Modelos de IA más rápidos: velocidad de salida
Modelos ordenados por tokens de salida por segundo. La velocidad de salida difiere del tiempo hasta la primera respuesta y del tiempo total, sobre todo en modelos de razonamiento. Se excluyen las mediciones ausentes.
¿Cuál deberías elegir?
Ningún benchmark cubre todos los usos. Prueba tus propias consultas y compara precisión, tiempo de respuesta, entradas y salidas admitidas y la factura real.
Modelos de IA
| Modelo | Puntuación de inteligencia | Costo del benchmark (USD) | Precio de entrada / 1 millón de tokens (USD) | Precio de salida / 1 millón de tokens (USD) | Velocidad de salida |
|---|---|---|---|---|---|
| Celeris-1Celeris | 6.30 | $60.0 | 0.20 | 0.70 | 1592 tok/s |
| Mercury 2.5Inception | 12.30 | $218 | 0.25 | 0.75 | 735 tok/s |
| Nemotron 3.5 Super VLNVIDIA | 26.50 | $286 | 0.23 | 0.57 | 444 tok/s |
| Mercury 2Inception | 10.80 | $105 | 0.25 | 0.75 | 443 tok/s |
| Gemini 3.5 Flash-LiteGoogle | 22.20 | $366 | 0.30 | 2.50 | 383 tok/s |
| Gemini 3.1 Flash-LiteGoogle | 15.60 | $156 | 0.25 | 1.50 | 365 tok/s |
| Gemini 2.5 Flash-Lite (Reasoning)Google | 8.50 | - | 0.10 | 0.40 | 355 tok/s |
| Trinity Large ThinkingArcee AI | 10.80 | $233 | 0.25 | 0.80 | 355 tok/s |
| Beam 1.0Reflection | 30.30 | $319 | 0.40 | 1.20 | 340 tok/s |
| Ling 3.0 FlashInclusionAI | 20.10 | - | 0.07 | 0.22 | 320 tok/s |
| Nemotron 3.5 LightningNVIDIA | 12.90 | $92.8 | 0.06 | 0.20 | 291 tok/s |
| DeepSeek V4.1 Flash (Non-reasoning)DeepSeek | 24.70 | $239 | 0.30 | 1.20 | 290 tok/s |
| Muse Spark 1.3 (Xhigh)Meta | 45.10 | $1655 | 1.25 | 4.25 | 290 tok/s |
| Nova MicroAmazon | 5.90 | - | 0.04 | 0.14 | 287 tok/s |
| Gemini 2.5 Flash-Lite (Non-reasoning)Google | 6.70 | - | 0.10 | 0.40 | 286 tok/s |
| Muse Spark 1.1 (Xhigh)Meta | 33.70 | $1737 | 1.25 | 4.25 | 282 tok/s |
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA | 6.80 | - | 0.05 | 0.20 | 275 tok/s |
| Muse Spark 1.2 (Xhigh)Meta | 39.60 | $1385 | 1.25 | 4.25 | 272 tok/s |
| gpt-oss-120b (Low)OpenAI | 10.20 | - | 0.13 | 0.59 | 264 tok/s |
| Qwen3 Coder 30B A3B InstructAlibaba | 9.60 | - | 0.19 | 0.77 | 255 tok/s |
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA | 8.90 | $63.7 | 0.05 | 0.20 | 235 tok/s |
| Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA | 10.30 | - | 0.40 | 1.36 | 234 tok/s |
| Claude Haiku 5.5 (Max)Anthropic | 43.40 | $330 | 0.10 | 0.50 | 234 tok/s |
| o3-mini (High)OpenAI | 11.00 | - | 1.10 | 4.40 | 230 tok/s |
| Step 5 PreviewStepFun | 43.70 | $1190 | 1.00 | 2.70 | 229 tok/s |
| Qwen3.5 Omni FlashAlibaba | 12.50 | - | 0.10 | 0.80 | 227 tok/s |
| GPT-4.1 nanoOpenAI | 7.80 | - | 0.10 | 0.40 | 226 tok/s |
| Inkling SmallThinking Machines | 25.70 | $241 | 0.30 | 1.20 | 226 tok/s |
| GPT-5.4 mini (Xhigh)OpenAI | 24.10 | $1524 | 0.75 | 4.50 | 221 tok/s |
| gpt-oss-120b (High)OpenAI | 11.60 | $123 | 0.15 | 0.60 | 216 tok/s |
| Ling 3.1 FlashInclusionAI | 41.10 | $1015 | 0.30 | 0.90 | 213 tok/s |
| Gemini 3 Flash Preview (Reasoning)Google | 26.30 | - | 0.50 | 3.00 | 211 tok/s |
| Gemini 2.5 Flash (Reasoning)Google | 13.10 | - | 0.30 | 2.50 | 210 tok/s |
| Ministral 3 3BMistral | 4.80 | $12.2 | 0.10 | 0.10 | 208 tok/s |
| Gemini 3 Flash Preview (Non-reasoning)Google | 17.90 | - | 0.50 | 3.00 | 207 tok/s |
| NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA | 5.80 | - | 0.20 | 0.60 | 203 tok/s |
| Gemini 3.5 Flash (High)Google | 32.60 | $4222 | 1.50 | 9.00 | 203 tok/s |
| GPT-5.4 mini (Medium)OpenAI | 19.70 | - | 0.75 | 4.50 | 201 tok/s |
| Qwen3.7 MaxAlibaba | 29.50 | $2277 | 2.50 | 7.50 | 201 tok/s |
