Ranking de LLMs — Comparação de modelos de IA da OpenAI, Anthropic, Google, SpaceXAI e outras
Comparação e ranking do desempenho de mais de 250 modelos de IA (LLMs) em métricas importantes como inteligência, preço, desempenho e velocidade (velocidade de saída — tokens por segundo — e latência — TTFT), janela de contexto e outras.
Para mais detalhes, inclusive sobre nossa metodologia, consulte as perguntas frequentes.
Inteligência
Claude Opus 5.5 (max with fallback) e Claude Sonnet 5.5 (max with fallback) são os modelos com maior inteligência, seguidos por Claude Opus 5.5 (xhigh with fallback) e Muse Wonder Full (max).
Velocidade de saída
Celeris-1 e Mercury 2.5 são os modelos mais rápidos, seguidos por Gemini 3.5 Flash-Lite e Trinity Large Thinking.
Latência
North Mini Code e Nemotron 3 Nano Omni 30B A3B são os modelos com menor latência, seguidos por Command A+ e Nemotron 3 Nano (non-reasoning).
Custo por tarefa
K2 Horizon 375B A23B e Gemma 4 31B têm o menor custo por tarefa, seguidos por Command A+ e Ling 3.0 Tiny.
Janela de contexto
Llama 4 Scout e GPT-6 Sol (Daybreak Blue, max) permitem as maiores janelas de contexto, seguidos por Muse Wonder (max) e Kimi K3 (max).
Análises adicionais | ||||||||
|---|---|---|---|---|---|---|---|---|
Claude Opus 5.5 (max with fallback) | 1M | Anthropic | 58 | $5.98 | 95 | 650.11 | 655.38 | |
Claude Sonnet 5.5 (max with fallback) | 1M | Anthropic | 56 | $5.46 | 137 | 435.21 | 438.87 | |
Claude Opus 5.5 (xhigh with fallback) | 1M | Anthropic | 56 | $3.46 | 82 | 144.79 | 150.85 | |
Muse Wonder Full (max) | 1M | Meta | 56 | -- | -- | -- | -- | |
Claude Opus 5.5 (high with fallback) | 1M | Anthropic | 54 | $1.82 | 83 | 60.69 | 66.73 | |
Claude Fable 5.1 (max with fallback) | 1M | Anthropic | 53 | $7.63 | 71 | 249.68 | 256.72 | |
Claude Fable 5.1 (xhigh with fallback) | 1M | Anthropic | 53 | $5.98 | 63 | 122.30 | 130.23 | |
GPT-6 Astra (max) | 1M | OpenAI | 53 | $3.26 | 61 | 284.19 | 292.34 | |
Gemini 4 Argon (high) | 1M | Google | 53 | $1.99 | -- | -- | -- | |
Muse Wonder (max) | 1.05M | Meta | 52 | $4.52 | 115 | 39.24 | 60.98 | |
GPT-6 Astra (xhigh) | 1M | OpenAI | 52 | $2.31 | 57 | 175.16 | 184.00 | |
Claude Sonnet 5.5 (xhigh with fallback) | 1M | Anthropic | 52 | $2.01 | 103 | 36.88 | 41.72 | |
GPT-6.1 Sol (max) | 1M | OpenAI | 52 | $0.72 | 59 | 278.78 | 287.21 | |
Claude Opus 5.5 (medium with fallback) | 1M | Anthropic | 51 | $1.34 | 79 | 26.77 | 33.11 | |
Claude Fable 5.1 (high with fallback) | 1M | Anthropic | 51 | $3.91 | 55 | 20.37 | 29.42 | |
GPT-6.1 Sol (xhigh) | 1M | OpenAI | 51 | $0.39 | 60 | 182.62 | 191.01 | |
GPT-6 Astra (high) | 1M | OpenAI | 51 | $1.73 | 53 | 94.34 | 103.75 | |
GPT-6.1 Sol (high) | 1M | OpenAI | 50 | $0.32 | 56 | 56.67 | 65.54 | |
GPT-6 Astra (medium) | 1M | OpenAI | 50 | $1.54 | 52 | 6.30 | 15.94 | |
