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 | 12.40 | - | 0.20 | 0.70 | 1894 tok/s |
| Mercury 2Inception | 21.90 | $97.5 | 0.25 | 0.75 | 846 tok/s |
| LFM2.5-VL-1.6BLiquid AI | 1.00 | - | 0.00 | 0.00 | 442 tok/s |
| HyperNova 60B 2605Multiverse Computing | 18.30 | $37.5 | 0.04 | 0.14 | 401 tok/s |
| Gemini 3.5 Flash-LiteGoogle | 37.40 | $153 | 0.30 | 2.50 | 376 tok/s |
| Step 3.7 FlashStepFun | 30.90 | $320 | 0.20 | 1.15 | 364 tok/s |
| Gemini 2.5 Flash-Lite (Reasoning)Google | 11.40 | - | 0.10 | 0.40 | 349 tok/s |
| LFM2.5-8B-A1BLiquid AI | 8.10 | - | 0.00 | 0.00 | 335 tok/s |
| Ling-3.0-flashInclusionAI | 37.80 | $72.7 | 0.07 | 0.22 | 333 tok/s |
| Gemini 3.1 Flash-LiteGoogle | 25.60 | $93.8 | 0.25 | 1.50 | 327 tok/s |
| Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA | 15.00 | - | 0.07 | 0.30 | 324 tok/s |
| Nova MicroAmazon | 4.40 | - | 0.04 | 0.14 | 280 tok/s |
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA | 14.50 | $39.4 | 0.05 | 0.20 | 253 tok/s |
| Qwen3.5 Omni FlashAlibaba | 19.20 | - | 0.10 | 0.80 | 245 tok/s |
| o3-mini (high)OpenAI | 15.70 | - | 1.10 | 4.40 | 228 tok/s |
| o3-miniOpenAI | 19.20 | - | 1.10 | 4.40 | 221 tok/s |
| Muse Spark 1.1 (xhigh)MetaFrontera de mejor relación calidad-precio | 53.20 | $547 | 1.25 | 4.25 | 221 tok/s |
| Gemini 2.5 Flash (Reasoning)Google | 20.30 | - | 0.30 | 2.50 | 216 tok/s |
| Gemini 2.5 Flash-Lite (Non-reasoning)Google | 6.70 | - | 0.10 | 0.40 | 215 tok/s |
| Gemini 3.6 Flash (high)Google | 51.60 | $727 | 1.50 | 7.50 | 213 tok/s |
| Ministral 3 3BMistral | 7.10 | $91.6 | 0.10 | 0.10 | 212 tok/s |
| Gemini 2.5 Flash (Non-reasoning)Google | 14.20 | - | 0.30 | 2.50 | 205 tok/s |
| Qwen3 Next 80B A3B (Reasoning)Alibaba | 16.90 | $400 | 0.50 | 6.00 | 205 tok/s |
| Trinity Large ThinkingArcee AI | 18.40 | - | 0.23 | 0.88 | 203 tok/s |
| Qwen3.7 MaxAlibaba | 46.70 | $1064 | 2.50 | 7.50 | 202 tok/s |
| Gemini 3.5 Flash (medium)Google | 46.70 | - | 1.50 | 9.00 | 192 tok/s |
| GPT-5.6 Luna (max)OpenAIFrontera de mejor relación calidad-precio | 52.30 | $172 | 0.20 | 1.20 | 190 tok/s |
| Gemini 3 Flash Preview (Reasoning)Google | 38.70 | - | 0.50 | 3.00 | 186 tok/s |
| NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA | 4.20 | - | 0.20 | 0.60 | 186 tok/s |
| gpt-oss-120b (low)OpenAI | 14.90 | $24.1 | 0.15 | 0.59 | 185 tok/s |
| Qwen3 Next 80B A3B InstructAlibaba | 13.80 | - | 0.50 | 2.00 | 183 tok/s |
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA | 7.20 | - | 0.05 | 0.20 | 182 tok/s |
| Jamba 1.6 MiniAI21 Labs | 2.10 | - | 0.20 | 0.40 | 181 tok/s |
| NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA | 8.70 | - | 0.04 | 0.16 | 179 tok/s |
| GPT-5.6 Luna (high)OpenAIFrontera de mejor relación calidad-precio | 47.00 | $55.0 | 0.20 | 1.20 | 176 tok/s |
| GPT-5.6 Luna (xhigh)OpenAI | 50.10 | $95.1 | 0.20 | 1.20 | 175 tok/s |