| Gemini 2.5 Flash (Non-reasoning)Google | 9.90 | - | 0.30 | 2.50 | 201 tok/s |
| Qwen3 30B A3B 2507 InstructAlibaba | 7.50 | - | 0.10 | 0.30 | 200 tok/s |
| Gemini 3.5 Flash (Medium)Google | 33.60 | - | 1.50 | 9.00 | 199 tok/s |
| Inkling (Xhigh)Thinking Machines | 25.00 | - | 1.00 | 4.05 | 198 tok/s |
| Gemini 3.6 Flash (High)Google | 34.00 | $1614 | 0.75 | 3.75 | 195 tok/s |
| Gemini 3.5 Flash (Minimal)Google | 23.80 | - | 1.50 | 9.00 | 193 tok/s |
| Sarvam 105B (High)Sarvam | 8.80 | - | 0.04 | 0.17 | 192 tok/s |
| o3-miniOpenAI | 12.50 | - | 1.10 | 4.40 | 187 tok/s |
| DeepSeek V4.1 Flash 1017 (Max)DeepSeek | 45.10 | $445 | 0.30 | 1.20 | 186 tok/s |
| Claude Haiku 5.5 (Xhigh)AnthropicFrontera de mejor relación calidad-precio | 41.20 | $158 | 0.10 | 0.50 | 185 tok/s |
| Mistral Small 4 (Reasoning)Mistral | 11.30 | $42.5 | 0.15 | 0.60 | 183 tok/s |
| GPT-4o (Nov '24)OpenAI | 8.40 | - | 2.50 | 10.00 | 183 tok/s |
| Nova 2.0 Lite (Non-reasoning)Amazon | 8.70 | - | 0.30 | 2.50 | 182 tok/s |
| GLM-5.2 (Non-reasoning)Z AI | 22.40 | - | 1.40 | 4.40 | 181 tok/s |
| DeepSeek V4 Flash Vision (Max)DeepSeek | 34.80 | $1081 | 0.44 | 1.32 | 181 tok/s |
| gpt-oss-20b (Low)OpenAI | 10.00 | - | 0.07 | 0.30 | 181 tok/s |
| Nova 2.0 Lite (Medium)Amazon | 12.50 | - | 0.30 | 2.50 | 180 tok/s |
| DeepSeek V4.1 Flash (Max)DeepSeek | 39.50 | $672 | 0.29 | 1.20 | 179 tok/s |
| Claude Haiku 5.5 (Medium)AnthropicFrontera de mejor relación calidad-precio | 34.50 | $56.4 | 0.10 | 0.50 | 179 tok/s |
| Claude Haiku 5.5 (High)AnthropicFrontera de mejor relación calidad-precio | 37.80 | $94.1 | 0.10 | 0.50 | 179 tok/s |
| Nova 2.0 Lite (High)Amazon | 13.40 | - | 0.30 | 2.50 | 179 tok/s |
| Nova 2.0 Lite (Low)Amazon | 11.80 | - | 0.30 | 2.50 | 178 tok/s |
| GPT-5 Codex (High)OpenAI | 24.90 | - | 1.25 | 10.00 | 176 tok/s |
| Mistral Small 4 (Non-reasoning)Mistral | 9.00 | - | 0.15 | 0.60 | 174 tok/s |
| GPT-5.4 nano (Non-reasoning)OpenAI | 11.70 | - | 0.20 | 1.25 | 172 tok/s |
| GPT-5.1 Codex mini (High)OpenAI | 20.40 | - | 0.25 | 2.00 | 171 tok/s |
| Nova LiteAmazon | 6.70 | - | 0.06 | 0.24 | 171 tok/s |
| Quasar 438B (Max, Based on GLM-5.2)Multiverse Computing | 26.70 | - | 0.11 | 0.33 | 170 tok/s |
| Nemotron 3 Super 120B A12B (Reasoning)NVIDIA | 12.80 | $1319 | 0.30 | 0.90 | 169 tok/s |
| GPT-4.1OpenAI | 12.70 | - | 2.00 | 8.00 | 168 tok/s |
| GPT-5.4 nano (Xhigh)OpenAI | 20.70 | $331 | 0.20 | 1.25 | 168 tok/s |
| GPT-5.4 nano (Medium)OpenAI | 20.00 | - | 0.20 | 1.25 | 168 tok/s |
| NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA | 6.80 | - | 0.05 | 0.20 | 167 tok/s |
| Qwen3.5 35B A3B (Non-reasoning)Alibaba | 15.10 | - | 0.25 | 2.00 | 167 tok/s |
| GPT-5.4 mini (Non-reasoning)OpenAI | 11.10 | - | 0.75 | 4.50 | 166 tok/s |
| Claude Haiku 5.5 (Low)Anthropic | 29.50 | $34.3 | 0.10 | 0.50 | 165 tok/s |
| Qwen3 30B A3B (Reasoning)Alibaba | 7.60 | - | 0.14 | 0.55 | 163 tok/s |
| Mistral Medium 3.5Mistral | 14.20 | $1264 | 1.50 | 7.50 | 159 tok/s |
| Qwen3 30B A3B (Non-reasoning)Alibaba | 6.60 | - | 0.12 | 0.50 | 159 tok/s |
| GPT-4.1 miniOpenAI | 10.20 | - | 0.40 | 1.60 | 159 tok/s |
| Step 3.7 FlashStepFun | 19.50 | - | 0.20 | 1.15 | 157 tok/s |
| Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA | 22.90 | $697 | 0.60 | 2.70 | 156 tok/s |
| gpt-oss-20b (High)OpenAI | 9.00 | $28.8 | 0.05 | 0.22 | 156 tok/s |
| Muse Wonder (Max)Meta | 52.40 | $5787 | 4.00 | 20.00 | 154 tok/s |
| GPT-5.5 Instant (June 2026)OpenAI | 26.00 | $1184 | 5.00 | 30.00 | 152 tok/s |
| Muse Spark Open (Xhigh)Meta | 38.90 | $1185 | 1.25 | 4.25 | 151 tok/s |
