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