| Qwen3.5 35B A3B (Non-reasoning)Alibaba | 24.30 | $228 | 0.25 | 2.00 | 174 tok/s |
| Grok 4.20 0309 v2 (Reasoning)SpaceXAI | 38.00 | - | 1.25 | 2.50 | 173 tok/s |
| NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA | 7.20 | - | 0.05 | 0.20 | 173 tok/s |
| GPT-5.4 mini (xhigh)OpenAI | 40.90 | $1096 | 0.75 | 4.50 | 172 tok/s |
| gpt-oss-120b (high)OpenAI | 24.10 | $94.6 | 0.15 | 0.59 | 170 tok/s |
| Gemini 3.5 Flash (high)Google | 52.00 | $1042 | 1.50 | 9.00 | 169 tok/s |
| Gemini 3.5 Flash (minimal)Google | 35.80 | - | 1.50 | 9.00 | 168 tok/s |
| Gemini 3 Flash Preview (Non-reasoning)Google | 27.90 | - | 0.50 | 3.00 | 168 tok/s |
| GPT-5.4 mini (medium)OpenAI | 30.50 | - | 0.75 | 4.50 | 167 tok/s |
| GPT-5.5 Instant (June 2026)OpenAI | 29.20 | $423 | 5.00 | 30.00 | 164 tok/s |
| Qwen3.6 35B A3B (Non-reasoning)Alibaba | 24.60 | - | 0.38 | 2.25 | 162 tok/s |
| GPT-5.4 nano (medium)OpenAI | 30.80 | - | 0.20 | 1.25 | 161 tok/s |
| GPT-5.4 nano (Non-Reasoning)OpenAI | 17.80 | - | 0.20 | 1.25 | 160 tok/s |
| GPT-4.1 nanoOpenAI | 9.60 | $36.7 | 0.10 | 0.40 | 160 tok/s |
| GPT-5.6 Luna (medium)OpenAIFrontera de mejor relación calidad-precio | 38.90 | $21.1 | 0.20 | 1.20 | 160 tok/s |
| Nova 2.0 Lite (low)Amazon | 18.00 | - | 0.30 | 2.50 | 159 tok/s |
| GPT-5.4 nano (xhigh)OpenAI | 39.70 | $277 | 0.20 | 1.25 | 157 tok/s |
| GPT-5.4 mini (Non-Reasoning)OpenAI | 16.80 | - | 0.75 | 4.50 | 156 tok/s |
| Qwen3.5 35B A3B (Reasoning)Alibaba | 29.90 | - | 0.25 | 2.00 | 156 tok/s |
| GPT-5.6 Luna (Non-reasoning)OpenAIFrontera de mejor relación calidad-precio | 26.80 | $10.2 | 0.20 | 1.20 | 156 tok/s |
| Nova 2.0 Lite (medium)Amazon | 19.20 | - | 0.30 | 2.50 | 156 tok/s |
| Nova 2.0 Lite (high)Amazon | 20.80 | - | 0.30 | 2.50 | 155 tok/s |
| Nova 2.0 Lite (Non-reasoning)Amazon | 11.80 | - | 0.30 | 2.50 | 154 tok/s |
| gpt-oss-20b (low)OpenAI | 14.40 | - | 0.07 | 0.20 | 154 tok/s |
| gpt-oss-20b (high)OpenAI | 15.20 | $32.7 | 0.06 | 0.19 | 152 tok/s |
| o4-mini (high)OpenAI | 26.10 | - | 1.10 | 4.40 | 151 tok/s |
| Nova LiteAmazon | 6.70 | - | 0.06 | 0.24 | 150 tok/s |
| GPT-5 nano (minimal)OpenAI | 7.80 | - | 0.05 | 0.40 | 148 tok/s |
| GPT-5.6 Luna (low)OpenAIFrontera de mejor relación calidad-precio | 33.90 | $13.7 | 0.20 | 1.20 | 147 tok/s |
| Mistral Medium 3.5Mistral | 30.40 | $883 | 1.50 | 7.50 | 145 tok/s |
| Mistral Small 4 (Reasoning)Mistral | 19.70 | $87.7 | 0.15 | 0.60 | 144 tok/s |
| Inkling SmallThinking Machines | 41.20 | $193 | 0.30 | 1.20 | 143 tok/s |
| Qwen3 30B A3B 2507 InstructAlibaba | 8.90 | - | 0.20 | 0.80 | 143 tok/s |
| Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA | 38.30 | $534 | 0.60 | 2.75 | 142 tok/s |
| Qwen3 30B A3B 2507 (Reasoning)Alibaba | 14.60 | $152 | 0.20 | 2.40 | 141 tok/s |
| NVIDIA Nemotron 3 Super 120B A12B (Reasoning)NVIDIA | 25.70 | $254 | 0.20 | 0.80 | 140 tok/s |
| Llama 3.1 Instruct 8BMeta | 7.40 | - | 0.05 | 0.08 | 139 tok/s |