| DeepSeek V4 Flash 0731 (Max)DeepSeek | 34.30 | $200 | 0.14 | 0.28 | 150 tok/s |
| DeepSeek R1 (Jan '25)DeepSeek | 11.40 | $461 | 2.00 | 4.00 | 149 tok/s |
| o4-mini (High)OpenAI | 16.70 | - | 1.10 | 4.40 | 149 tok/s |
| Qwen3.6 35B A3B (Non-reasoning)Alibaba | 15.20 | - | 0.38 | 2.25 | 147 tok/s |
| Qwen3.5 35B A3B (Reasoning)Alibaba | 19.30 | - | 0.25 | 2.00 | 145 tok/s |
| Step 3.5 FlashStepFun | 16.60 | - | 0.10 | 0.30 | 144 tok/s |
| GPT-5 nano (Medium)OpenAI | 12.50 | - | 0.05 | 0.40 | 143 tok/s |
| Qwen3.5 122B A10B (Non-reasoning)Alibaba | 17.70 | - | 0.40 | 3.20 | 143 tok/s |
| Solar Pro 3Upstage | 7.80 | $159 | 0.15 | 0.60 | 142 tok/s |
| Muse Spark 1.3 (Max)Meta | 48.10 | $2000 | 1.25 | 4.25 | 141 tok/s |
| Step 3.5 Flash 2603StepFun | 17.00 | - | 0.10 | 0.30 | 141 tok/s |
| GPT-6 Luna (Max)OpenAIFrontera de mejor relación calidad-precio | 38.10 | $122 | 0.10 | 0.50 | 140 tok/s |
| o3OpenAI | 20.20 | - | 2.00 | 8.00 | 138 tok/s |
| GPT-4o (Aug '24)OpenAI | 7.70 | - | 2.50 | 10.00 | 138 tok/s |
| Gemini 3.8 Flash (High)Google | 40.90 | $1623 | 0.75 | 3.75 | 136 tok/s |
| Llama 3.1 Instruct 8BMeta | 6.90 | - | 0.04 | 0.07 | 135 tok/s |
| Claude Sonnet 5.5 (Max, Default Fallback)Anthropic | 56.00 | $7260 | 2.00 | 10.00 | 133 tok/s |
| Qwen3.6 35B A3B (Reasoning)Alibaba | 18.20 | $896 | 0.38 | 2.25 | 131 tok/s |
| Nova ProAmazon | 7.00 | - | 0.80 | 3.20 | 131 tok/s |
| GPT-4o (May '24)OpenAI | 7.30 | - | 5.00 | 15.00 | 130 tok/s |
| Gemini 3.1 Pro PreviewGoogle | 29.70 | $1935 | 2.00 | 12.00 | 130 tok/s |
| Qwen3.5 122B A10B (Reasoning)Alibaba | 15.60 | $661 | 0.40 | 3.20 | 128 tok/s |
| GPT-6 Luna (Xhigh)OpenAIFrontera de mejor relación calidad-precio | 34.60 | $66.8 | 0.10 | 0.50 | 127 tok/s |
| Apertus 8B InstructSwiss AI Initiative | 4.80 | - | 0.10 | 0.20 | 127 tok/s |
| GPT-5.1 Codex (High)OpenAI | 23.70 | - | 1.25 | 10.00 | 127 tok/s |
| GPT-5.6 Luna (Max)OpenAI | 37.30 | $320 | 0.20 | 1.20 | 126 tok/s |
| GPT-5.6 Terra (Max)OpenAI | 42.10 | $2501 | 2.00 | 12.00 | 126 tok/s |
| GPT-5 nano (High)OpenAI | 13.00 | - | 0.05 | 0.40 | 125 tok/s |
| Nova 2.0 Pro Preview (Medium)Amazon | 14.20 | - | 1.25 | 10.00 | 125 tok/s |
| GPT-5.6 Luna (Medium)OpenAI | 25.00 | $44.3 | 0.20 | 1.20 | 124 tok/s |
| GPT-5 nano (Minimal)OpenAI | 7.10 | - | 0.05 | 0.40 | 124 tok/s |
| GPT-5.6 Luna (Non-reasoning)OpenAI | 15.50 | $23.0 | 0.20 | 1.20 | 124 tok/s |
| GPT-5 mini (Medium)OpenAI | 20.60 | - | 0.25 | 2.00 | 123 tok/s |
| GPT-6 Luna (High)OpenAIFrontera de mejor relación calidad-precio | 32.90 | $47.9 | 0.10 | 0.50 | 121 tok/s |
| GPT-6 Luna (Non-reasoning)OpenAI | 18.50 | $19.2 | 0.10 | 0.50 | 121 tok/s |
| Kimi K2 ThinkingKimi | 22.00 | - | 0.60 | 2.50 | 121 tok/s |
| GPT-5.6 Luna (High)OpenAI | 32.10 | $108 | 0.20 | 1.20 | 121 tok/s |
| Ring-2.6-1TInclusionAI | 16.60 | $576 | 0.30 | 2.50 | 121 tok/s |
| Gemma 4 12B (Non-reasoning)Google | 9.40 | - | 0.10 | 0.30 | 120 tok/s |
| DeepSeek V3.1 (Reasoning)DeepSeek | 13.50 | - | 0.58 | 1.68 | 120 tok/s |
| GPT-5.6 Luna (Xhigh)OpenAI | 34.60 | $179 | 0.20 | 1.20 | 120 tok/s |
| Nova 2.0 Pro Preview (Low)Amazon | 12.80 | - | 1.25 | 10.00 | 118 tok/s |
| GPT-5 mini (High)OpenAI | 16.80 | $189 | 0.25 | 2.00 | 118 tok/s |
| DeepSeek V3 0324DeepSeek | 9.70 | $19.9 | 0.24 | 0.90 | 117 tok/s |
| GPT-5.6 Luna (Low)OpenAI | 21.00 | $27.0 | 0.20 | 1.20 | 117 tok/s |
| Grok 4.20 0309 v2 (Reasoning)SpaceXAI | 25.70 | - | 1.25 | 2.50 | 117 tok/s |
| Llama 4 ScoutMeta | 6.50 | $73.6 | 0.18 | 0.66 | 115 tok/s |
| Gemma 4 12B (Reasoning)Google | 14.20 | - | 0.10 | 0.30 | 115 tok/s |