Claude Fable 5.1 (medium with fallback) | 1M | Anthropic | 49 | $2.98 | 56 | 11.41 | 20.42 | |
Muse Spark 1.3 (max) | 1M | Meta | 48 | $1.60 | 128 | 47.22 | 66.72 | |
GPT-6.1 Sol (medium) | 1M | OpenAI | 48 | $0.21 | 55 | 7.59 | 16.64 | |
Claude Fable 5.1 (low with fallback) | 1M | Anthropic | 47 | $2.37 | 59 | 3.05 | 11.55 | |
Claude Sonnet 5.5 (high with fallback) | 1M | Anthropic | 47 | $0.88 | 97 | 14.98 | 20.15 | |
Grok 4.7 (xhigh) | 500k |  SpaceXAI | 46 | $3.74 | 86 | 100.97 | 106.81 | |
Grok 4.7 (high) | 500k | SpaceXAI | 46 | $2.73 | 77 | 55.62 | 62.15 | |
MiMo-V2.6-Pro | 1M |  Xiaomi | 46 | $0.13 | 47 | 4.01 | 57.45 | |
GPT-6 Astra (low) | 1M | OpenAI | 46 | $0.82 | 52 | 2.55 | 12.11 | |
Qwen3.8 Max (0902) | 984k |  Alibaba | 45 | $5.41 | 42 | 2.96 | 62.00 | |
Muse Spark 1.3 (xhigh) | 1M | Meta | 45 | $1.37 | 239 | 28.99 | 39.44 | |
GLM-5.3 (max) | 1M |  Z AI | 45 | $2.01 | 62 | 3.48 | 43.52 | |
Step 5 Preview | 1M |  StepFun | 44 | $1.03 | 90 | 2.92 | 30.60 | |
Kimi K3 (max) | 1.05M | Kimi | 44 | $2.00 | 45 | 3.18 | 59.21 | |
Claude Haiku 5.5 (max) | 1M | Anthropic | 43 | $0.21 | 237 | 318.08 | 320.19 | |
Claude Opus 5.5 (low with fallback) | 1M | Anthropic | 42 | $0.55 | 80 | 12.35 | 18.59 | |
Grok 4.7 (low) | 500k | SpaceXAI | 42 | $1.25 | 65 | 7.25 | 14.96 | |
GPT-6.1 Sol (low) | 1M | OpenAI | 42 | $0.13 | 51 | 2.85 | 12.74 | |
GPT-5.6 Terra (max) | 1M | OpenAI | 42 | $1.40 | 132 | 130.36 | 134.15 | |
GLM-5.3-Flash | 1M | Z AI | 42 | $0.28 | 67 | 2.74 | 40.32 | |
Claude Haiku 5.5 (xhigh) | 1M | Anthropic | 41 | $0.12 | 183 | 72.39 | 75.12 | |
Ling 3.1 Flash | 1M | InclusionAI | 41 | $1.00 | 209 | 1.88 | 13.83 | |
Gemini 3.8 Flash (high) | 1M | Google | 41 | $1.24 | 145 | 24.95 | 28.39 | |
Claude Sonnet 5.5 (medium with fallback) | 1M | Anthropic | 41 | $0.48 | 95 | 1.10 | 6.37 | |
Qwen3.8 2.4T A95B | 262k | Alibaba | 40 | $2.16 | 40 | 3.10 | 65.65 | |
Qwen3.8-Flash-Next | 256k | Alibaba | 40 | $0.37 | 51 | 2.01 | 50.80 | |
Gemini 3.8 Flash (medium) | 1M | Google | 40 | $0.93 | -- | -- | -- | |
DeepSeek V4.1 Flash (max) | 1M |  DeepSeek | 39 | $0.27 | 187 | 0.96 | 14.30 | |
Mistral Large 4 Preview | 524k |  Mistral | 38 | $1.13 | -- | -- | -- | |
GPT-6 Luna (max) | 1M | OpenAI | 38 | $0.07 | 135 | 88.98 | 92.68 | |
GPT-5.6 Terra (xhigh) | 1M | OpenAI | 38 | $0.63 | 109 | 38.82 | 43.40 | |
MiMo-V2.6-Flash | 1M | Xiaomi | 38 | $0.06 | 65 | 3.17 | 41.74 | |
Claude Haiku 5.5 (high) | 1M | Anthropic | 38 | $0.08 | 175 | 24.23 | 27.09 | |
DeepSeek V4 Pro 0813 (max) | 1M | DeepSeek | 36 | $0.67 | 99 | 1.61 | 26.76 | |
Claude Sonnet 5.5 (low with fallback) | 1M | Anthropic | 36 | $0.35 | 101 | 0.68 | 5.65 | |
Agnes 2.5 Pro Beta | 1M |  Sapiens AI | 35* | -- | -- | -- | -- | |
DeepSeek V4 Flash Vision (max) | 1M | DeepSeek | 35 | $0.31 | 187 | 1.02 | 14.35 | |
GPT-6 Luna (xhigh) | 1M | OpenAI | 35 | $0.04 | 126 | 45.19 | 49.16 | |
