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

ModeloPontuação de inteligênciaCusto 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 Telecom21.50----
Apertus 70B InstructSwiss AI Initiative5.10----
Apertus 8B InstructSwiss AI Initiative4.80-0.100.20Tok/s 127
Apriel-v1.5-15B-ThinkerServiceNow13.80-0.000.00-
Apriel-v1.6-15B-ThinkerServiceNow13.40----
Arctic InstructSnowflake5.40----
Beam 1.0Reflection30.30$3190.401.20Tok/s 340
Cogito v2.1 (Reasoning)Deep Cogito-----
Command ACohere7.00-2.5010.00Tok/s 40
Command-R (Mar '24)Cohere5.00----
Command-R+ (Apr '24)Cohere5.30----
DBRX InstructDatabricks5.30----
DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)Nous Research5.10----
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)Nous Research6.10----
DeepSeek Coder V2 Lite InstructDeepSeek5.30----
DeepSeek LLM 67B Chat (V1)DeepSeek5.30----
DeepSeek R1 (Jan '25)DeepSeek11.40$4612.004.00Tok/s 149
DeepSeek R1 0528 (May '25)DeepSeek13.10-1.852.75Tok/s 33
DeepSeek R1 0528 Qwen3 8BDeepSeek8.10----
DeepSeek R1 Distill Llama 70BDeepSeek7.90-0.701.10-
DeepSeek R1 Distill Llama 8BDeepSeek6.50----
DeepSeek R1 Distill Qwen 1.5BDeepSeek5.50----
DeepSeek R1 Distill Qwen 14BDeepSeek7.80----
DeepSeek R1 Distill Qwen 32BDeepSeek8.40----
DeepSeek V3 (Dec '24)DeepSeek8.50$25.40.320.89Tok/s 46
DeepSeek V3 0324DeepSeek9.70$19.90.240.90Tok/s 117
DeepSeek V3.1 (Non-reasoning)DeepSeek13.70-0.561.68Tok/s 97
DeepSeek V3.1 (Reasoning)DeepSeek13.50-0.581.68Tok/s 120
DeepSeek V3.1 Terminus (Non-reasoning)DeepSeek13.90-0.271.00Tok/s 74
DeepSeek V3.1 Terminus (Reasoning)DeepSeek14.80-1.642.75-
DeepSeek V3.2 (Non-reasoning)DeepSeek16.00-0.280.42-
DeepSeek V3.2 (Reasoning)DeepSeek21.50-0.280.42-
DeepSeek V3.2 Exp (Non-reasoning)DeepSeek13.90-0.280.42-
DeepSeek V3.2 Exp (Reasoning)DeepSeek16.60-0.280.42-
DeepSeek V3.2 SpecialeDeepSeek14.50----
DeepSeek V4 Flash 0420 (High)DeepSeek24.40$1210.110.23-
DeepSeek V4 Flash 0420 (Max)DeepSeek24.20$1490.110.23Tok/s 53
DeepSeek V4 Flash 0420 (Non-reasoning)DeepSeek18.90-0.090.19-
DeepSeek V4 Flash 0731 (Max)DeepSeek34.30$2000.140.28Tok/s 150
DeepSeek V4 Pro 0424 (High)DeepSeek30.10-0.430.87Tok/s 101
DeepSeek V4 Pro 0424 (Max)DeepSeek30.40$2770.430.87Tok/s 104
DeepSeek V4 Pro 0424 (Non-reasoning)DeepSeek20.80-0.430.87Tok/s 94
DeepSeek V4 Pro 0813 (Max)DeepSeek36.00$11221.323.96Tok/s 103
DeepSeek V4 Pro 0813 (Non-reasoning)DeepSeek20.40$4511.323.96Tok/s 98
DeepSeek V4.1 Flash (Max)DeepSeek39.50$6720.291.20Tok/s 179
DeepSeek V4.1 Flash (Non-reasoning)DeepSeek24.70$2390.301.20Tok/s 290