| Grok 4.20 0309 v2 (Non-reasoning)SpaceXAI | 22.20 | - | 1.25 | 2.50 | 138 tok/s |
| Gemini 2.5 ProGoogle | 25.90 | $611 | 1.25 | 10.00 | 137 tok/s |
| Mistral Small 3.2Mistral | 10.70 | $129 | 0.10 | 0.30 | 137 tok/s |
| Qwen3 Coder NextAlibaba | 21.30 | $250 | 0.35 | 1.20 | 136 tok/s |
| Step 3.5 FlashStepFun | 26.00 | - | 0.10 | 0.30 | 136 tok/s |
| GPT-5 nano (high)OpenAI | 20.10 | - | 0.05 | 0.40 | 135 tok/s |
| Step 3.5 Flash 2603StepFun | 26.50 | - | 0.10 | 0.30 | 135 tok/s |
| GPT-5 nano (medium)OpenAI | 19.20 | - | 0.05 | 0.40 | 135 tok/s |
| Mistral Small 3Mistral | 6.70 | - | 0.10 | 0.30 | 134 tok/s |
| Mistral Small (Feb '24)Mistral | 3.20 | - | 0.15 | 0.60 | 133 tok/s |
| Solar Pro 3Upstage | 14.50 | $158 | 0.15 | 0.60 | 132 tok/s |
| Gemini 3.1 Pro PreviewGoogle | 47.70 | $812 | 2.00 | 12.00 | 131 tok/s |
| Mistral Small (Sep '24)Mistral | 4.30 | - | 0.20 | 0.60 | 131 tok/s |
| Agnes 2.5 Pro AlphaSapiens AI | 39.70 | - | 0.45 | 0.90 | 131 tok/s |
| Qwen3.5 122B A10B (Non-reasoning)Alibaba | 28.20 | $221 | 0.40 | 3.20 | 130 tok/s |
| Nex-N2-ProNex AGI | 42.10 | - | 0.50 | 2.50 | 129 tok/s |
| Mistral Small 4 (Non-reasoning)Mistral | 12.30 | - | 0.15 | 0.60 | 128 tok/s |
| Magistral Small 1.2Mistral | 11.50 | $301 | 0.50 | 1.50 | 126 tok/s |
| Mistral Small 3.1Mistral | 14.90 | $29.8 | 0.10 | 0.30 | 125 tok/s |
| GPT-4o (Nov '24)OpenAI | 11.10 | - | 2.50 | 10.00 | 125 tok/s |
| GPT-5.4 (xhigh)OpenAI | 53.10 | $2183 | 2.50 | 15.00 | 125 tok/s |
| GPT-5.6 Terra (max)OpenAI | 56.60 | $1390 | 2.00 | 12.00 | 125 tok/s |
| GLM-5.2 (max)Z AI | 52.60 | $904 | 1.30 | 4.18 | 124 tok/s |
| Qwen3.6 35B A3B (Reasoning)Alibaba | 32.10 | $334 | 0.25 | 1.49 | 124 tok/s |
| GPT-5.3 Codex (xhigh)OpenAI | 45.50 | - | 1.75 | 14.00 | 120 tok/s |
| Grok 4.3 (medium)SpaceXAI | 36.90 | - | 1.25 | 2.50 | 119 tok/s |
| GLM-4.7-Flash (Non-reasoning)Z AI | 15.60 | - | 0.07 | 0.40 | 117 tok/s |
| Nova 2.0 Pro Preview (low)Amazon | 19.80 | - | 1.25 | 10.00 | 116 tok/s |
| Grok 4.3 (high)SpaceXAI | 37.90 | $288 | 1.25 | 2.50 | 116 tok/s |
| Nova 2.0 Pro Preview (medium)Amazon | 22.10 | - | 1.25 | 10.00 | 116 tok/s |
| Qwen3 VL 8B (Reasoning)Alibaba | 10.50 | - | 0.18 | 2.10 | 114 tok/s |
| o3OpenAI | 31.10 | - | 2.00 | 8.00 | 114 tok/s |
| Qwen3 VL 8B InstructAlibaba | 8.20 | - | 0.18 | 0.70 | 114 tok/s |
| Grok 4.3 (low)SpaceXAI | 36.30 | - | 1.25 | 2.50 | 113 tok/s |
| Qwen3.5 122B A10B (Reasoning)Alibaba | 32.80 | $444 | 0.40 | 3.20 | 113 tok/s |
| Mistral 7B InstructMistral | 1.70 | - | 0.25 | 0.25 | 111 tok/s |
| Llama 4 MaverickMeta | 14.50 | $35.9 | 0.27 | 0.85 | 111 tok/s |
| DeepSeek V4 Flash (Non-reasoning)DeepSeek | 29.30 | - | 0.14 | 0.28 | 110 tok/s |
| Ministral 3 8BMistral | 9.00 | $114 | 0.15 | 0.15 | 110 tok/s |
| Qwen3 VL 30B A3B (Reasoning)Alibaba | 13.40 | - | 0.20 | 2.40 | 110 tok/s |
| GPT-5.6 Terra (medium)OpenAI | 46.80 | $192 | 2.00 | 12.00 | 109 tok/s |