Claude Haiku 5.5 (medium) | 1M | Anthropic | 34 | $0.05 | 175 | 12.85 | 15.71 | |
GLM-5.3 (low) | 1M | Z AI | 34 | $0.85 | 74 | 2.99 | 36.69 | |
GPT-5.6 Terra (high) | 1M | OpenAI | 34 | $0.34 | 107 | 10.91 | 15.58 | |
JT-4.1 Flash 236B A21B | 262k |  China Mobile | 34 | -- | -- | -- | -- | |
Qwen3.8 27B (xhigh) | 256k | Alibaba | 34 | $1.01 | 45 | 3.86 | 59.26 | |
Motif 3 | 262k |  Motif Technologies | 34* | -- | -- | -- | -- | |
Gemini 3.8 Flash (low) | 1M | Google | 33 | -- | -- | -- | -- | |
GPT-6 Luna (high) | 1M | OpenAI | 33 | $0.03 | 132 | 18.55 | 22.33 | |
GPT-5.3 Codex (xhigh) | 400k | OpenAI | 33* | -- | 111 | 72.02 | 76.53 | |
K2 Horizon 375B A23B | 524k | Institute of Foundation Models | 31 | $0.00 | 118 | 2.64 | 23.83 | |
GPT-5.6 Terra (medium) | 1M | OpenAI | 30 | $0.18 | 106 | 1.81 | 6.51 | |
Kimi K3 (low) | 1.05M | Kimi | 30 | $1.15 | 48 | 3.17 | 54.86 | |
GPT-6 Luna (medium) | 1M | OpenAI | 30 | $0.02 | -- | -- | -- | |
Gemini 3.1 Pro Preview | 1M | Google | 30 | $1.30 | 140 | 27.69 | 31.26 | |
Claude Haiku 5.5 (low) | 1M | Anthropic | 29 | $0.02 | 170 | 9.21 | 12.15 | |
MiniMax-M3 | 1M |  MiniMax | 29 | $0.51 | 107 | 1.16 | 24.54 | |
Nex-N2-Pro | 262k |  Nex AGI | 28* | -- | -- | -- | -- | |
Solar Pro 4 | 512k |  Upstage | 28* | -- | 93 | 2.02 | 28.88 | |
Qwen3.8 27B (medium) | 256k | Alibaba | 28 | $1.13 | 48 | 3.87 | 56.17 | |
GPT-5.6 Terra (low) | 1M | OpenAI | 27 | $0.14 | 103 | 1.80 | 6.64 | |
JT-4.1 Flash 236B A21B (non-reasoning) | 262k | China Mobile | 27* | -- | -- | -- | -- | |
Quasar 438B (max) | 1M |  Multiverse Computing | 27 | $2.02 | 156 | 1.28 | 17.30 | |
Apodex 1.1 | 256k |  Apodex | 26 | $0.46 | -- | -- | -- | |
Qwen3.8 27B (low) | 256k | Alibaba | 26 | $1.05 | 51 | 3.79 | 52.82 | |
GPT-5.5 Instant (June 2026) | 400k | OpenAI | 26 | $0.69 | 158 | 0.91 | 16.71 | |
Kimi K2.7 Code | 256k | Kimi | 26 | $0.54 | 64 | 2.75 | 45.48 | |
Inkling Small | 1M |  Thinking Machines | 26 | $0.09 | 182 | 2.20 | 15.93 | |
K2 Horizon MoVA 36B A4B | 524k | Institute of Foundation Models | 25 | -- | -- | -- | -- | |
Hy3 | 256k |  Tencent | 25 | $0.07 | 85 | 2.81 | 32.26 | |
Qwen3.7 Plus | 1M | Alibaba | 25 | $0.22 | 56 | 2.24 | 47.14 | |
Inkling (xhigh) | 1M | Thinking Machines | 25 | -- | 186 | 1.91 | 15.33 | |
Solar Open2 250B | 1.05M | Upstage | 25* | -- | -- | -- | -- | |
DeepSeek V4.1 Flash (non-reasoning) | 1M | DeepSeek | 25 | $0.15 | 193 | 1.05 | 3.65 | |
Ling-3.0-flash-VL | 262k | InclusionAI | 25 | -- | -- | -- | -- | |
Solar Mini 4 | 1.05M | Upstage | 24 | $0.37 | 80 | 1.86 | 32.99 | |
Nemotron 3 Ultra | 262k | NVIDIA | 23 | $0.60 | 166 | 1.12 | 17.80 | |
Ling-3.0-flash-Fin | 262k | InclusionAI | 23 | -- | 298 | 1.63 | 10.03 | |
Gemini 3.5 Flash-Lite | 1M | Google | 22 | $0.19 | 408 | 8.23 | 9.45 | |
G9v3-39A5B | 131k |  AI9Stars | 22* | -- | -- | -- | -- | |
