Modelos de IA de pesos abertos: benchmarks e preços
Os pesos são os arquivos necessários para executar o modelo por conta própria com software e hardware adequados. Compare modelos com pesos disponíveis para download. Isso não implica licença de código aberto, uso comercial irrestrito ou hospedagem gratuita. Os preços API são do serviço hospedado; confira a licença antes de implantar.
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 |
|---|---|---|---|---|---|
| A.X-K2SK Telecom | 35.00 | - | - | - | - |
| Apertus 70B InstructSwiss AI Initiative | 2.00 | - | 0.82 | 2.92 | - |
| Apertus 8B InstructSwiss AI Initiative | 1.00 | - | 0.10 | 0.20 | - |
| Apriel-v1.5-15B-ThinkerServiceNow | 21.60 | - | 0.00 | 0.00 | - |
| Apriel-v1.6-15B-ThinkerServiceNow | 20.80 | - | 0.00 | 0.00 | - |
| Arctic InstructSnowflake | 3.00 | - | - | - | - |
| Cogito v2.1 (Reasoning)Deep Cogito | - | - | 1.25 | 1.25 | - |
| Command ACohere | 7.50 | - | 2.50 | 10.00 | Tok/s 60 |
| Command-R (Mar '24)Cohere | 1.70 | - | 0.50 | 1.50 | - |
| Command-R+ (Apr '24)Cohere | 2.60 | - | 3.00 | 15.00 | - |
| DBRX InstructDatabricks | 2.60 | - | - | - | - |
| DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)Nous Research | 1.90 | - | - | - | - |
| DeepHermes 3 - Mistral 24B Preview (Non-reasoning)Nous Research | 5.00 | - | - | - | - |
| DeepSeek Coder V2 Lite InstructDeepSeek | 2.70 | - | - | - | - |
| DeepSeek LLM 67B Chat (V1)DeepSeek | 2.60 | - | - | - | - |
| DeepSeek R1 (Jan '25)DeepSeek | 18.60 | $417 | 2.00 | 4.00 | - |
| DeepSeek R1 0528 (May '25)DeepSeek | 20.40 | - | 1.35 | 3.00 | - |
| DeepSeek R1 0528 Qwen3 8BDeepSeek | 10.30 | - | - | - | - |
| DeepSeek R1 Distill Llama 70BDeepSeek | 9.80 | - | 0.70 | 1.10 | Tok/s 25 |
| DeepSeek R1 Distill Llama 8BDeepSeek | 6.20 | - | - | - | - |
| DeepSeek R1 Distill Qwen 1.5BDeepSeek | 3.30 | - | - | - | - |
| DeepSeek R1 Distill Qwen 14BDeepSeek | 9.70 | - | - | - | - |
| DeepSeek R1 Distill Qwen 32BDeepSeek | 11.00 | - | - | - | - |
| DeepSeek V3 (Dec '24)DeepSeek | 14.20 | $20.0 | 0.36 | 0.89 | - |
| DeepSeek V3 0324DeepSeek | 15.20 | $35.2 | 0.27 | 1.12 | - |
| DeepSeek V3.1 (Non-reasoning)DeepSeek | 21.40 | - | 0.56 | 1.68 | - |
| DeepSeek V3.1 (Reasoning)DeepSeek | 21.00 | - | 0.59 | 1.69 | - |
| DeepSeek V3.1 Terminus (Non-reasoning)DeepSeek | 21.70 | - | 0.27 | 1.00 | - |
| DeepSeek V3.1 Terminus (Reasoning)DeepSeek | 31.40 | - | 1.64 | 2.75 | - |
| DeepSeek V3.2 (Non-reasoning)DeepSeek | 25.10 | - | 0.28 | 0.42 | - |
| DeepSeek V3.2 (Reasoning)DeepSeek | 32.80 | - | 0.28 | 0.42 | - |
| DeepSeek V3.2 Exp (Non-reasoning)DeepSeek | 21.70 | - | 0.28 | 0.42 | - |
| DeepSeek V3.2 Exp (Reasoning)DeepSeek | 25.90 | - | 0.28 | 0.42 | - |
| DeepSeek V3.2 SpecialeDeepSeek | 22.60 | - | - | - | - |
| DeepSeek V4 Flash (Non-reasoning)DeepSeek | 29.30 | - | 0.09 | 0.20 | - |
| DeepSeek V4 Flash (Reasoning, High Effort)DeepSeek | 39.00 | $57.0 | 0.13 | 0.28 | - |