| GPT-5.6 Terra (Non-reasoning)OpenAI | 20.80 | $256 | 2.00 | 12.00 | 115 tok/s |
| GPT-6 Luna (Low)OpenAIFrontera de mejor relación calidad-precio | 21.50 | $10.6 | 0.10 | 0.50 | 115 tok/s |
| GPT-5.6 Terra (Medium)OpenAI | 30.10 | $447 | 2.00 | 12.00 | 114 tok/s |
| Qwen3.5 Omni PlusAlibaba | 20.40 | - | 0.40 | 4.80 | 114 tok/s |
| GPT-5.6 Terra (Xhigh)OpenAI | 38.00 | $1187 | 2.00 | 12.00 | 114 tok/s |
| GPT-5 mini (Minimal)OpenAI | 9.90 | - | 0.25 | 2.00 | 114 tok/s |
| Nova 2.0 Pro Preview (Non-reasoning)Amazon | 10.00 | - | 1.25 | 10.00 | 114 tok/s |
| GPT-5.1 (High)OpenAI | 24.70 | - | 1.25 | 10.00 | 113 tok/s |
| GPT-5.6 Terra (High)OpenAI | 34.20 | $768 | 2.00 | 12.00 | 113 tok/s |
| Qwen3 Next 80B A3B InstructAlibaba | 9.60 | - | 0.10 | 1.10 | 113 tok/s |
| GPT-5.6 Terra (Low)OpenAI | 27.50 | $350 | 2.00 | 12.00 | 113 tok/s |
| Gemini 2.5 ProGoogle | 16.10 | $823 | 1.25 | 10.00 | 111 tok/s |
| Ministral 3 8BMistral | 5.50 | $27.5 | 0.15 | 0.15 | 111 tok/s |
| Agnes 2.5 Pro BetaSapiens AI | 35.20 | - | 0.10 | 0.30 | 111 tok/s |
| Grok 4.3 (High)SpaceXAI | 24.90 | $363 | 1.25 | 2.50 | 110 tok/s |
| Grok 4.20 0309 v2 (Non-reasoning)SpaceXAI | 14.20 | - | 1.25 | 2.50 | 108 tok/s |
| MiniMax-M3.1-FlashMiniMax | 42.70 | $283 | 0.15 | 0.60 | 105 tok/s |
| Muse Glimmer (High)Meta | 17.50 | $146 | 0.30 | 1.20 | 105 tok/s |
| Claude Sonnet 5.5 (Xhigh, Default Fallback)Anthropic | 51.90 | $2177 | 2.00 | 10.00 | 105 tok/s |
| Claude Sonnet 5.5 (High, Default Fallback)Anthropic | 46.80 | $1027 | 2.00 | 10.00 | 105 tok/s |
| DeepSeek V4 Pro 0424 (Max)DeepSeek | 30.40 | $277 | 0.43 | 0.87 | 104 tok/s |
| DeepSeek V4 Pro 0813 (Max)DeepSeek | 36.00 | $1122 | 1.32 | 3.96 | 103 tok/s |
| Grok 4.3 (Medium)SpaceXAI | 24.80 | - | 1.25 | 2.50 | 103 tok/s |
| Qwen3 Omni 30B A3B (Reasoning)Alibaba | 7.80 | - | 0.25 | 0.97 | 102 tok/s |
| Mistral Large 4 PreviewMistral | 38.40 | $1608 | 1.36 | 4.18 | 102 tok/s |
| Claude Sonnet 5.5 (Low, Default Fallback)Anthropic | 35.90 | $482 | 2.00 | 10.00 | 102 tok/s |
| GPT-6 Sol (Max)OpenAI | 47.60 | $1536 | 2.00 | 10.00 | 102 tok/s |
| GPT-6 Sol (Low)OpenAI | 34.20 | $269 | 2.00 | 10.00 | 101 tok/s |
| DeepSeek V4 Pro 0424 (High)DeepSeek | 30.10 | - | 0.43 | 0.87 | 101 tok/s |
| MiniMax-M2MiniMax | 18.60 | - | 0.30 | 1.20 | 101 tok/s |
| NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA | 7.40 | - | 0.04 | 0.16 | 101 tok/s |
| Claude Sonnet 5.5 (Medium, Default Fallback)Anthropic | 40.80 | $622 | 2.00 | 10.00 | 100 tok/s |
| Gemma 4 26B A4B (Non-reasoning)Google | 13.10 | - | 0.12 | 0.40 | 99 tok/s |
| GLM-4.7-Flash (Non-reasoning)Z AI | 10.60 | - | 0.07 | 0.40 | 99 tok/s |
| MiniMax-M3MiniMax | 29.20 | $538 | 0.30 | 1.20 | 98 tok/s |
| DeepSeek V4 Pro 0813 (Non-reasoning)DeepSeek | 20.40 | $451 | 1.32 | 3.96 | 98 tok/s |
| Solar Mini 4Upstage | 24.10 | $502 | 0.10 | 0.40 | 98 tok/s |
| GPT-6 Sol (High)OpenAI | 42.40 | $605 | 2.00 | 10.00 | 98 tok/s |
| GPT-6 Sol (Non-reasoning)OpenAI | 28.50 | $449 | 2.00 | 10.00 | 97 tok/s |
| DeepSeek V3.1 (Non-reasoning)DeepSeek | 13.70 | - | 0.56 | 1.68 | 97 tok/s |
| GPT-6 Sol (Xhigh)OpenAI | 44.20 | $855 | 2.00 | 10.00 | 97 tok/s |
| GPT-4o miniOpenAI | 6.70 | - | 0.15 | 0.60 | 96 tok/s |
| Qwen3 Omni 30B A3B InstructAlibaba | 6.00 | - | 0.25 | 0.97 | 96 tok/s |
| MiniMax M1 80kMiniMax | 11.70 | - | 0.55 | 2.20 | 96 tok/s |
| Claude Opus 5.5 (Max, Default Fallback)AnthropicFrontera de mejor relación calidad-precio | 57.60 | $8708 | 4.00 | 20.00 | 96 tok/s |
| GPT-5.1 (Non-reasoning)OpenAI | 13.30 | - | 1.25 | 10.00 | 96 tok/s |