| GPT-5.6 Terra (xhigh)OpenAI | 52.80 | $590 | 2.00 | 12.00 | 109 tok/s |
| Qwen3 VL 30B A3B InstructAlibaba | 9.90 | - | 0.20 | 0.80 | 109 tok/s |
| Grok 4.3 (Non-reasoning)SpaceXAI | 25.00 | $201 | 1.25 | 2.50 | 108 tok/s |
| KAT Coder Pro V2KwaiKAT | 34.50 | - | 0.30 | 1.20 | 108 tok/s |
| Kimi K2 ThinkingKimi | 33.50 | - | 0.60 | 2.50 | 107 tok/s |
| Llama 4 ScoutMeta | 10.30 | $11.6 | 0.18 | 0.66 | 107 tok/s |
| GPT-5.6 Terra (low)OpenAI | 41.30 | $130 | 2.00 | 12.00 | 106 tok/s |
| DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeekFrontera de mejor relación calidad-precio | 51.80 | $72.0 | 0.14 | 0.28 | 106 tok/s |
| Qwen2.5 TurboAlibaba | 6.00 | - | 0.05 | 0.20 | 106 tok/s |
| Qwen3 30B A3B (Reasoning)Alibaba | 9.20 | - | 0.20 | 2.40 | 105 tok/s |
| GPT-4.1OpenAI | 19.60 | - | 2.00 | 8.00 | 104 tok/s |
| Qwen3 30B A3B (Non-reasoning)Alibaba | 6.60 | - | 0.20 | 0.80 | 103 tok/s |
| Granite 4.1 8BIBM | 6.40 | - | 0.05 | 0.10 | 103 tok/s |
| GPT-5.6 Terra (Non-reasoning)OpenAI | 34.60 | $98.5 | 2.00 | 12.00 | 103 tok/s |
| GPT-5.1 (Non-reasoning)OpenAI | 20.70 | - | 1.25 | 10.00 | 103 tok/s |
| Grok Build 0.1 0616SpaceXAI | 40.70 | $377 | 1.00 | 2.00 | 102 tok/s |
| Llama 3.1 Nemotron Instruct 70BNVIDIA | 7.40 | - | 1.20 | 1.20 | 102 tok/s |
| Gemma 4 12B (Reasoning)Google | 22.20 | - | 0.10 | 0.30 | 101 tok/s |
| GPT-5.1 (high)OpenAI | 37.50 | $782 | 1.25 | 10.00 | 100 tok/s |
| Qwen3 Omni 30B A3B (Reasoning)Alibaba | 9.50 | - | 0.25 | 0.97 | 100 tok/s |
| Ling 2.6 FlashInclusionAI | 14.20 | - | 0.10 | 0.30 | 98 tok/s |
| GPT-5.6 Terra (high)OpenAI | 50.10 | $395 | 2.00 | 12.00 | 98 tok/s |
| GLM-4.7 (Non-reasoning)Z AI | 27.10 | - | 0.60 | 2.20 | 98 tok/s |
| MiMo-V2.5Xiaomi | 38.00 | $25.2 | 0.14 | 0.28 | 97 tok/s |
| MiniMax-M3MiniMax | 45.40 | $205 | 0.30 | 1.20 | 97 tok/s |
| GLM-4.7 (Reasoning)Z AI | 34.50 | $607 | 0.60 | 2.20 | 96 tok/s |
| MiniMax-M2MiniMax | 28.90 | - | 0.30 | 1.20 | 95 tok/s |
| Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA | 8.50 | - | 0.40 | 0.40 | 95 tok/s |
| Qwen3 Omni 30B A3B InstructAlibaba | 4.80 | - | 0.25 | 0.97 | 95 tok/s |
| MiniMax-M2.5MiniMax | 34.50 | - | 0.30 | 1.20 | 94 tok/s |
| MiniMax-M2.1MiniMax | 32.10 | - | 0.30 | 1.20 | 94 tok/s |
| Qwen3 32B (Reasoning)Alibaba | 11.40 | - | 0.70 | 8.40 | 93 tok/s |
| GLM-4.7-Flash (Reasoning)Z AI | 23.30 | - | 0.07 | 0.40 | 93 tok/s |
| Nova 2.0 Pro Preview (Non-reasoning)Amazon | 14.40 | - | 1.25 | 10.00 | 93 tok/s |
| Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research | 6.70 | - | 0.13 | 0.40 | 92 tok/s |
| Qwen3 32B (Non-reasoning)Alibaba | 8.50 | - | 0.70 | 2.80 | 92 tok/s |
| Claude 4.5 Haiku (Reasoning)Anthropic | 29.90 | $471 | 1.00 | 5.00 | 92 tok/s |
| GLM-4.5V (Non-reasoning)Z AI | 6.80 | - | 0.60 | 1.80 | 92 tok/s |
| Qwen3 Coder 30B A3B InstructAlibaba | 13.60 | - | 0.45 | 2.25 | 91 tok/s |