KAT-Coder-Pro V2 | 256k |  KwaiKAT | 22* | -- | -- | -- | -- | |
GPT-6 Luna (low) | 1M | OpenAI | 22 | $0.0045 | 122 | 2.64 | 6.74 | |
A.X-K2 | 262k |  SK Telecom | 21 | -- | -- | -- | -- | |
Qwen3.5 397B A17B (non-reasoning) | 262k | Alibaba | 21* | -- | 63 | 2.49 | 10.48 | |
GPT-5.6 Terra (non-reasoning) | 1M | OpenAI | 21 | $0.14 | 104 | 0.74 | 5.55 | |
K2 Horizon 7B | 524k | Institute of Foundation Models | 21 | -- | -- | -- | -- | |
Qwen3.5 Omni Plus | 256k | Alibaba | 20* | -- | 89 | 2.11 | 7.71 | |
DeepSeek V4 Pro 0813 (non-reasoning) | 1M | DeepSeek | 20 | $0.36 | 97 | 1.68 | 6.84 | |
o3 | 200k | OpenAI | 20* | -- | 121 | 6.79 | 10.92 | |
Qwen3.8 27B (non-reasoning) | 256k | Alibaba | 20 | $2.49 | 49 | 4.33 | 14.49 | |
K-EXAONE 2.0 | 262k |  LG AI Research | 20* | -- | -- | -- | -- | |
LongCat 2.0 | 1M |  LongCat | 19 | $0.15 | 68 | 2.64 | 39.19 | |
JT-35B-Flash | 256k | China Mobile | 19* | -- | -- | -- | -- | |
GPT-6 Luna (non-reasoning) | 1M | OpenAI | 18 | $0.01 | 112 | 0.86 | 5.32 | |
Qwen3.5 397B A17B | 262k | Alibaba | 18 | $0.47 | 64 | 2.42 | 59.65 | |
Qwen3.6 35B A3B | 262k | Alibaba | 18 | $0.48 | 132 | 2.05 | 46.67 | |
Qwen3.5 122B A10B (non-reasoning) | 262k | Alibaba | 18* | -- | 142 | 2.30 | 5.82 | |
Muse Glimmer (high) | 131k | Meta | 17 | $0.05 | 133 | 0.98 | 19.83 | |
Doubao Seed Code | 256k |  ByteDance Seed | 17* | -- | -- | -- | -- | |
Gemma 4 26B A4B | 256k | Google | 17* | -- | 70 | 1.00 | 36.82 | |
Ring-2.6-1T | 262k | InclusionAI | 17 | $0.29 | 121 | 3.86 | 24.52 | |
K2 Horizon 3.7B | 524k | Institute of Foundation Models | 16 | -- | -- | -- | -- | |
Qwen3.5 122B A10B | 262k | Alibaba | 16 | $0.32 | 127 | 2.32 | 22.05 | |
Qwen3.6 35B A3B (non-reasoning) | 262k | Alibaba | 15* | -- | 142 | 2.03 | 5.55 | |
Gemma 4 31B | 256k | Google | 15 | $0.00 | 35 | 1.10 | 64.16 | |
ERNIE 5.0 Thinking Preview | 128k |  Baidu | 14* | -- | -- | -- | -- | |
Mistral Medium 3.5 | 256k | Mistral | 14 | $0.50 | 167 | 2.21 | 17.18 | |
Gemma 4 12B | 262k | Google | 14* | -- | 111 | 2.51 | 25.08 | |
Nova 2.0 Pro Preview (medium) | 256k |  Amazon | 14* | -- | 127 | 15.68 | 35.37 | |
Gemma 4 31B (non-reasoning) | 256k | Google | 14* | -- | 45 | 2.00 | 13.21 | |
Nova 2.0 Omni (medium) | 1M | Amazon | 14* | -- | -- | -- | -- | |
Apriel-v1.6-15B-Thinker | 128k |  ServiceNow | 13* | -- | -- | -- | -- | |
Nova 2.0 Lite (high) | 1M | Amazon | 13* | -- | 188 | 19.37 | 32.65 | |
Qwen3.5 9B (non-reasoning) | 262k | Alibaba | 13* | -- | 98 | 0.73 | 5.83 | |
EXAONE 4.5 33B | 262k | LG AI Research | 13* | -- | -- | -- | -- | |
Command A+ | 192k | Cohere | 13 | $0.00 | 187 | 0.50 | 13.85 | |
Gemma 4 26B A4B (non-reasoning) | 256k | Google | 13* | -- | 95 | 0.99 | 6.23 | |
Qwen3.5 4B | 262k | Alibaba | 13* | -- | 25 | 0.82 | 99.53 | |
Nemotron 3.5 Lightning | 1M | NVIDIA | 13 | $0.09 | 302 | 0.60 | 8.88 | |