DeepSeek V4.1 Flash 1017 (Max)DeepSeek45.10$4450.301.20Tok/s 186
DeepSeek-Coder-V2DeepSeek6.00----
DeepSeek-V2-ChatDeepSeek5.50----
DeepSeek-V2.5DeepSeek6.60----
DeepSeek-V2.5 (Dec '24)DeepSeek6.60----
Devstral 2Mistral8.60----
Devstral Small (Jul '25)Mistral7.60----
Devstral Small (May '25)Mistral8.70----
Devstral Small 2Mistral7.50----
DiffusionGemma 26B A4BGoogle9.50----
ERNIE 4.5 300B A47BBaidu7.50----
Exaone 4.0 1.2B (Non-reasoning)LG AI Research5.20----
Exaone 4.0 1.2B (Reasoning)LG AI Research5.30----
EXAONE 4.0 32B (Non-reasoning)LG AI Research6.30----
EXAONE 4.0 32B (Reasoning)LG AI Research8.20----
EXAONE 4.5 33B (Non-reasoning)LG AI Research-----
EXAONE 4.5 33B (Reasoning)LG AI Research13.20----
Falcon-H1R-7BTII UAE7.80----
G9v3-39A5BAI9Stars21.80----
G9v3-3BAI9Stars10.80----
Gemma 3 1B InstructGoogle4.80-0.000.00-
Gemma 3 270MGoogle5.10----
Gemma 3 4B InstructGoogle4.80-0.000.00-
Gemma 3n E2B InstructGoogle4.80-0.000.00-
Gemma 3n E4B InstructGoogle4.80----
Gemma 3n E4B Instruct Preview (May '25)Google5.80----
Gemma 4 12B (Non-reasoning)Google9.40-0.100.30Tok/s 120
Gemma 4 12B (Reasoning)Google14.20-0.100.30Tok/s 115
Gemma 4 26B A4B (Non-reasoning)Google13.10-0.120.40Tok/s 99
Gemma 4 26B A4B (Reasoning)Google16.70-0.100.34Tok/s 86
Gemma 4 31B (Non-reasoning)Google13.90-0.170.40Tok/s 53
Gemma 4 E2B (Non-reasoning)Google6.50----
Gemma 4 E2B (Reasoning)Google7.80----
Gemma 4 E4B (Non-reasoning)Google7.50-0.020.10Tok/s 49
Gemma 4 E4B (Reasoning)Google8.90$14.70.020.10Tok/s 44
GLM-4.5 (Reasoning)Z AI12.80----
GLM-4.5-AirZ AI11.10-0.170.98Tok/s 79
GLM-4.5V (Non-reasoning)Z AI6.70-0.601.80Tok/s 66
GLM-4.5V (Reasoning)Z AI7.60-0.601.80Tok/s 63
GLM-4.6 (Non-reasoning)Z AI14.90-0.572.20Tok/s 34
GLM-4.6 (Reasoning)Z AI18.50-0.552.20Tok/s 33
GLM-4.6V (Non-reasoning)Z AI8.40-0.300.90Tok/s 82
GLM-4.6V (Reasoning)Z AI11.20-0.300.90Tok/s 86
GLM-4.7 (Non-reasoning)Z AI17.40-0.532.10Tok/s 36
GLM-4.7 (Reasoning)Z AI22.20-0.532.10Tok/s 35
GLM-4.7-Flash (Non-reasoning)Z AI10.60-0.070.40Tok/s 99
GLM-4.7-Flash (Reasoning)Z AI14.90-0.070.40Tok/s 81
GLM-5 (Non-reasoning)Z AI21.80-1.003.20Tok/s 67
GLM-5 (Reasoning)Z AI27.90-1.003.20Tok/s 69
GLM-5.1 (Non-reasoning)Z AI24.20-1.384.40Tok/s 67
GLM-5.1 (Reasoning)Z AI26.10$14871.284.07Tok/s 70
GLM-5.2 (Max)Z AI33.70$20971.404.40Tok/s 93
GLM-5.2 (Non-reasoning)Z AI22.40-1.404.40Tok/s 181
GLM-5.3 (Low)Z AI34.30$10131.404.40Tok/s 89
GLM-5.3 (Max)Z AI44.80$25031.404.40Tok/s 86
GLM-5.3-FlashZ AI41.80$3060.150.50Tok/s 69
gpt-oss-120b (High)OpenAI11.60$1230.150.60Tok/s 216