| GLM-5.2 (Non-reasoning)Z AI | 34.80 | - | 1.35 | 4.25 | 91 tok/s |
| Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research | 9.90 | - | 0.13 | 0.40 | 91 tok/s |
| GPT-5 mini (medium)OpenAI | 31.60 | - | 0.25 | 2.00 | 90 tok/s |
| Ministral 3 14BMistral | 11.20 | $119 | 0.20 | 0.20 | 90 tok/s |
| Qwen3 VL 32B (Reasoning)Alibaba | 18.10 | - | 0.70 | 8.40 | 89 tok/s |
| GPT-5.4 (low)OpenAI | 40.20 | - | 2.50 | 15.00 | 89 tok/s |
| GPT-5 mini (high)OpenAI | 25.80 | $130 | 0.25 | 2.00 | 89 tok/s |
| GPT-5 (high)OpenAI | 35.30 | $789 | 1.25 | 10.00 | 89 tok/s |
| Claude 4.5 Haiku (Non-reasoning)Anthropic | 24.10 | - | 1.00 | 5.00 | 87 tok/s |
| GPT-5.4 (Non-reasoning)OpenAI | 28.30 | - | 2.50 | 15.00 | 87 tok/s |
| GPT-4o miniOpenAI | 6.70 | - | 0.15 | 0.60 | 86 tok/s |
| GPT-5 (low)OpenAI | 31.90 | - | 1.25 | 10.00 | 86 tok/s |
| Mistral Medium 3.1Mistral | 14.70 | $134 | 0.40 | 2.00 | 86 tok/s |
| Gemma 4 12B (Non-reasoning)Google | 13.20 | - | 0.10 | 0.30 | 85 tok/s |
| GLM-4.5-AirZ AI | 16.70 | - | 0.17 | 0.98 | 83 tok/s |
| GPT-5 mini (minimal)OpenAI | 14.30 | - | 0.25 | 2.00 | 83 tok/s |
| GPT-4o (Aug '24)OpenAI | 9.40 | - | 2.50 | 10.00 | 82 tok/s |
| GLM-4.5V (Reasoning)Z AI | 9.00 | - | 0.60 | 1.80 | 82 tok/s |
| Inkling (xhigh)Thinking Machines | 42.30 | - | 1.00 | 4.05 | 81 tok/s |
| Qwen3.5 27B (Non-reasoning)Alibaba | 30.00 | - | 0.30 | 2.40 | 81 tok/s |
| Llama 3.3 Instruct 70BMeta | 9.30 | - | 0.66 | 0.72 | 80 tok/s |
| Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA | 12.40 | - | 0.40 | 0.40 | 80 tok/s |
| GPT-5 (medium)OpenAI | 34.60 | - | 1.25 | 10.00 | 79 tok/s |
| Qwen3.5 397B A17B (Reasoning)Alibaba | 34.30 | $527 | 0.60 | 3.60 | 78 tok/s |
| Mistral MediumMistral | 3.20 | - | 1.50 | 7.50 | 78 tok/s |
| Qwen3.5 397B A17B (Non-reasoning)Alibaba | 32.70 | - | 0.60 | 3.60 | 78 tok/s |
| Qwen3.5 27B (Reasoning)Alibaba | 34.60 | - | 0.30 | 2.40 | 77 tok/s |
| GLM-4.6V (Non-reasoning)Z AI | 10.90 | - | 0.30 | 0.90 | 77 tok/s |
| Ling-flash-2.0InclusionAI | 9.60 | - | 0.14 | 0.57 | 76 tok/s |
| GLM-5.1 (Reasoning)Z AI | 41.00 | $676 | 1.38 | 4.40 | 74 tok/s |
| Grok 3 mini Reasoning (high)SpaceXAI | 22.90 | - | 0.30 | 0.50 | 74 tok/s |
| GPT-5.2 (xhigh)OpenAI | 43.30 | - | 1.75 | 14.00 | 73 tok/s |
| Gemma 4 E4B (Reasoning)Google | 12.20 | - | 0.02 | 0.10 | 72 tok/s |
| Gemma 4 E4B (Non-reasoning)Google | 8.70 | - | 0.02 | 0.10 | 72 tok/s |
| MiMo-V2.5-ProXiaomi | 42.90 | $98.9 | 0.43 | 0.87 | 71 tok/s |
| GPT-4o (May '24)OpenAI | 8.40 | - | 5.00 | 15.00 | 70 tok/s |
| GPT-4.1 miniOpenAI | 14.80 | $64.2 | 0.40 | 1.60 | 69 tok/s |
| NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA | 8.80 | - | 0.20 | 0.60 | 69 tok/s |
| GPT-5.5 (xhigh)OpenAI | 56.30 | $2778 | 5.00 | 30.00 | 69 tok/s |
| Gemma 4 26B A4B (Non-reasoning)Google | 20.40 | - | 0.13 | 0.40 | 68 tok/s |
| Qwen3.8 MaxAlibaba | 58.10 | $1741 | 2.00 | 6.00 | 68 tok/s |