| DeepSeek V4 Flash (Reasoning, Max Effort)DeepSeek | 42.10 | $104 | 0.13 | 0.28 | - |
| DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeek | 51.80 | $323 | 0.44 | 1.32 | Tok/s 103 |
| DeepSeek V4 Pro (Non-reasoning)DeepSeek | 31.90 | - | 0.43 | 0.87 | Tok/s 76 |
| DeepSeek V4 Pro (Reasoning, High Effort)DeepSeek | 43.70 | $109 | 0.43 | 0.87 | Tok/s 75 |
| DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek | 45.30 | $176 | 0.43 | 0.87 | Tok/s 74 |
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek | 53.20 | $605 | 1.32 | 3.96 | Tok/s 74 |
| DeepSeek-Coder-V2DeepSeek | 4.70 | - | - | - | - |
| DeepSeek-V2-ChatDeepSeek | 3.30 | - | - | - | - |
| DeepSeek-V2.5DeepSeek | 6.40 | - | - | - | - |
| DeepSeek-V2.5 (Dec '24)DeepSeek | 6.50 | - | - | - | - |
| Devstral Small (Jul '25)Mistral | 9.10 | - | - | - | - |
| Devstral Small (May '25)Mistral | 11.80 | - | - | - | - |
| DiffusionGemma 26B A4BGoogle | 13.50 | - | - | - | - |
| ERNIE 4.5 300B A47BBaidu | 8.90 | - | 0.28 | 1.10 | - |
| Exaone 4.0 1.2B (Non-reasoning)LG AI Research | 2.40 | - | - | - | - |
| Exaone 4.0 1.2B (Reasoning)LG AI Research | 2.50 | - | - | - | - |
| EXAONE 4.0 32B (Non-reasoning)LG AI Research | 5.70 | - | - | - | - |
| EXAONE 4.0 32B (Reasoning)LG AI Research | 10.50 | - | - | - | - |
| EXAONE 4.5 33BLG AI Research | 20.50 | - | - | - | - |
| EXAONE 4.5 33B (Non-reasoning)LG AI Research | - | - | - | - | - |
| Falcon-H1R-7BTII UAE | 9.70 | - | - | - | - |
| G9v3-39A5BAI9Stars | 31.60 | - | 0.00 | 0.00 | - |
| G9v3-3BAI9Stars | 16.20 | - | 0.00 | 0.00 | - |
| Gemma 3 1B InstructGoogle | 1.00 | - | 0.00 | 0.00 | - |
| Gemma 3 270MGoogle | 2.00 | - | - | - | - |
| Gemma 3 4B InstructGoogle | 1.00 | - | 0.00 | 0.00 | - |
| Gemma 3n E2B InstructGoogle | 1.00 | - | 0.00 | 0.00 | - |
| Gemma 3n E4B InstructGoogle | 1.00 | - | 0.06 | 0.12 | Tok/s 55 |
| Gemma 3n E4B Instruct Preview (May '25)Google | 4.20 | - | - | - | - |
| Gemma 4 12B (Non-reasoning)Google | 13.20 | - | 0.10 | 0.30 | Tok/s 114 |
| Gemma 4 12B (Reasoning)Google | 22.20 | - | 0.10 | 0.30 | Tok/s 109 |
| Gemma 4 26B A4B (Non-reasoning)Google | 20.40 | - | 0.13 | 0.40 | Tok/s 75 |
| Gemma 4 26B A4B (Reasoning)Google | 26.10 | $53.9 | 0.12 | 0.37 | - |
| Gemma 4 31B (Non-reasoning)Google | 22.30 | $33.8 | 0.15 | 0.40 | Tok/s 82 |
| Gemma 4 E2B (Non-reasoning)Google | 6.20 | - | - | - | - |
| Gemma 4 E2B (Reasoning)Google | 9.50 | - | - | - | - |
| Gemma 4 E4B (Non-reasoning)Google | 8.70 | - | 0.02 | 0.10 | Tok/s 52 |
| Gemma 4 E4B (Reasoning)Google | 12.20 | - | 0.02 | 0.10 | Tok/s 54 |
| GLM-4.5 (Reasoning)Z AI | 19.70 | - | - | - | - |
| GLM-4.5-AirZ AI | 16.70 | - | 0.17 | 0.98 | Tok/s 77 |
| GLM-4.5V (Non-reasoning)Z AI | 6.80 | - | 0.60 | 1.80 | Tok/s 92 |
| GLM-4.5V (Reasoning)Z AI | 9.00 | - | 0.60 | 1.80 | Tok/s 83 |
| GLM-4.6 (Non-reasoning)Z AI | 23.40 | - | 0.57 | 2.20 | Tok/s 55 |