| Grok 4.3 (Non-reasoning)SpaceXAI | 14.00 | $250 | 1.25 | 2.50 | 96 tok/s |
| GPT-5.4 (Xhigh)OpenAI | 39.00 | - | 2.50 | 15.00 | 95 tok/s |
| DeepSeek V4 Pro 0424 (Non-reasoning)DeepSeek | 20.80 | - | 0.43 | 0.87 | 94 tok/s |
| GPT-5.3 Codex (Xhigh)OpenAI | 32.50 | - | 1.75 | 14.00 | 93 tok/s |
| Claude 4.5 Haiku (Reasoning)Anthropic | 16.90 | $594 | 1.00 | 5.00 | 93 tok/s |
| GPT-5 (Medium)OpenAI | 22.90 | - | 1.25 | 10.00 | 93 tok/s |
| GLM-5.2 (Max)Z AI | 33.70 | $2097 | 1.40 | 4.40 | 93 tok/s |
| GPT-6 Luna (Medium)OpenAIFrontera de mejor relación calidad-precio | 29.90 | $31.2 | 0.10 | 0.50 | 92 tok/s |
| Qwen3 Coder NextAlibaba | 9.20 | $405 | 0.31 | 1.00 | 91 tok/s |
| Llama 3.3 Instruct 70BMeta | 7.70 | - | 0.66 | 0.71 | 90 tok/s |
| GPT-5 (Minimal)OpenAI | 11.40 | - | 1.25 | 10.00 | 89 tok/s |
| GLM-5.3 (Low)Z AI | 34.30 | $1013 | 1.40 | 4.40 | 89 tok/s |
| Grok 4.7 (Xhigh)SpaceXAI | 46.40 | $4967 | 2.00 | 6.00 | 89 tok/s |
| Grok 3SpaceXAI | 12.10 | - | 3.00 | 15.00 | 88 tok/s |
| Reka Flash 3Reka AI | 5.60 | - | 0.20 | 0.80 | 88 tok/s |
| GPT-5 (High)OpenAI | 23.00 | - | 1.25 | 10.00 | 88 tok/s |
| GLM-5.3 (Max)Z AI | 44.80 | $2503 | 1.40 | 4.40 | 86 tok/s |
| GLM-4.6V (Reasoning)Z AI | 11.20 | - | 0.30 | 0.90 | 86 tok/s |
| GPT-5.5 (Xhigh)OpenAI | 38.40 | $5294 | 5.00 | 30.00 | 86 tok/s |
| Gemma 4 26B A4B (Reasoning)Google | 16.70 | - | 0.10 | 0.34 | 86 tok/s |
| Grok 4.7 (High)SpaceXAI | 46.30 | $3881 | 2.00 | 6.00 | 86 tok/s |
| Grok 4.3 (Low)SpaceXAI | 24.30 | - | 1.25 | 2.50 | 84 tok/s |
| Qwen3 Coder 480B A35B InstructAlibaba | 11.90 | - | 0.38 | 1.40 | 83 tok/s |
| Claude Sonnet 5 (Max)Anthropic | 38.20 | $6998 | 2.00 | 10.00 | 83 tok/s |
| Ministral 3 14BMistral | 6.00 | $37.6 | 0.20 | 0.20 | 83 tok/s |
| GPT-5.6 Sol (Max)OpenAI | 47.00 | $3465 | 4.00 | 20.00 | 83 tok/s |
| Claude 4.5 Haiku (Non-reasoning)Anthropic | 15.40 | - | 1.00 | 5.00 | 82 tok/s |
| GPT-5.2 Codex (Xhigh)OpenAI | 28.50 | - | 1.75 | 14.00 | 82 tok/s |
| Qwen3 235B A22B 2507 (Reasoning)Alibaba | 12.70 | - | 0.23 | 2.30 | 82 tok/s |
| GLM-4.6V (Non-reasoning)Z AI | 8.40 | - | 0.30 | 0.90 | 82 tok/s |
| Kimi K2.5 (Reasoning)Kimi | 23.50 | - | 0.60 | 3.00 | 82 tok/s |
| Mistral Large 3Mistral | 9.30 | $46.4 | 0.50 | 1.50 | 82 tok/s |
| Hy3Tencent | 25.30 | $150 | 0.14 | 0.56 | 82 tok/s |
| Claude Opus 5.5 (Xhigh, Default Fallback)AnthropicFrontera de mejor relación calidad-precio | 56.00 | $4057 | 4.00 | 20.00 | 82 tok/s |
| Qwen3 14B (Non-reasoning)Alibaba | 6.70 | - | 0.12 | 0.24 | 82 tok/s |
| Qwen3.5 27B (Non-reasoning)Alibaba | 19.40 | - | 0.30 | 2.40 | 81 tok/s |
| GPT-5 (Low)OpenAI | 20.80 | - | 1.25 | 10.00 | 81 tok/s |
| GLM-4.7-Flash (Reasoning)Z AI | 14.90 | - | 0.07 | 0.40 | 81 tok/s |
| GPT-5.6 Sol (Xhigh)OpenAI | 44.00 | $2082 | 4.00 | 20.00 | 81 tok/s |
| Qwen3 14B (Reasoning)Alibaba | 6.40 | - | 0.12 | 0.24 | 81 tok/s |
| GPT-5.6 Sol (High)OpenAI | 42.30 | $1487 | 4.00 | 20.00 | 80 tok/s |
| Grok 4.6 (Xhigh)SpaceXAI | 44.20 | $2242 | 2.00 | 6.00 | 80 tok/s |
| Qwen3.5 9B (Non-reasoning)Alibaba | 13.30 | - | 0.17 | 0.25 | 80 tok/s |
| Kimi K2.6 (Reasoning)Kimi | 27.00 | $1528 | 0.95 | 4.00 | 79 tok/s |
| GPT-5.5 (High)OpenAI | 37.00 | $3411 | 5.00 | 30.00 | 79 tok/s |
| GLM-4.5-AirZ AI | 11.10 | - | 0.17 | 0.98 | 79 tok/s |
| Grok 4.6 (High)SpaceXAI | 44.30 | $1963 | 2.00 | 6.00 | 79 tok/s |
| Claude Opus 5.5 (Medium, Default Fallback)Anthropic | 51.20 | $1627 | 4.00 | 20.00 | 79 tok/s |
| GPT-5.6 Sol (Low)OpenAI | 33.50 | $637 | 4.00 | 20.00 | 79 tok/s |
| Grok 4.6 (Low)SpaceXAI | 35.10 | $614 | 2.00 | 6.00 | 79 tok/s |