| Qwen3.5 9B (Reasoning)Alibaba | 21.80 | $240 | 0.14 | 0.20 | 67 tok/s |
| GPT-5.2 (Non-reasoning)OpenAI | 26.50 | - | 1.75 | 14.00 | 67 tok/s |
| Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Anthropic | 55.30 | $4011 | 2.00 | 10.00 | 67 tok/s |
| Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic | 62.10 | $5455 | 10.00 | 50.00 | 67 tok/s |
| Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)Anthropic | - | - | 2.00 | 10.00 | 66 tok/s |
| GPT-5.5 (high)OpenAI | 54.70 | $1721 | 5.00 | 30.00 | 66 tok/s |
| Hy3Tencent | 42.20 | $93.6 | 0.14 | 0.56 | 66 tok/s |
| MiMo-V2.5-Pro (Non-reasoning)Xiaomi | 28.40 | - | 0.43 | 0.87 | 66 tok/s |
| Qwen3 VL 32B InstructAlibaba | 11.00 | - | 0.70 | 2.80 | 66 tok/s |
| GPT-5.5 (medium)OpenAI | 51.40 | $939 | 5.00 | 30.00 | 65 tok/s |
| Claude Sonnet 5 (Adaptive Reasoning, High Effort)Anthropic | - | - | 2.00 | 10.00 | 65 tok/s |
| Gemma 4 31B (Non-reasoning)Google | 22.30 | $32.8 | 0.15 | 0.40 | 65 tok/s |
| Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)Anthropic | - | - | 2.00 | 10.00 | 65 tok/s |
| GLM-4.6V (Reasoning)Z AI | 16.90 | - | 0.30 | 0.90 | 64 tok/s |
| GPT-5 (minimal)OpenAI | 17.30 | - | 1.25 | 10.00 | 64 tok/s |
| Magistral Medium 1.2Mistral | 18.00 | $920 | 2.00 | 5.00 | 64 tok/s |
| GPT-5.6 Sol (max)OpenAI | 60.90 | $2823 | 5.00 | 30.00 | 63 tok/s |
| GLM-5.1 (Non-reasoning)Z AI | 36.30 | - | 1.38 | 4.40 | 63 tok/s |
| DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek | 45.30 | $176 | 0.43 | 0.87 | 63 tok/s |
| Qwen3 235B A22B 2507 (Reasoning)Alibaba | 19.90 | $610 | 0.70 | 8.40 | 62 tok/s |
| Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Anthropic | 48.40 | $3355 | 3.00 | 15.00 | 62 tok/s |
| GPT-5.5 (low)OpenAI | 44.50 | $374 | 5.00 | 30.00 | 61 tok/s |
| GPT-5.6 Sol (high)OpenAIFrontera de mejor relación calidad-precio | 57.30 | $955 | 5.00 | 30.00 | 61 tok/s |
| Claude Sonnet 5 (Non-reasoning, High Effort)Anthropic | 42.60 | $416 | 2.00 | 10.00 | 61 tok/s |
| GLM-4.6 (Non-reasoning)Z AI | 23.40 | - | 0.57 | 2.20 | 61 tok/s |
| MiniMax-M2.7MiniMax | 38.90 | - | 0.30 | 1.20 | 61 tok/s |
| GPT-5.6 Sol (Non-reasoning)OpenAI | 41.90 | $240 | 5.00 | 30.00 | 60 tok/s |
| GPT-5.6 Sol (xhigh)OpenAIFrontera de mejor relación calidad-precio | 59.00 | $1525 | 5.00 | 30.00 | 60 tok/s |
| GPT-5.6 Sol (low)OpenAI | 50.70 | $344 | 5.00 | 30.00 | 60 tok/s |
| Qwen3 235B A22B (Reasoning)Alibaba | 13.50 | - | 0.70 | 8.40 | 59 tok/s |
| Qwen3 Max (Preview)Alibaba | 19.40 | - | 1.20 | 6.00 | 58 tok/s |
| Qwen3 Coder 480B A35B InstructAlibaba | 18.20 | - | 1.50 | 7.50 | 57 tok/s |
| GPT-5.5 (Non-reasoning)OpenAI | 35.80 | $212 | 5.00 | 30.00 | 57 tok/s |
| Qwen3 14B (Non-reasoning)Alibaba | 6.80 | - | 0.35 | 1.40 | 57 tok/s |
| Claude Sonnet 5 (Adaptive Reasoning, Low Effort)Anthropic | - | - | 2.00 | 10.00 | 57 tok/s |
| Command ACohere | 7.50 | - | 2.50 | 10.00 | 57 tok/s |