| GLM-4.6 (Reasoning)Z AI | 29.30 | $314 | 0.55 | 2.20 | Tok/s 50 |
| GLM-4.6V (Non-reasoning)Z AI | 10.90 | - | 0.30 | 0.90 | Tok/s 73 |
| GLM-4.6V (Reasoning)Z AI | 16.90 | - | 0.30 | 0.90 | Tok/s 70 |
| GLM-4.7 (Non-reasoning)Z AI | 27.10 | - | 0.60 | 2.20 | Tok/s 108 |
| GLM-4.7 (Reasoning)Z AI | 34.50 | $607 | 0.60 | 2.20 | Tok/s 107 |
| GLM-4.7-Flash (Non-reasoning)Z AI | 15.60 | - | 0.07 | 0.40 | Tok/s 104 |
| GLM-4.7-Flash (Reasoning)Z AI | 23.30 | - | 0.07 | 0.40 | Tok/s 93 |
| GLM-5 (Non-reasoning)Z AI | 33.20 | - | 1.00 | 3.20 | Tok/s 40 |
| GLM-5 (Reasoning)Z AI | 40.60 | - | 1.00 | 3.20 | Tok/s 46 |
| GLM-5.1 (Non-reasoning)Z AI | 36.30 | - | 1.39 | 4.40 | Tok/s 62 |
| GLM-5.1 (Reasoning)Z AI | 41.00 | $700 | 1.39 | 4.40 | Tok/s 83 |
| GLM-5.2 (max)Z AI | 52.60 | $843 | 1.40 | 4.40 | Tok/s 113 |
| GLM-5.2 (Non-reasoning)Z AI | 34.80 | - | 1.40 | 4.40 | Tok/s 140 |
| gpt-oss-120b (high)OpenAI | 24.10 | $95.0 | 0.15 | 0.60 | Tok/s 161 |
| gpt-oss-120b (low)OpenAI | 14.90 | $24.2 | 0.15 | 0.59 | Tok/s 160 |
| gpt-oss-20b (high)OpenAI | 15.20 | $32.7 | 0.06 | 0.19 | Tok/s 136 |
| gpt-oss-20b (low)OpenAI | 14.40 | - | 0.07 | 0.20 | Tok/s 170 |
| Granite 3.3 8B (Non-reasoning)IBM | 1.30 | - | 0.03 | 0.25 | Tok/s 14 |
| Granite 4.0 1BIBM | 1.60 | - | - | - | - |
| Granite 4.0 350MIBM | 1.00 | - | - | - | - |
| Granite 4.0 H 1BIBM | 2.20 | - | - | - | - |
| Granite 4.0 H 350MIBM | 1.00 | - | - | - | - |
| Granite 4.0 H SmallIBM | 4.90 | - | 0.06 | 0.25 | Tok/s 25 |
| Granite 4.0 MicroIBM | 2.00 | - | - | - | - |
| Granite 4.1 30BIBM | 8.70 | - | - | - | - |
| Granite 4.1 3BIBM | 4.40 | - | - | - | - |
| Granite 4.1 8BIBM | 6.40 | - | 0.05 | 0.10 | Tok/s 115 |
| Grok 2 (Dec '24)SpaceXAI | 7.80 | - | - | - | - |
| Grok-1SpaceXAI | 5.80 | - | - | - | - |
| Hermes 3 - Llama-3.1 70BNous Research | 4.80 | - | 0.70 | 0.70 | Tok/s 34 |
| Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research | 8.60 | - | 1.00 | 3.00 | Tok/s 22 |
| Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research | 8.80 | - | 1.00 | 3.00 | Tok/s 30 |
| Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research | 6.70 | - | 0.13 | 0.40 | Tok/s 56 |
| Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research | 9.90 | - | 0.13 | 0.40 | Tok/s 74 |
| Hy3Tencent | 42.20 | $93.2 | 0.14 | 0.55 | Tok/s 67 |
| Hy3-preview (Non-reasoning)Tencent | 26.60 | - | 0.06 | 0.21 | - |
| Hy3-preview (Reasoning)Tencent | 34.40 | - | 0.06 | 0.21 | - |
| HyperCLOVA X SEED Think (32B)Naver | 17.20 | - | - | - | - |
| HyperNova 60B 2605Multiverse Computing | 18.30 | - | - | - | - |
| Inkling (xhigh)Thinking Machines | 42.30 | $698 | 1.00 | 4.05 | Tok/s 74 |
| Inkling SmallThinking Machines | 41.20 | $193 | 0.30 | 1.20 | Tok/s 67 |
| INTELLECT-3Prime Intellect | 15.70 | - | - | - | - |
| Jamba 1.5 LargeAI21 Labs | 4.80 | - | 2.00 | 8.00 | - |
| Jamba 1.5 MiniAI21 Labs | 2.30 | - | 0.20 | 0.40 | - |