Nemotron 3 Super | 1M | NVIDIA | 13 | $1.64 | 146 | 1.30 | 18.46 | |
Nova 2.0 Pro Preview (low) | 256k | Amazon | 13* | -- | 123 | 10.33 | 30.69 | |
Granite 4.2 30B | 131k |  IBM | 13 | $0.07 | 77 | 0.91 | 33.49 | |
Nova 2.0 Lite (medium) | 1M | Amazon | 12* | -- | 210 | 18.85 | 30.74 | |
Qwen3.5 Omni Flash | 256k | Alibaba | 12* | -- | 226 | 1.81 | 4.02 | |
MiniCPM5-2B | 131k |  OpenBMB | 12 | -- | -- | -- | -- | |
Mercury 2.5 | 260k | Inception | 12 | $0.12 | 762 | 3.74 | 4.40 | |
JT-MINI | 128k | China Mobile | 12* | -- | -- | -- | -- | |
Magistral Medium 1.2 | 128k | Mistral | 12* | -- | -- | -- | -- | |
Nova 2.0 Lite (low) | 1M | Amazon | 12* | -- | 187 | 10.84 | 24.24 | |
HyperNova 60B 2605 (high) | 131k | Multiverse Computing | 12* | -- | -- | -- | -- | |
Nemotron Cascade 2 30B A3B | 1M | NVIDIA | 12* | -- | -- | -- | -- | |
gpt-oss-120b (high) | 131k | OpenAI | 12 | $0.11 | 233 | 0.82 | 11.55 | |
K2 Think V2 | 262k | Institute of Foundation Models | 11* | -- | -- | -- | -- | |
LongCat Flash Lite | 256k | LongCat | 11* | -- | -- | -- | -- | |
HyperCLOVA X SEED Think (32B) | 128k |  Naver | 11* | -- | -- | -- | -- | |
Mistral Small 4 | 256k | Mistral | 11 | $0.02 | 165 | 0.81 | 15.95 | |
Qwen3 Next 80B A3B | 262k | Alibaba | 11* | -- | 157 | 0.73 | 16.61 | |
Qwen3.5 9B | 262k | Alibaba | 11 | $0.21 | 66 | 1.90 | 39.93 | |
Nova 2.0 Omni (low) | 1M | Amazon | 11* | -- | -- | -- | -- | |
Granite 4.2 8B | 131k | IBM | 11 | $0.02 | 59 | 0.75 | 43.20 | |
Ling 3.0 Tiny | 262k | InclusionAI | 11 | $0.00 | 17 | 15.07 | 163.76 | |
Mi:dm K 2.5 Pro | 128k |  Korea Telecom | 11* | -- | -- | -- | -- | |
G9v3-3B | 131k | AI9Stars | 11* | -- | -- | -- | -- | |
Trinity Large Thinking | 512k | Arcee AI | 11 | $0.12 | 352 | 1.12 | 8.23 | |
Qwen3.5 4B (non-reasoning) | 262k | Alibaba | 11* | -- | 20 | 0.85 | 25.63 | |
INTELLECT-3 | 131k |  Prime Intellect | 11* | -- | -- | -- | -- | |
Solar Open 100B | 128k | Upstage | 10* | -- | -- | -- | -- | |
Nemotron 3 Nano Omni 30B A3B | 256k | NVIDIA | 10* | -- | 240 | 0.45 | 10.88 | |
gpt-oss-120b (low) | 131k | OpenAI | 10* | -- | 241 | 0.85 | 11.23 | |
Llama 4 Maverick | 1M | Meta | 10* | -- | 44 | 1.09 | 12.36 | |
Nova 2.0 Pro Preview (non-reasoning) | 256k | Amazon | 10* | -- | 111 | 1.04 | 5.53 | |
gpt-oss-20b (low) | 131k | OpenAI | 10* | -- | 296 | 0.73 | 9.18 | |
North Mini Code | 256k | Cohere | 10 | $0.00 | 101 | 0.42 | 25.29 | |
K2-V2 (high) | 512k | Institute of Foundation Models | 10* | -- | -- | -- | -- | |
Qwen3 Next 80B A3B | 262k | Alibaba | 10* | -- | 161 | 0.83 | 3.93 | |
DiffusionGemma 26B A4B | 256k | Google | 10* | -- | -- | -- | -- | |
Gemma 4 12B (non-reasoning) | 262k | Google | 9* | -- | 113 | 2.52 | 6.92 | |
Qwen3 Coder Next | 256k | Alibaba | 9 | $0.78 | 71 | 1.03 | 8.08 | |
Motif-2-12.7B | 128k | Motif Technologies | 9* | -- | -- | -- | -- | |
Nova Premier | 1M | Amazon | 9* | -- | -- | -- | -- | |