| GPT-5.5 (Low)OpenAI | 30.70 | - | 5.00 | 30.00 | 78 tok/s |
| Claude Opus 5.5 (High, Default Fallback)AnthropicFrontera de mejor relación calidad-precio | 53.60 | $2172 | 4.00 | 20.00 | 78 tok/s |
| Grok 4.7 (Low)SpaceXAI | 42.20 | $1631 | 2.00 | 6.00 | 77 tok/s |
| Qwen3.5 27B (Reasoning)Alibaba | 22.90 | - | 0.30 | 2.40 | 77 tok/s |
| Grok 4SpaceXAI | 22.50 | - | 3.00 | 15.00 | 77 tok/s |
| GPT-5.5 (Medium)OpenAI | 33.80 | $2095 | 5.00 | 30.00 | 76 tok/s |
| Gemini 4 Argon (High)Google | 52.60 | $2407 | 2.00 | 10.00 | 76 tok/s |
| Kimi K2.6 (Non-reasoning)Kimi | 23.60 | - | 0.95 | 4.00 | 76 tok/s |
| Magistral Small 1.2Mistral | 8.60 | - | 0.50 | 1.50 | 76 tok/s |
| LongCat 2.0LongCat | 19.10 | $545 | 0.75 | 2.95 | 76 tok/s |
| Claude Opus 5.5 (Low, Default Fallback)Anthropic | 42.30 | $860 | 4.00 | 20.00 | 75 tok/s |
| GPT-5.6 Sol (Medium)OpenAI | 39.20 | $997 | 4.00 | 20.00 | 75 tok/s |
| GPT-5.5 (Non-reasoning)OpenAI | 23.20 | - | 5.00 | 30.00 | 74 tok/s |
| DeepSeek V3.1 Terminus (Non-reasoning)DeepSeek | 13.90 | - | 0.27 | 1.00 | 74 tok/s |
| GPT-5.2 (Xhigh)OpenAI | 30.40 | - | 1.75 | 14.00 | 73 tok/s |
| GPT-5.6 Sol (Non-reasoning)OpenAI | 28.30 | - | 4.00 | 20.00 | 72 tok/s |
| Granite 4.2 3BIBM | 9.10 | $14.9 | 0.03 | 0.12 | 72 tok/s |
| GPT-5.4 (Non-reasoning)OpenAI | 18.20 | - | 2.50 | 15.00 | 71 tok/s |
| Grok 4.6 (Medium)SpaceXAI | 42.80 | $1557 | 2.00 | 6.00 | 71 tok/s |
| Granite 4.2 30BIBM | 12.70 | $111 | 0.16 | 0.65 | 71 tok/s |
| GPT-5.4 (Low)OpenAI | 27.60 | - | 2.50 | 15.00 | 70 tok/s |
| GLM-5.1 (Reasoning)Z AI | 26.10 | $1487 | 1.28 | 4.07 | 70 tok/s |
| GLM-5.3-FlashZ AI | 41.80 | $306 | 0.15 | 0.50 | 69 tok/s |
| Claude Sonnet 5 (Xhigh)Anthropic | 34.40 | $3255 | 2.00 | 10.00 | 69 tok/s |
| GLM-5 (Reasoning)Z AI | 27.90 | - | 1.00 | 3.20 | 69 tok/s |
| Claude Fable 5.1 (Max, Default Fallback)Anthropic | 53.40 | $13129 | 10.00 | 50.00 | 69 tok/s |
| Claude Sonnet 5 (Medium)Anthropic | 28.10 | $1218 | 2.00 | 10.00 | 68 tok/s |
| GLM-5 (Non-reasoning)Z AI | 21.80 | - | 1.00 | 3.20 | 67 tok/s |
| GLM-5.1 (Non-reasoning)Z AI | 24.20 | - | 1.38 | 4.40 | 67 tok/s |
| GLM-4.5V (Non-reasoning)Z AI | 6.70 | - | 0.60 | 1.80 | 66 tok/s |
| Claude Fable 5 (Max, Opus 4.8 Fallback)Anthropic | 49.60 | $11161 | 10.00 | 50.00 | 66 tok/s |
| GPT-5.2 (Non-reasoning)OpenAI | 17.00 | - | 1.75 | 14.00 | 66 tok/s |
| Claude Sonnet 5 (High)Anthropic | 31.70 | $2086 | 2.00 | 10.00 | 66 tok/s |
| Claude Sonnet 5 (Non-reasoning, High)Anthropic | 23.20 | - | 2.00 | 10.00 | 66 tok/s |
| GPT-6 Astra (Max)OpenAI | 52.70 | $5324 | 10.00 | 50.00 | 65 tok/s |
| Granite 4.2 8BIBM | 11.10 | $53.1 | 0.06 | 0.25 | 65 tok/s |
| Grok Build 0.1 0616SpaceXAI | 27.20 | - | 1.00 | 2.00 | 65 tok/s |
| Claude Sonnet 5 (Low)Anthropic | 24.30 | $653 | 2.00 | 10.00 | 65 tok/s |
| Grok 4.5 (High)SpaceXAI | 38.80 | $1244 | 2.00 | 6.00 | 65 tok/s |
| MiniMax-M2.1MiniMax | 20.90 | - | 0.30 | 1.20 | 64 tok/s |
| GLM-4.5V (Reasoning)Z AI | 7.60 | - | 0.60 | 1.80 | 63 tok/s |
| Kimi K3.1 ProKimiFrontera de mejor relación calidad-precio | 55.10 | $3117 | 2.00 | 10.00 | 63 tok/s |
| Claude Fable 5.1 (Xhigh, Default Fallback)Anthropic | 53.20 | $9063 | 10.00 | 50.00 | 63 tok/s |
| Grok 3 mini Reasoning (High)SpaceXAI | 14.60 | - | 0.30 | 0.50 | 63 tok/s |
| Kimi K2.7 CodeKimi | 25.80 | $993 | 0.95 | 4.00 | 62 tok/s |
| MiMo-V2.5Xiaomi | 21.80 | $61.9 | 0.13 | 0.27 | 62 tok/s |
| Claude Opus 4.8 (Max)Anthropic | 41.80 | $6874 | 5.00 | 25.00 | 62 tok/s |
| MiniMax-M2.5MiniMax | 22.80 | - | 0.30 | 1.20 | 61 tok/s |