| Jamba 1.6 LargeAI21 Labs | 4.70 | - | - | - | - |
| Jamba 1.6 MiniAI21 Labs | 2.10 | - | - | - | - |
| Jamba 1.7 LargeAI21 Labs | 5.00 | - | - | - | - |
| Jamba 1.7 MiniAI21 Labs | 2.30 | - | - | - | - |
| Jamba Reasoning 3BAI21 Labs | 3.80 | - | - | - | - |
| K-EXAONE (Non-reasoning)LG AI Research | 16.90 | - | - | - | - |
| K-EXAONE (Reasoning)LG AI Research | 22.50 | - | - | - | - |
| K-EXAONE 2.0 0803LG AI Research | 31.00 | - | - | - | - |
| K2 Think V2MBZUAI Institute de Foundation Models | 17.40 | - | - | - | - |
| K2-V2 (high)MBZUAI Institute de Foundation Models | 14.20 | - | - | - | - |
| K2-V2 (low)MBZUAI Institute de Foundation Models | 8.40 | - | - | - | - |
| K2-V2 (medium)MBZUAI Institute de Foundation Models | 12.40 | - | - | - | - |
| Kimi K2Kimi | 19.70 | - | 0.57 | 2.30 | Tok/s 41 |
| Kimi K2 0905Kimi | 24.00 | - | 0.60 | 2.50 | Tok/s 41 |
| Kimi K2 ThinkingKimi | 33.50 | - | 0.60 | 2.50 | Tok/s 121 |
| Kimi K2.5 (Non-reasoning)Kimi | 30.10 | - | 0.60 | 3.00 | Tok/s 45 |
| Kimi K2.5 (Reasoning)Kimi | 36.00 | $304 | 0.60 | 3.00 | Tok/s 43 |
| Kimi K2.6Kimi | 45.10 | $841 | 0.95 | 4.00 | Tok/s 46 |
| Kimi K2.6 (Non-reasoning)Kimi | 35.40 | - | 0.95 | 4.00 | Tok/s 40 |
| Kimi K2.7 CodeKimi | 43.00 | $545 | 0.95 | 4.00 | Tok/s 37 |
| Kimi K3 (low)Kimi | 48.30 | $283 | 3.00 | 15.00 | Tok/s 36 |
| Kimi K3 (max)Kimi | 59.70 | $2425 | 3.00 | 15.00 | Tok/s 38 |
| Kimi Linear 48B A3B InstructKimi | 8.40 | - | - | - | - |
| LFM2 1.2BLiquid AI | 1.00 | - | - | - | - |
| LFM2 2.6BLiquid AI | 2.30 | - | - | - | - |
| LFM2 24B A2BLiquid AI | 4.60 | - | - | - | - |
| LFM2 8B A1BLiquid AI | 1.30 | - | - | - | - |
| LFM2.5-1.2B-InstructLiquid AI | 2.30 | - | - | - | - |
| LFM2.5-1.2B-ThinkingLiquid AI | 2.30 | - | - | - | - |
| LFM2.5-8B-A1BLiquid AI | 8.10 | - | 0.00 | 0.00 | Tok/s 339 |
| LFM2.5-VL-1.6BLiquid AI | 1.00 | - | 0.00 | 0.00 | Tok/s 265 |
| Ling 2.6 FlashInclusionAI | 14.20 | - | 0.10 | 0.30 | Tok/s 91 |
| Ling 3.0 FlashInclusionAI | 37.80 | $72.8 | 0.07 | 0.22 | - |
| Ling-1TInclusionAI | 12.70 | - | - | - | - |
| Ling-2.6-1TInclusionAI | 26.60 | - | 0.30 | 2.50 | - |
| Ling-flash-2.0InclusionAI | 9.60 | - | 0.14 | 0.57 | Tok/s 84 |
| Ling-mini-2.0InclusionAI | 3.40 | - | - | - | - |
| Llama 2 Chat 13BMeta | 2.60 | - | - | - | - |
| Llama 2 Chat 70BMeta | 2.60 | - | - | - | - |
| Llama 2 Chat 7BMeta | 3.90 | - | 0.05 | 0.25 | - |
| Llama 3 Instruct 70BMeta | 3.10 | - | 0.65 | 2.75 | - |
| Llama 3 Instruct 8BMeta | 1.00 | - | 0.04 | 0.14 | - |
| Llama 3.1 Instruct 405BMeta | 8.30 | - | - | - | - |
| Llama 3.1 Instruct 70BMeta | 6.50 | - | 0.56 | 0.56 | Tok/s 55 |
| Llama 3.1 Instruct 8BMeta | 7.40 | - | 0.02 | 0.05 | Tok/s 137 |
| Llama 3.1 Nemotron Instruct 70BNVIDIA | 7.40 | - | 1.20 | 1.20 | Tok/s 109 |
| Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)NVIDIA | 8.40 | - | - | - | - |
| Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA | 8.90 | - | 0.60 | 1.80 | Tok/s 48 |
| Llama 3.1 Tulu3 405BAllen Institute for AI | 8.10 | - | - | - | - |
| Llama 3.2 Instruct 11B (Vision)Meta | 3.00 | - | 0.34 | 0.34 | Tok/s 47 |
| Llama 3.2 Instruct 1BMeta | 1.00 | - | - | - | - |
| Llama 3.2 Instruct 3BMeta | 3.90 | - | - | - | - |
| Llama 3.2 Instruct 90B (Vision)Meta | 6.00 | - | - | - | - |
| Llama 3.3 Instruct 70BMeta | 9.30 | - | 0.66 | 0.72 | Tok/s 88 |
| Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)NVIDIA | 8.30 | - | - | - | - |
| Llama 3.3 Nemotron Super 49B v1 (Reasoning)NVIDIA | 12.20 | - | - | - | - |
| Llama 4 MaverickMeta | 14.50 | $35.9 | 0.27 | 0.85 | Tok/s 113 |
| Llama 4 ScoutMeta | 10.30 | $11.6 | 0.18 | 0.66 | Tok/s 135 |
| Llama 65BMeta | 1.70 | - | - | - | - |
| Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA | 8.50 | - | 0.40 | 0.40 | Tok/s 90 |
| Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA | 12.40 | - | 0.40 | 0.40 | Tok/s 106 |
| LongCat 2.0LongCat | 34.00 | $442 | 0.75 | 2.95 | Tok/s 39 |
| LongCat Flash LiteLongCat | 17.40 | - | - | - | - |
| Magistral Small 1Mistral | 10.60 | - | - | - | - |
| Magistral Small 1.2Mistral | 11.50 | $301 | 0.50 | 1.50 | Tok/s 143 |
| MiMo-V2-Flash (Feb 2026)Xiaomi | 34.00 | - | - | - | - |
| MiMo-V2-Flash (Non-reasoning)Xiaomi | 25.10 | - | - | - | - |
| MiMo-V2-Flash (Reasoning)Xiaomi | 31.90 | - | 0.10 | 0.30 | - |
| MiMo-V2.5Xiaomi | 38.00 | $25.2 | 0.14 | 0.28 | Tok/s 56 |
| MiMo-V2.5-ProXiaomi | 42.90 | $98.9 | 0.43 | 0.87 | Tok/s 59 |
| MiMo-V2.5-Pro (Non-reasoning)Xiaomi | 28.40 | - | 0.43 | 0.87 | Tok/s 56 |
| MiniCPM-V 4.6 1.3BOpenBMB | 3.80 | - | - | - | - |
| MiniCPM5-1B (Non-reasoning)OpenBMB | 11.70 | - | - | - | - |
| MiniCPM5-1B (Reasoning)OpenBMB | 11.90 | - | - | - | - |
| MiniMax M1 40kMiniMax | 14.50 | - | - | - | - |
| MiniMax M1 80kMiniMax | 17.90 | - | 0.55 | 2.20 | - |
| MiniMax-M2MiniMax | 28.90 | - | 0.30 | 1.20 | Tok/s 89 |
| MiniMax-M2.1MiniMax | 32.10 | - | 0.30 | 1.20 | Tok/s 88 |
| MiniMax-M2.5MiniMax | 34.50 | - | 0.30 | 1.20 | Tok/s 94 |
| MiniMax-M2.7MiniMax | 38.90 | $143 | 0.30 | 1.20 | Tok/s 61 |
| MiniMax-M3MiniMax | 45.40 | $205 | 0.30 | 1.20 | Tok/s 90 |
| Ministral 3 14BMistral | 11.20 | $119 | 0.20 | 0.20 | Tok/s 94 |
| Ministral 3 3BMistral | 7.10 | $91.6 | 0.10 | 0.10 | Tok/s 203 |
| Ministral 3 8BMistral | 9.00 | $114 | 0.15 | 0.15 | Tok/s 120 |
| Mistral 7B InstructMistral | 1.70 | - | 0.25 | 0.25 | Tok/s 122 |
| Mistral Large 2 (Jul '24)Mistral | 7.00 | - | 2.00 | 6.00 | - |
| Mistral Large 2 (Nov '24)Mistral | 9.00 | - | - | - | - |
| Mistral Large 3Mistral | 15.90 | $71.1 | 0.50 | 1.50 | Tok/s 48 |
| Mistral Medium 3.5Mistral | 30.40 | $883 | 1.50 | 7.50 | Tok/s 132 |
| Mistral Small (Sep '24)Mistral | 4.30 | - | 0.20 | 0.60 | Tok/s 156 |
| Mistral Small 3Mistral | 6.70 | - | 0.10 | 0.30 | Tok/s 142 |
| Mistral Small 3.1Mistral | 14.90 | $29.8 | 0.10 | 0.30 | Tok/s 149 |