Granite 4.2 3B | 131k | IBM | 9 | $0.01 | 215 | 0.53 | 12.14 | |
K2-V2 (medium) | 512k | Institute of Foundation Models | 9* | -- | -- | -- | -- | |
Mistral Small 4 (non-reasoning) | 256k | Mistral | 9* | -- | 147 | 0.93 | 4.33 | |
Tri-21B-Think | 32k |  Trillion Labs | 9* | -- | -- | -- | -- | |
gpt-oss-20b (high) | 131k | OpenAI | 9 | $0.01 | 219 | 0.76 | 12.18 | |
Gemma 4 E4B | 128k | Google | 9* | -- | 41 | 0.95 | 62.35 | |
Nemotron 3 Nano | 1M | NVIDIA | 9 | $0.02 | 235 | 0.97 | 11.61 | |
MiniCPM5-1B | 128k | OpenBMB | 9* | -- | -- | -- | -- | |
Sarvam 105B (high) | 128k |  Sarvam | 9* | -- | -- | -- | -- | |
Nova 2.0 Lite (non-reasoning) | 1M | Amazon | 9* | -- | 178 | 1.06 | 3.87 | |
MiniCPM5-1B (non-reasoning) | 128k | OpenBMB | 9* | -- | -- | -- | -- | |
Magistral Small 1.2 | 128k | Mistral | 9* | -- | 75 | 1.55 | 34.84 | |
Nanbeige4.1-3B | 256k |  Nanbeige | 8* | -- | -- | -- | -- | |
LFM2.5-2.6B | 128k |  Liquid AI | 8* | -- | -- | -- | -- | |
EXAONE 4.0 32B | 131k | LG AI Research | 8* | -- | -- | -- | -- | |
Nova 2.0 Omni (non-reasoning) | 1M | Amazon | 8* | -- | -- | -- | -- | |
Llama 4 Scout | 10M | Meta | 8* | -- | 68 | 0.87 | 8.27 | |
Hermes 4 70B | 128k |  Nous Research | 8* | -- | -- | -- | -- | |
Falcon-H1R-7B | 256k |  TII UAE | 8* | -- | -- | -- | -- | |
Gemma 4 E2B | 128k | Google | 8* | -- | -- | -- | -- | |
Qwen3 Omni 30B A3B | 65.5k | Alibaba | 8* | -- | 102 | 1.95 | 26.35 | |
Step3 VL 10B | 65.5k | StepFun | 8* | -- | -- | -- | -- | |
Llama 3.3 70B | 128k | Meta | 8* | -- | 93 | 1.75 | 7.14 | |
Llama Nemotron Ultra | 128k | NVIDIA | 8* | -- | -- | -- | -- | |
ERNIE 4.5 300B A47B | 131k | Baidu | 8* | -- | -- | -- | -- | |
Hermes 4 405B | 128k | Nous Research | 7* | -- | 41 | 2.33 | 63.78 | |
NVIDIA Nemotron Nano 12B v2 VL | 128k | NVIDIA | 7* | -- | -- | -- | -- | |
Gemma 4 E4B (non-reasoning) | 128k | Google | 7* | -- | 29 | 0.85 | 18.29 | |
NVIDIA Nemotron Nano 9B V2 | 131k | NVIDIA | 7* | -- | 202 | 0.57 | 12.94 | |
Hermes 4 405B (non-reasoning) | 128k | Nous Research | 7* | -- | 38 | 2.34 | 15.40 | |
K2-V2 (low) | 512k | Institute of Foundation Models | 7* | -- | -- | -- | -- | |
Kimi Linear 48B A3B Instruct | 1M | Kimi | 7* | -- | -- | -- | -- | |
Llama 3.1 405B | 128k | Meta | 7* | -- | -- | -- | -- | |
LFM2.5-8B-A1B | 32.8k | Liquid AI | 7* | -- | -- | -- | -- | |
Ring-flash-2.0 | 128k | InclusionAI | 7* | -- | -- | -- | -- | |
Olmo 3.1 32B Think | 65.5k |  Allen Institute for AI | 7* | -- | -- | -- | -- | |
Command A | 256k | Cohere | 7* | -- | 62 | 1.78 | 9.79 | |
Qwen3.5 2B | 262k | Alibaba | 7* | -- | -- | -- | -- | |
Nemotron 3 Nano (non-reasoning) | 1M | NVIDIA | 7* | -- | 248 | 0.53 | 2.55 | |
NVIDIA Nemotron Nano 9B V2 (non-reasoning) | 131k | NVIDIA | 7* | -- | 172 | 1.07 | 3.98 | |
Hermes 4 70B (non-reasoning) | 128k | Nous Research | 7* | -- | -- | -- | -- | |