| Qwen3.5 9B (Reasoning)Alibaba | 11.20 | $329 | 0.14 | 0.20 | 61 tok/s |
| Qwen3 32B (Non-reasoning)Alibaba | 7.30 | - | 0.15 | 0.60 | 60 tok/s |
| Qwen3.5 397B A17B (Non-reasoning)Alibaba | 21.40 | - | 0.60 | 3.60 | 59 tok/s |
| Qwen3.5 397B A17B (Reasoning)Alibaba | 18.40 | $941 | 0.60 | 3.60 | 59 tok/s |
| Qwen3.7 PlusAlibaba | 25.20 | $428 | 0.40 | 1.60 | 59 tok/s |
| GPT-6.1 Sol (Max)OpenAIFrontera de mejor relación calidad-precio | 51.80 | $1082 | 2.00 | 10.00 | 57 tok/s |
| Claude Fable 5.1 (High, Default Fallback)Anthropic | 51.20 | $5242 | 10.00 | 50.00 | 57 tok/s |
| Qwen3.6 27B (Non-reasoning)Alibaba | 19.80 | - | 0.60 | 3.60 | 57 tok/s |
| Qwen3.6 27B (Reasoning)Alibaba | 21.40 | $1145 | 0.60 | 3.60 | 57 tok/s |
| Claude Fable 5.1 (Low, Default Fallback)Anthropic | 46.80 | $3158 | 10.00 | 50.00 | 57 tok/s |
| GPT-6 Astra (High)OpenAI | 50.90 | $2925 | 10.00 | 50.00 | 57 tok/s |
| Claude Sonnet 4.6 (Max)Anthropic | 30.10 | $4925 | 3.00 | 15.00 | 56 tok/s |
| MiMo-V2.6-FlashXiaomiFrontera de mejor relación calidad-precio | 37.90 | $110 | 0.14 | 0.28 | 56 tok/s |
| Qwen3.6 PlusAlibaba | 27.00 | - | 0.50 | 3.00 | 56 tok/s |
| Claude Fable 5.1 (Medium, Default Fallback)Anthropic | 48.90 | $3983 | 10.00 | 50.00 | 55 tok/s |
| GPT-6 Astra (Xhigh)OpenAI | 52.40 | $3803 | 10.00 | 50.00 | 55 tok/s |
| MiMo-V2.6-ProXiaomiFrontera de mejor relación calidad-precio | 46.30 | $207 | 0.43 | 0.87 | 55 tok/s |
| Kimi K2.5 (Non-reasoning)Kimi | 19.40 | - | 0.60 | 3.00 | 53 tok/s |
| GPT-6 Astra (Low)OpenAI | 45.80 | $1537 | 10.00 | 50.00 | 53 tok/s |
| Gemma 4 31B (Non-reasoning)Google | 13.90 | - | 0.17 | 0.40 | 53 tok/s |
| DeepSeek V4 Flash 0420 (Max)DeepSeek | 24.20 | $149 | 0.11 | 0.23 | 53 tok/s |
| Claude Opus 4.7 (Max)Anthropic | 40.70 | - | 5.00 | 25.00 | 52 tok/s |
| Claude Opus 5 (High)Anthropic | 48.10 | $4332 | 5.00 | 25.00 | 52 tok/s |
| MiMo-V2.5-Pro (Non-reasoning)Xiaomi | 18.30 | - | 0.39 | 1.17 | 52 tok/s |
| Claude Opus 5 (Low)Anthropic | 39.40 | $1561 | 5.00 | 25.00 | 52 tok/s |
| Claude Opus 5 (Xhigh)Anthropic | 49.70 | $5868 | 5.00 | 25.00 | 52 tok/s |
| MiMo-V2.5-Pro (Reasoning)Xiaomi | 26.00 | $231 | 0.41 | 1.02 | 52 tok/s |
| GPT-6 Astra (Medium)OpenAI | 49.60 | $2434 | 10.00 | 50.00 | 52 tok/s |
| Claude Opus 5 (Max)Anthropic | 50.80 | $7275 | 5.00 | 25.00 | 52 tok/s |
| GPT-6.1 Sol (High)OpenAIFrontera de mejor relación calidad-precio | 50.20 | $521 | 2.00 | 10.00 | 52 tok/s |
| Qwen3.8-Flash-NextAlibaba | 39.80 | $363 | 0.15 | 0.47 | 52 tok/s |
| MiniMax-M2.7MiniMax | 22.80 | - | 0.30 | 1.20 | 51 tok/s |
| GPT-6.1 Sol (Xhigh)OpenAIFrontera de mejor relación calidad-precio | 51.00 | $662 | 2.00 | 10.00 | 51 tok/s |
| Claude Opus 4.5 (Reasoning)Anthropic | 29.10 | - | 5.00 | 25.00 | 51 tok/s |
| Claude Opus 5 (Medium)Anthropic | 44.80 | $2732 | 5.00 | 25.00 | 50 tok/s |
| Kimi K2 0905Kimi | 15.30 | - | 0.60 | 2.50 | 50 tok/s |
| Qwen3.8 27B (Low)Alibaba | 26.20 | $1060 | 0.50 | 3.00 | 50 tok/s |
| Llama 4 MaverickMeta | 9.30 | $44.0 | 0.25 | 0.92 | 49 tok/s |
| Qwen3.8 27B (Non-reasoning)Alibaba | 20.20 | $2022 | 0.50 | 3.00 | 49 tok/s |
| Qwen3.8 27B (Medium)Alibaba | 27.60 | $1165 | 0.50 | 3.00 | 49 tok/s |
| Gemma 4 E4B (Non-reasoning)Google | 7.50 | - | 0.02 | 0.10 | 49 tok/s |
| Kimi K2Kimi | 12.70 | - | 0.57 | 2.30 | 48 tok/s |
| GPT-6.1 Sol (Low)OpenAI | 42.10 | $250 | 2.00 | 10.00 | 48 tok/s |
| GPT-6.1 Sol (Medium)OpenAIFrontera de mejor relación calidad-precio | 47.80 | $361 | 2.00 | 10.00 | 48 tok/s |
| Claude Opus 4.5 (Non-reasoning)Anthropic | 23.70 | - | 5.00 | 25.00 | 48 tok/s |