| Mistral Small 3.2Mistral | 10.70 | $129 | 0.10 | 0.30 | Tok/s 151 |
| Mistral Small 4 (Non-reasoning)Mistral | 12.30 | - | 0.15 | 0.60 | Tok/s 137 |
| Mistral Small 4 (Reasoning)Mistral | 19.70 | $87.7 | 0.15 | 0.60 | Tok/s 160 |
| Mixtral 8x22B InstructMistral | 4.00 | - | - | - | - |
| Mixtral 8x7B InstructMistral | 2.00 | - | 0.45 | 0.70 | - |
| Molmo 7B-DAllen Institute for AI | 3.40 | - | - | - | - |
| Molmo2-8BAllen Institute for AI | 1.60 | - | - | - | - |
| Motif 3Motif Technologies | 47.40 | - | - | - | - |
| Muse Glimmer (high)Meta | 35.10 | $105 | 0.32 | 1.35 | Tok/s 111 |
| Nanbeige4.1-3BNanbeige | 11.00 | - | - | - | - |
| Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA | 15.00 | - | 0.07 | 0.30 | Tok/s 323 |
| Nemotron 3 Super 120B A12B (Reasoning)NVIDIA | 25.70 | $254 | 0.20 | 0.80 | Tok/s 129 |
| Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA | 38.30 | $534 | 0.60 | 2.75 | Tok/s 132 |
| Nemotron 3.5 LightningNVIDIA | 23.60 | $71.5 | 0.07 | 0.22 | Tok/s 302 |
| Nemotron Cascade 2 30B A3BNVIDIA | 17.80 | - | - | - | - |
| Nex-N2-ProNex AGI | 41.70 | - | 0.50 | 2.50 | Tok/s 138 |
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA | 7.20 | - | 0.05 | 0.20 | Tok/s 225 |
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA | 14.50 | $39.4 | 0.05 | 0.20 | Tok/s 230 |
| NVIDIA Nemotron 3 Nano 4BNVIDIA | 8.60 | - | - | - | - |
| NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA | 4.20 | - | 0.20 | 0.60 | Tok/s 163 |
| NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA | 8.80 | - | 0.20 | 0.60 | Tok/s 101 |
| NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA | 7.20 | - | 0.05 | 0.20 | Tok/s 168 |
| NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA | 8.70 | - | 0.04 | 0.16 | Tok/s 186 |
| OLMo 2 32BAllen Institute for AI | 4.70 | - | - | - | - |
| OLMo 2 7BAllen Institute for AI | 3.50 | - | - | - | - |
| Olmo 3 32B ThinkAllen Institute for AI | 6.10 | - | - | - | - |
| Olmo 3 7B InstructAllen Institute for AI | 2.40 | - | 0.10 | 0.20 | - |
| Olmo 3 7B ThinkAllen Institute for AI | 3.60 | - | - | - | - |
| Olmo 3.1 32B InstructAllen Institute for AI | 6.20 | - | - | - | - |
| Olmo 3.1 32B ThinkAllen Institute for AI | 7.90 | - | 0.00 | 0.00 | - |
| OpenChat 3.5 (1210)OpenChat | 2.60 | - | - | - | - |
| Phi-3 Mini Instruct 3.8BMicrosoft | 4.30 | - | - | - | - |
| Phi-4Microsoft | 4.60 | - | 0.13 | 0.50 | Tok/s 39 |
| Phi-4 Mini InstructMicrosoft | 5.70 | - | 0.00 | 0.00 | Tok/s 44 |
| Phi-4 Multimodal InstructMicrosoft | 4.20 | - | 0.00 | 0.00 | Tok/s 17 |
| Pixtral LargeMistral | 8.00 | - | - | - | - |
| Qwen Chat 14BAlibaba | 1.70 | - | - | - | - |
| Qwen Chat 72BAlibaba | 3.00 | - | - | - | - |
| Qwen1.5 Chat 110BAlibaba | 3.70 | - | - | - | - |
| Qwen2 Instruct 72BAlibaba | 5.70 | - | - | - | - |
| Qwen2.5 Coder Instruct 32BAlibaba | 6.90 | - | - | - | - |