Sarvam 30B (high) | 65.5k | Sarvam | 7* | -- | -- | -- | -- | |
Olmo 3.1 32B Instruct | 65.5k | Allen Institute for AI | 6* | -- | -- | -- | -- | |
Gemma 4 E2B (non-reasoning) | 128k | Google | 6* | -- | -- | -- | -- | |
R1 1776 | 128k |  Perplexity | 6* | -- | -- | -- | -- | |
Llama 3.2 90B (Vision) | 128k | Meta | 6* | -- | -- | -- | -- | |
Celeris-1 | 131k | Celeris | 6 | $0.05 | 1,549 | 0.60 | 0.93 | |
Phi-4 Mini | 128k |  Microsoft | 6* | -- | 46 | 0.82 | 11.66 | |
EXAONE 4.0 32B (non-reasoning) | 131k | LG AI Research | 6* | -- | -- | -- | -- | |
Qwen3.5 2B (non-reasoning) | 262k | Alibaba | 6* | -- | -- | -- | -- | |
Qwen3.5 0.8B | 262k | Alibaba | 6* | -- | -- | -- | -- | |
DeepHermes 3 - Mistral 24B (non-reasoning) | 32k | Nous Research | 6* | -- | -- | -- | -- | |
Jamba 1.7 Large | 256k |  AI21 Labs | 6* | -- | -- | -- | -- | |
Granite 4.0 H Small | 128k | IBM | 6* | -- | 14 | 35.61 | 70.72 | |
Ministral 3 14B | 256k | Mistral | 6 | $0.02 | 55 | 1.09 | 10.15 | |
Qwen3 Omni 30B A3B | 65.5k | Alibaba | 6* | -- | 96 | 1.85 | 7.05 | |
LFM2 24B A2B | 32.8k | Liquid AI | 6* | -- | -- | -- | -- | |
Phi-4 | 16k | Microsoft | 6* | -- | 42 | 2.46 | 14.48 | |
Nova Micro | 130k | Amazon | 6* | -- | 313 | 0.86 | 2.46 | |
NVIDIA Nemotron Nano 12B v2 VL (non-reasoning) | 128k | NVIDIA | 6* | -- | 206 | 1.12 | 3.54 | |
Phi-4 Multimodal | 128k | Microsoft | 6* | -- | -- | -- | -- | |
MiniCPM-V 4.6 1.3B | 262k | OpenBMB | 6* | -- | -- | -- | -- | |
Jamba Reasoning 3B | 262k | AI21 Labs | 6* | -- | -- | -- | -- | |
Reka Flash 3 | 128k |  Reka AI | 6* | -- | 92 | 1.40 | 28.53 | |
Olmo 3 7B Think | 65.5k | Allen Institute for AI | 6* | -- | -- | -- | -- | |
Molmo 7B-D | 4.1k | Allen Institute for AI | 6* | -- | -- | -- | -- | |
Ministral 3 8B | 256k | Mistral | 5 | $0.01 | 106 | 0.79 | 5.50 | |
Llama 3.2 11B (Vision) | 128k | Meta | 5* | -- | 22 | 1.72 | 24.75 | |
Qwen3.5 0.8B (non-reasoning) | 262k | Alibaba | 5* | -- | -- | -- | -- | |
Exaone 4.0 1.2B | 64k | LG AI Research | 5* | -- | -- | -- | -- | |
Olmo 3 7B | 65.5k | Allen Institute for AI | 5* | -- | -- | -- | -- | |
Exaone 4.0 1.2B (non-reasoning) | 64k | LG AI Research | 5* | -- | -- | -- | -- | |
LFM2.5-1.2B-Thinking | 32k | Liquid AI | 5* | -- | -- | -- | -- | |
Jamba 1.7 Mini | 258k | AI21 Labs | 5* | -- | -- | -- | -- | |
LFM2.5-1.2B-Instruct | 32k | Liquid AI | 5* | -- | -- | -- | -- | |
Granite 4.0 H 1B | 128k | IBM | 5* | -- | -- | -- | -- | |
Gemma 3 270M | 32k | Google | 5* | -- | -- | -- | -- | |
Apertus 70B Instruct | 65.5k |  Swiss AI Initiative | 5* | -- | -- | -- | -- | |
Granite 4.0 Micro | 128k | IBM | 5* | -- | -- | -- | -- | |
DeepHermes 3 - Llama-3.1 8B (non-reasoning) | 128k | Nous Research | 5* | -- | -- | -- | -- | |
Molmo2-8B | 36.9k | Allen Institute for AI | 5* | -- | -- | -- | -- | |