| Qwen3 MaxAlibaba | 24.50 | - | 1.20 | 6.00 | 57 tok/s |
| Qwen3.7 PlusAlibaba | 39.40 | $322 | 0.40 | 1.60 | 57 tok/s |
| Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic | 57.30 | $3752 | 5.00 | 25.00 | 57 tok/s |
| Llama 3.1 Instruct 70BMeta | 6.50 | - | 0.56 | 0.56 | 57 tok/s |
| Qwen3 235B A22B 2507 InstructAlibaba | 18.40 | - | 0.70 | 2.80 | 57 tok/s |
| Qwen3 VL 235B A22B (Reasoning)Alibaba | 20.90 | - | 0.70 | 8.40 | 57 tok/s |
| Qwen3 Max Thinking (Preview)Alibaba | 25.50 | - | 1.20 | 6.00 | 56 tok/s |
| Qwen3 235B A22B (Non-reasoning)Alibaba | 10.80 | - | 0.70 | 2.80 | 56 tok/s |
| Qwen3.6 PlusAlibaba | 40.50 | $526 | 0.50 | 3.00 | 56 tok/s |
| Reka Flash (Sep '24)Reka AI | 6.00 | - | 0.20 | 0.80 | 56 tok/s |
| DeepSeek V4 Pro (Reasoning, High Effort)DeepSeek | 43.70 | $109 | 0.43 | 0.87 | 56 tok/s |
| Jamba 1.6 LargeAI21 Labs | 4.70 | - | 2.00 | 8.00 | 56 tok/s |
| GPT-5.6 Sol (medium)OpenAI | 55.60 | $580 | 5.00 | 30.00 | 56 tok/s |
| Qwen3.6 27B (Reasoning)Alibaba | 37.70 | $667 | 0.60 | 3.60 | 56 tok/s |
| Qwen3.6 27B (Non-reasoning)Alibaba | 31.30 | $359 | 0.60 | 3.60 | 55 tok/s |
| Claude Opus 5 (Adaptive Reasoning, Medium Effort)AnthropicFrontera de mejor relación calidad-precio | 58.60 | $1116 | 5.00 | 25.00 | 55 tok/s |
| Claude Opus 5 (Adaptive Reasoning, Max Effort)AnthropicFrontera de mejor relación calidad-precio | 63.10 | $3836 | 5.00 | 25.00 | 55 tok/s |
| Grok 4.5 (high)SpaceXAIFrontera de mejor relación calidad-precio | 55.80 | $579 | 2.00 | 6.00 | 54 tok/s |
| Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)AnthropicFrontera de mejor relación calidad-precio | 62.50 | $2909 | 5.00 | 25.00 | 54 tok/s |
| Jamba 1.7 LargeAI21 Labs | 5.00 | - | 2.00 | 8.00 | 54 tok/s |
| DeepSeek V4 Pro (Non-reasoning)DeepSeek | 31.90 | - | 0.43 | 0.87 | 53 tok/s |
| Claude Opus 5 (Adaptive Reasoning, High Effort)AnthropicFrontera de mejor relación calidad-precio | 61.50 | $1974 | 5.00 | 25.00 | 53 tok/s |
| Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA | 8.90 | - | 0.60 | 1.80 | 52 tok/s |
| Claude Opus 5 (Adaptive Reasoning, Low Effort)Anthropic | 52.50 | $555 | 5.00 | 25.00 | 52 tok/s |
| Qwen3 14B (Reasoning)Alibaba | 10.40 | - | 0.35 | 4.20 | 52 tok/s |
| Qwen3.5 Omni PlusAlibaba | 31.30 | - | 0.40 | 4.80 | 52 tok/s |
| Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Anthropic | 55.00 | $3743 | 5.00 | 25.00 | 51 tok/s |
| Qwen3 VL 235B A22B InstructAlibaba | 14.40 | - | 0.70 | 2.80 | 51 tok/s |
| Kimi K2.5 (Reasoning)Kimi | 36.00 | $304 | 0.60 | 3.00 | 50 tok/s |
| Qwen3.6 Max PreviewAlibaba | 41.10 | - | 1.30 | 7.80 | 50 tok/s |
| Mistral Medium 3Mistral | 12.50 | - | 0.40 | 2.00 | 48 tok/s |
| Claude Opus 4.5 (Reasoning)Anthropic | 41.90 | - | 5.00 | 25.00 | 48 tok/s |
| Granite 4.0 H SmallIBM | 4.90 | - | 0.06 | 0.25 | 47 tok/s |
| GLM-4.6 (Reasoning)Z AI | 29.30 | $314 | 0.55 | 2.20 | 47 tok/s |