| Qwen2.5 Coder Instruct 7B Alibaba | 4.10 | - | - | - | - |
| Qwen2.5 Instruct 32BAlibaba | 7.20 | - | - | - | - |
| Qwen2.5 Instruct 72BAlibaba | 9.40 | - | 0.47 | 0.49 | - |
| Qwen3 0.6B (Non-reasoning)Alibaba | 1.00 | - | - | - | - |
| Qwen3 0.6B (Reasoning)Alibaba | 1.00 | - | - | - | - |
| Qwen3 1.7B (Non-reasoning)Alibaba | 1.10 | - | - | - | - |
| Qwen3 1.7B (Reasoning)Alibaba | 2.20 | - | - | - | - |
| Qwen3 14B (Non-reasoning)Alibaba | 6.80 | - | 0.35 | 1.40 | Tok/s 60 |
| Qwen3 14B (Reasoning)Alibaba | 10.40 | - | 0.35 | 4.20 | Tok/s 59 |
| Qwen3 235B A22B (Non-reasoning)Alibaba | 10.80 | - | 0.70 | 2.80 | Tok/s 59 |
| Qwen3 235B A22B (Reasoning)Alibaba | 13.50 | - | 0.70 | 8.40 | Tok/s 61 |
| Qwen3 235B A22B 2507 (Reasoning)Alibaba | 19.90 | $170 | 0.23 | 2.30 | Tok/s 64 |
| Qwen3 235B A22B 2507 InstructAlibaba | 18.40 | - | 0.23 | 0.92 | Tok/s 56 |
| Qwen3 30B A3B (Non-reasoning)Alibaba | 6.60 | - | 0.20 | 0.80 | Tok/s 107 |
| Qwen3 30B A3B (Reasoning)Alibaba | 9.20 | - | 0.20 | 2.40 | Tok/s 103 |
| Qwen3 30B A3B 2507 (Reasoning)Alibaba | 14.60 | $152 | 0.20 | 2.40 | Tok/s 138 |
| Qwen3 30B A3B 2507 InstructAlibaba | 8.90 | - | 0.20 | 0.80 | Tok/s 140 |
| Qwen3 32B (Non-reasoning)Alibaba | 8.50 | - | 0.16 | 0.64 | Tok/s 104 |
| Qwen3 32B (Reasoning)Alibaba | 11.40 | - | 0.16 | 0.64 | Tok/s 101 |
| Qwen3 4B (Non-reasoning)Alibaba | 6.50 | - | - | - | - |
| Qwen3 4B (Reasoning)Alibaba | 8.20 | - | - | - | - |
| Qwen3 4B 2507 (Reasoning)Alibaba | 11.90 | - | - | - | - |
| Qwen3 4B 2507 InstructAlibaba | 6.90 | - | - | - | - |
| Qwen3 8B (Non-reasoning)Alibaba | 4.80 | - | 0.18 | 0.70 | Tok/s 39 |
| Qwen3 8B (Reasoning)Alibaba | 8.30 | - | 0.18 | 2.10 | Tok/s 39 |
| Qwen3 Coder 30B A3B InstructAlibaba | 13.60 | - | 0.45 | 2.25 | Tok/s 91 |
| Qwen3 Coder 480B A35B InstructAlibaba | 18.20 | - | 1.50 | 7.50 | Tok/s 66 |
| Qwen3 Coder NextAlibaba | 21.30 | $250 | 0.35 | 1.20 | Tok/s 128 |
| Qwen3 Next 80B A3B (Reasoning)Alibaba | 16.90 | $84.0 | 0.15 | 1.20 | Tok/s 198 |
| Qwen3 Next 80B A3B InstructAlibaba | 13.80 | - | 0.15 | 1.20 | Tok/s 183 |
| Qwen3 Omni 30B A3B (Reasoning)Alibaba | 9.50 | - | 0.25 | 0.97 | Tok/s 99 |
| Qwen3 Omni 30B A3B InstructAlibaba | 4.80 | - | 0.25 | 0.97 | Tok/s 93 |
| Qwen3 VL 235B A22B (Reasoning)Alibaba | 20.90 | - | 0.40 | 4.00 | Tok/s 57 |
| Qwen3 VL 235B A22B InstructAlibaba | 14.40 | - | 0.40 | 1.60 | Tok/s 47 |
| Qwen3 VL 30B A3B (Reasoning)Alibaba | 13.40 | - | 0.20 | 2.40 | Tok/s 111 |
| Qwen3 VL 30B A3B InstructAlibaba | 9.90 | - | 0.20 | 0.80 | Tok/s 109 |
| Qwen3 VL 32B (Reasoning)Alibaba | 18.10 | - | 0.16 | 0.64 | Tok/s 90 |
| Qwen3 VL 32B InstructAlibaba | 11.00 | - | 0.16 | 0.64 | Tok/s 67 |
| Qwen3 VL 4B (Reasoning)Alibaba | 7.70 | - | - | - | - |
| Qwen3 VL 4B InstructAlibaba | 3.70 | - | - | - | - |
| Qwen3 VL 8B (Reasoning)Alibaba | 10.50 | - | 0.18 | 2.10 | Tok/s 114 |
| Qwen3 VL 8B InstructAlibaba | 8.20 | - | 0.18 | 0.70 | Tok/s 107 |