| Claude Opus 4.7 (Non-reasoning, High)Anthropic | 30.90 | - | 5.00 | 25.00 | 48 tok/s |
| Claude 4.5 Sonnet (Reasoning)Anthropic | 20.70 | $1501 | 3.00 | 15.00 | 47 tok/s |
| Mistral Medium 3Mistral | 9.00 | - | 0.40 | 2.00 | 46 tok/s |
| DeepSeek V3 (Dec '24)DeepSeek | 8.50 | $25.4 | 0.32 | 0.89 | 46 tok/s |
| Phi-4 Mini InstructMicrosoft | 6.30 | - | 0.07 | 0.30 | 46 tok/s |
| Mistral Small 3.1Mistral | 7.10 | $27.8 | 0.08 | 0.14 | 45 tok/s |
| Qwen3.8 27B (Xhigh)Alibaba | 33.70 | $1336 | 0.50 | 3.00 | 44 tok/s |
| Gemma 4 E4B (Reasoning)Google | 8.90 | $14.7 | 0.02 | 0.10 | 44 tok/s |
| Mistral Small 3Mistral | 6.70 | - | 0.05 | 0.08 | 44 tok/s |
| Claude 4.5 Sonnet (Non-reasoning)Anthropic | 19.30 | - | 3.00 | 15.00 | 43 tok/s |
| Claude Sonnet 4.6 (Non-reasoning, Low)Anthropic | 23.30 | - | 3.00 | 15.00 | 43 tok/s |
| Mistral Small 3.2Mistral | 7.00 | $122 | 0.07 | 0.20 | 43 tok/s |
| Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research | 7.40 | - | 1.00 | 3.00 | 43 tok/s |
| Claude Sonnet 4.6 (Non-reasoning, High)Anthropic | 24.70 | - | 3.00 | 15.00 | 43 tok/s |
| Qwen3.8 2.4T A95BAlibaba | 39.90 | $2632 | 2.00 | 6.00 | 43 tok/s |
| Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research | 7.50 | - | 1.00 | 3.00 | 42 tok/s |
| Kimi K3 (Max)Kimi | 43.60 | $3658 | 3.00 | 15.00 | 42 tok/s |
| Qwen3.8 MaxAlibaba | 40.20 | $3172 | 2.00 | 6.00 | 42 tok/s |
| Qwen3.8 Max (0902)Alibaba | 45.40 | $4935 | 2.00 | 6.00 | 41 tok/s |
| Qwen3 VL 235B A22B InstructAlibaba | 9.90 | - | 0.21 | 1.39 | 41 tok/s |
| Command ACohere | 7.00 | - | 2.50 | 10.00 | 40 tok/s |
| Claude Opus 4.6 (Max)Anthropic | 31.90 | - | 5.00 | 25.00 | 40 tok/s |
| Kimi K3 (Low)Kimi | 30.10 | $1190 | 3.00 | 15.00 | 40 tok/s |
| Seed-OSS-36B-InstructByteDance Seed | 12.10 | - | 0.21 | 0.57 | 40 tok/s |
| Llama 3.1 Instruct 70BMeta | 6.60 | - | 0.56 | 0.56 | 40 tok/s |
| Phi-4Microsoft | 5.90 | - | 0.13 | 0.50 | 39 tok/s |
| Qwen3 235B A22B 2507 InstructAlibaba | 12.00 | - | 0.21 | 0.84 | 39 tok/s |
| Granite 3.3 8B (Non-reasoning)IBM | 4.90 | - | 0.03 | 0.25 | 38 tok/s |
| Claude Opus 4.6 (Non-reasoning, High)Anthropic | 26.40 | - | 5.00 | 25.00 | 38 tok/s |
| GLM-4.7 (Non-reasoning)Z AI | 17.40 | - | 0.53 | 2.10 | 36 tok/s |
| GLM-4.7 (Reasoning)Z AI | 22.20 | - | 0.53 | 2.10 | 35 tok/s |
| GLM-4.6 (Non-reasoning)Z AI | 14.90 | - | 0.57 | 2.20 | 34 tok/s |
| GLM-4.6 (Reasoning)Z AI | 18.50 | - | 0.55 | 2.20 | 33 tok/s |
| GPT-4 TurboOpenAI | 7.00 | - | 10.00 | 30.00 | 33 tok/s |
| DeepSeek R1 0528 (May '25)DeepSeek | 13.10 | - | 1.85 | 2.75 | 33 tok/s |
| Hermes 3 - Llama-3.1 70BNous Research | 6.00 | - | 0.70 | 0.70 | 32 tok/s |
| Qwen3 VL 30B A3B InstructAlibaba | 7.90 | - | 0.35 | 0.60 | 29 tok/s |
| Qwen2.5 Instruct 72BAlibaba | 7.70 | - | 0.47 | 0.49 | 27 tok/s |
| Mixtral 8x7B InstructMistral | 5.10 | - | 0.45 | 0.70 | 25 tok/s |
| Llama 3.2 Instruct 11B (Vision)Meta | 5.40 | - | 0.34 | 0.34 | 24 tok/s |
| Qwen3 32B (Reasoning)Alibaba | 7.20 | - | 0.24 | 0.54 | 23 tok/s |
| Qwen3.5 4B (Reasoning)Alibaba | 13.10 | - | 0.03 | 0.15 | 15 tok/s |
| Qwen3.5 4B (Non-reasoning)Alibaba | 10.80 | - | 0.03 | 0.15 | 11 tok/s |
| Ling-flash-2.0InclusionAI | 7.80 | - | 0.14 | 0.57 | 5 tok/s |
Guías
Cómo comparamos los modelos
La inteligencia se mide con el Artificial Analysis Intelligence Index. El costo del benchmark es el costo total en USD de ejecutar esa prueba, incluidos los tokens de razonamiento; no es el precio de la API por token. Todas las versiones usan los mismos datos y cálculos. La puntuación general no mide el rendimiento en un idioma o tarea específicos.