Ministral 3 3B | 256k | Mistral | 5 | $0.01 | 212 | 0.61 | 2.97 | |
LFM2.5-VL-1.6B | 32k | Liquid AI | 5* | -- | -- | -- | -- | |
Granite 4.0 350M | 32.8k | IBM | 5* | -- | -- | -- | -- | |
Tiny Aya Global | 8.19k | Cohere | 5* | -- | -- | -- | -- | |
Apertus 8B Instruct | 65.5k | Swiss AI Initiative | 5* | -- | -- | -- | -- | |
Granite 4.0 H 350M | 32.8k | IBM | 5* | -- | -- | -- | -- | |
Nemotron 3 Nano 4B | 262k | NVIDIA | 5 | -- | -- | -- | -- | |
K2 Horizon 0.9B | 131k | Institute of Foundation Models | 3 | -- | -- | -- | -- | |
EXAONE 4.5 33B (non-reasoning) | 262k | LG AI Research | -- | -- | -- | -- | -- | |
GPT-6 Sol (Daybreak Blue, max) | 1.05M | OpenAI | -- | -- | -- | -- | -- | |
Gemini 3 Deep Think | 128k | Google | -- | -- | -- | -- | -- | |
GPT-5.5 Pro (xhigh) | 922k | OpenAI | -- | -- | -- | -- | -- | |
Cogito v2.1 | 128k |  Deep Cogito | -- | -- | -- | -- | -- | |
Principais definições
Perguntas frequentes
Atualmente, Claude Opus 5.5 (Max, Default Fallback) ocupa o 1º lugar no ranking de LLMs da Artificial Analysis, com 58 pontos no Artificial Analysis Intelligence Index, entre 127 modelos classificados.
Os melhores modelos segundo o Artificial Analysis Intelligence Index são: 1. Claude Opus 5.5 (Max, Default Fallback) (58), 2. Claude Sonnet 5.5 (Max, Default Fallback) (56), 3. Claude Opus 5.5 (Xhigh, Default Fallback) (56), 4. Muse Wonder Full (Max) (56), 5. Claude Opus 5.5 (High, Default Fallback) (54).
Celeris-1 é o mais rápido, com 1,549.2 tokens por segundo, seguido por Mercury 2.5 (761.8 t/s) e Gemini 3.5 Flash-Lite (407.6 t/s).
K2 Horizon 375B A23B tem o menor custo por tarefa do Artificial Analysis Intelligence Index, de $0.00, seguido por Gemma 4 31B (Reasoning) ($0.00) e Command A+ ($0.00).
MiMo-V2.6-Pro é o modelo de pesos abertos mais bem classificado, com 46 pontos no Artificial Analysis Intelligence Index. O ranking tem 59 modelos de pesos abertos entre 127 modelos no total.
Os melhores modelos de pesos abertos segundo o Artificial Analysis Intelligence Index são: 1. MiMo-V2.6-Pro (46), 2. GLM-5.3 (Max) (45), 3. Kimi K3 (Max) (44).
Claude Opus 5.5 (Max, Default Fallback) lidera entre 117 modelos de raciocínio, com 58 pontos no Artificial Analysis Intelligence Index. Os modelos de raciocínio usam um processo de reflexão prolongado para resolver problemas complexos antes de responder.
O ranking inclui filtros para restringir os resultados por tipo de modelo (com ou sem raciocínio), abertura (pesos abertos ou proprietário) e outros critérios. Você também pode ajustar as opções de prompt para ver como o desempenho varia conforme a extensão da entrada.
Clique no nome de qualquer modelo no ranking para acessar sua página de comparação, com gráficos detalhados de inteligência, preços, velocidade, latência e outras métricas. Você também pode comparar os provedores de API de cada modelo. Ver todos os modelos