| Qwen3.5 0.8B (Non-reasoning)Alibaba | 2.90 | - | - | - | - |
| Qwen3.5 0.8B (Reasoning)Alibaba | 5.20 | - | - | - | - |
| Qwen3.5 122B A10B (Non-reasoning)Alibaba | 28.20 | $221 | 0.40 | 3.20 | Tok/s 143 |
| Qwen3.5 122B A10B (Reasoning)Alibaba | 32.80 | $444 | 0.40 | 3.20 | Tok/s 130 |
| Qwen3.5 27B (Non-reasoning)Alibaba | 30.00 | - | 0.30 | 2.40 | Tok/s 82 |
| Qwen3.5 27B (Reasoning)Alibaba | 34.60 | - | 0.30 | 2.40 | Tok/s 77 |
| Qwen3.5 2B (Non-reasoning)Alibaba | 5.30 | - | - | - | - |
| Qwen3.5 2B (Reasoning)Alibaba | 7.40 | - | - | - | - |
| Qwen3.5 35B A3B (Non-reasoning)Alibaba | 24.30 | $228 | 0.25 | 2.00 | Tok/s 169 |
| Qwen3.5 35B A3B (Reasoning)Alibaba | 29.90 | - | 0.25 | 2.00 | Tok/s 151 |
| Qwen3.5 397B A17B (Non-reasoning)Alibaba | 32.70 | - | 0.60 | 3.60 | Tok/s 83 |
| Qwen3.5 397B A17B (Reasoning)Alibaba | 34.30 | $527 | 0.60 | 3.60 | Tok/s 88 |
| Qwen3.5 4B (Non-reasoning)Alibaba | 16.10 | - | 0.03 | 0.15 | Tok/s 28 |
| Qwen3.5 4B (Reasoning)Alibaba | 20.40 | - | 0.03 | 0.15 | Tok/s 30 |
| Qwen3.5 9B (Non-reasoning)Alibaba | 20.60 | - | 0.17 | 0.25 | Tok/s 87 |
| Qwen3.5 9B (Reasoning)Alibaba | 21.80 | $240 | 0.14 | 0.20 | Tok/s 81 |
| Qwen3.6 27B (Non-reasoning)Alibaba | 31.30 | $359 | 0.60 | 3.60 | Tok/s 55 |
| Qwen3.6 27B (Reasoning)Alibaba | 37.70 | $667 | 0.60 | 3.60 | Tok/s 55 |
| Qwen3.6 35B A3B (Non-reasoning)Alibaba | 24.60 | $530 | 0.38 | 2.25 | Tok/s 138 |
| Qwen3.6 35B A3B (Reasoning)Alibaba | 32.10 | $505 | 0.38 | 2.25 | Tok/s 118 |
| Qwen3.8 2.4T A95BAlibaba | 57.70 | $1672 | 2.00 | 6.00 | Tok/s 46 |
| Qwen3.8 27BAlibaba | 52.00 | - | 0.45 | 3.20 | - |
| QwQ 32BAlibaba | 13.40 | - | 0.66 | 1.00 | - |
| QwQ 32B-PreviewAlibaba | 9.10 | - | - | - | - |
| R1 1776Perplexity | 6.00 | - | - | - | - |
| Reka Flash 3Reka AI | 3.70 | - | 0.20 | 0.80 | - |
| Ring-1TInclusionAI | 16.30 | - | - | - | - |
| Ring-2.6-1TInclusionAI | 31.70 | $455 | 0.30 | 2.50 | - |
| Ring-flash-2.0InclusionAI | 8.00 | - | 0.14 | 0.57 | - |
| Sarvam 105B (high)Sarvam | 11.90 | - | 0.04 | 0.17 | - |
| Sarvam 30B (high)Sarvam | 6.40 | - | 0.03 | 0.11 | - |
| Sarvam M (Reasoning)Sarvam | 2.60 | - | 0.00 | 0.00 | - |
| Seed-OSS-36B-InstructByteDance Seed | 18.50 | - | 0.21 | 0.57 | Tok/s 30 |
| Solar MiniUpstage | 6.00 | - | 0.15 | 0.15 | - |
| Solar Open 100B (Reasoning)Upstage | 15.20 | - | - | - | - |
| Solar Open2 250BUpstage | 37.40 | - | - | - | - |
| Step 3.5 FlashStepFun | 26.00 | - | 0.10 | 0.30 | Tok/s 224 |
| Step 3.7 FlashStepFun | 30.90 | $320 | 0.20 | 1.15 | Tok/s 117 |
| Step3 VL 10BStepFun | 9.30 | - | - | - | - |
| Tiny Aya GlobalCohere | 1.00 | - | 0.00 | 0.00 | - |
| Tri-21B-ThinkTrillion Labs | 12.30 | - | - | - | - |
| Tri-21B-think PreviewTrillion Labs | 13.60 | - | - | - | - |
| Trinity Large ThinkingArcee AI | 18.70 | $255 | 0.23 | 0.88 | Tok/s 197 |
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.