,288 | Probar |
| 33 | qwen3.6-plusalibaba | $1.13 | 1,283 | Probar |
| 34 | moonshotai.kimi-k2.5moonshot | $1.20 | 1,208 | Probar |
| 35 | qwen3.5-397b-a17balibaba | $1.35 | 1,068 | Probar |
| 36 | gemini-3.8-flashgoogle | $1.50 | 998 | Probar |
| 37 | gemini-3.6-flashgoogle | $1.50 | 988 | Probar |
| 38 | zai.glm-5zai | $1.55 | 940 | Probar |
| 39 | kimi-k2.6moonshot | $1.71 | 853 | Probar |
| 40 | qwen3-next-80b-a3b-thinkingalibaba | $1.88 | 730 | Probar |
| 41 | claude-haiku-4-5-20251001anthropic | $2.00 | 707 | Probar |
| 42 | qwen3-maxalibaba | $2.40 | 593 | Probar |
| 43 | qwen3.6-max-previewalibaba | $2.92 | 499 | Probar |
| 44 | qwen3.8-maxalibaba | $3.00 | 495 | Probar |
| 45 | qwen-maxalibaba | $2.80 | 471 | Probar |
| 46 | qwen3-coder-480b-a35b-instructalibaba | $3.00 | 463 | Probar |
| 47 | gpt-5.1openai | $3.44 | 423 | Probar |
| 48 | gpt-5openai | $3.44 | 417 | Probar |
| 49 | gpt-4.1openai | $3.50 | 404 | Probar |
| 50 | kimi-k3.1-promoonshot | $4.00 | 371 | Probar |
Velocidad en WayJet
Mediana de la velocidad de salida y del tiempo hasta el primer token en los últimos siete días de peticiones reales a través del gateway de WayJet.
Fuente: gateway de WayJet, medianas de 7 días, datos a 2026-11-11. Solo agregados; ningún dato de clientes. Método
| Puesto | Modelo | Velocidad de salida | Tiempo hasta el primer token | En WayJet |
|---|---|---|---|---|
| 1 | claude-sonnet-5-5 | 85.9 tok/s | — | Probar |