| Kimi K2.5 (Non-reasoning)Kimi | 30.10 | - | 0.60 | 3.00 | 46 tok/s |
| Gemma 3n E4B InstructGoogle | 1.00 | - | 0.06 | 0.12 | 45 tok/s |
| Claude Opus 4.5 (Non-reasoning)Anthropic | 35.60 | - | 5.00 | 25.00 | 45 tok/s |
| Claude Opus 4.7 (Non-reasoning, High Effort)Anthropic | 43.90 | - | 5.00 | 25.00 | 44 tok/s |
| Kimi K2.6Kimi | 45.10 | $841 | 0.95 | 4.00 | 44 tok/s |
| Claude Sonnet 4.6 (Non-reasoning, High Effort)Anthropic | 36.80 | - | 3.00 | 15.00 | 43 tok/s |
| Kimi K2.7 CodeKimi | 43.00 | $545 | 0.95 | 4.00 | 43 tok/s |
| Claude Sonnet 4.6 (Non-reasoning, Low Effort)Anthropic | 35.10 | - | 3.00 | 15.00 | 43 tok/s |
| Claude Opus 4.6 (Adaptive Reasoning, Max Effort)Anthropic | 44.90 | - | 5.00 | 25.00 | 42 tok/s |
| Phi-4 Mini InstructMicrosoft | 5.70 | - | 0.00 | 0.00 | 42 tok/s |
| LongCat 2.0LongCat | 34.30 | - | 0.75 | 2.95 | 41 tok/s |
| Claude 4.5 Sonnet (Reasoning)Anthropic | 37.40 | $1037 | 3.00 | 15.00 | 40 tok/s |
| Mistral Large 3Mistral | 15.90 | $71.1 | 0.50 | 1.50 | 40 tok/s |
| Kimi K2.6 (Non-reasoning)Kimi | 35.40 | - | 0.95 | 4.00 | 40 tok/s |
| Kimi K3 (low)Kimi | 48.30 | $283 | 3.00 | 15.00 | 40 tok/s |
| Claude 4.5 Sonnet (Non-reasoning)Anthropic | 29.90 | - | 3.00 | 15.00 | 40 tok/s |
| GLM-5 (Reasoning)Z AI | 40.60 | - | 1.00 | 3.20 | 40 tok/s |
| Kimi K3 (max)Kimi | 59.70 | $2425 | 3.00 | 15.00 | 39 tok/s |
| GLM-5 (Non-reasoning)Z AI | 33.20 | - | 1.00 | 3.20 | 38 tok/s |
| Kimi K2 0905Kimi | 24.00 | - | 0.60 | 2.50 | 38 tok/s |
| Qwen3 8B (Non-reasoning)Alibaba | 4.80 | - | 0.18 | 0.70 | 38 tok/s |
| Kimi K2Kimi | 19.70 | - | 0.57 | 2.30 | 37 tok/s |
| Qwen3.5 4B (Reasoning)Alibaba | 20.40 | - | 0.03 | 0.15 | 37 tok/s |
| Qwen3 8B (Reasoning)Alibaba | 8.30 | - | 0.18 | 2.10 | 37 tok/s |
| Claude Opus 4.6 (Non-reasoning, High Effort)Anthropic | 38.80 | - | 5.00 | 25.00 | 36 tok/s |
| Gemma 4 31B (Reasoning)Google | 30.00 | - | 0.00 | 0.00 | 35 tok/s |
| Seed-OSS-36B-InstructByteDance Seed | 18.50 | - | 0.21 | 0.57 | 35 tok/s |
| Hermes 3 - Llama-3.1 70BNous Research | 4.80 | - | 0.70 | 0.70 | 34 tok/s |
| Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research | 8.80 | - | 1.00 | 3.00 | 33 tok/s |
| Nova PremierAmazon | 12.70 | - | 2.50 | 12.50 | 33 tok/s |
| QwQ 32BAlibaba | 13.40 | - | 0.66 | 1.00 | 32 tok/s |
| Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research | 8.60 | - | 1.00 | 3.00 | 32 tok/s |
| GPT-4 TurboOpenAI | 7.70 | - | 10.00 | 30.00 | 29 tok/s |
| Qwen3.5 4B (Non-reasoning)Alibaba | 16.10 | - | 0.03 | 0.15 | 29 tok/s |
| DeepSeek R1 Distill Llama 70BDeepSeek | 9.80 | - | 0.70 | 1.05 | 26 tok/s |
| Phi-4 Multimodal InstructMicrosoft | 4.20 | - | 0.00 | 0.00 | 18 tok/s |
| Granite 3.3 8B (Non-reasoning)IBM | 1.30 | - | 0.03 | 0.25 | 15 tok/s |
| Llama 3.2 Instruct 11B (Vision)Meta | 3.00 | - | 0.34 | 0.34 | 9 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.