gpt-oss-120b (Low)OpenAI10.20-0.130.59Tok/s 264
gpt-oss-20b (High)OpenAI9.00$28.80.050.22Tok/s 156
gpt-oss-20b (Low)OpenAI10.00-0.070.30Tok/s 181
Granite 3.3 8B (Non-reasoning)IBM4.90-0.030.25Tok/s 38
Granite 4.0 1BIBM5.00----
Granite 4.0 350MIBM4.80----
Granite 4.0 H 1BIBM5.20----
Granite 4.0 H 350MIBM4.80----
Granite 4.0 H SmallIBM6.00----
Granite 4.0 MicroIBM5.10----
Granite 4.1 30BIBM7.40----
Granite 4.1 3BIBM5.90----
Granite 4.1 8BIBM6.60----
Granite 4.2 30BIBM12.70$1110.160.65Tok/s 71
Granite 4.2 3BIBM9.10$14.90.030.12Tok/s 72
Granite 4.2 8BIBM11.10$53.10.060.25Tok/s 65
Grok 2 (Dec '24)SpaceXAI7.10----
Grok-1SpaceXAI6.30----
Hermes 3 - Llama-3.1 70BNous Research6.00-0.700.70Tok/s 32
Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research7.40-1.003.00Tok/s 43
Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research7.50-1.003.00Tok/s 42
Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research6.70----
Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research7.90----
Hy3Tencent25.30$1500.140.56Tok/s 82
Hy3-preview (Non-reasoning)Tencent17.00-0.060.21-
Hy3-preview (Reasoning)Tencent22.70-0.060.21-
HyperCLOVA X SEED Think (32B)Naver11.40----
HyperNova 60B 2605 (High, Based on gpt-oss-120b)Multiverse Computing11.70----
Inkling (Xhigh)Thinking Machines25.00-1.004.05Tok/s 198
Inkling SmallThinking Machines25.70$2410.301.20Tok/s 226
INTELLECT-3 (Based on GLM-4.5-Air)Prime Intellect10.60----
Jamba 1.5 LargeAI21 Labs6.00-2.008.00-
Jamba 1.5 MiniAI21 Labs5.20-0.200.40-
Jamba 1.6 LargeAI21 Labs6.00----
Jamba 1.6 MiniAI21 Labs5.20----
Jamba 1.7 LargeAI21 Labs6.10----
Jamba 1.7 MiniAI21 Labs5.20----
Jamba Reasoning 3BAI21 Labs5.70----
K-EXAONE (Non-reasoning)LG AI Research11.20----
K-EXAONE (Reasoning)LG AI Research14.40----
K-EXAONE 2.0 0803LG AI Research19.70----
K2 Horizon 0.9BInstitute de Foundation Models3.00----
K2 Horizon 3.7BInstitute de Foundation Models15.60----
K2 Horizon 7BInstitute de Foundation Models20.60----
K2 Horizon MoVA 36B A4BInstitute de Foundation Models25.30----
K2 Think V2Institute de Foundation Models11.50----
K2-V2 (High)Institute de Foundation Models9.90----
K2-V2 (Low)Institute de Foundation Models7.30----
K2-V2 (Medium)Institute de Foundation Models9.00----
Kimi K2Kimi12.70-0.572.30Tok/s 48
Kimi K2 0905Kimi15.30-0.602.50Tok/s 50
Kimi K2 ThinkingKimi22.00-0.602.50Tok/s 121
Kimi K2.5 (Non-reasoning)Kimi19.40-0.603.00Tok/s 53
Kimi K2.5 (Reasoning)Kimi23.50-0.603.00Tok/s 82
Kimi K2.6 (Non-reasoning)Kimi23.60-0.954.00Tok/s 76
Kimi K2.6 (Reasoning)Kimi27.00$15280.954.00Tok/s 79
Kimi K2.7 CodeKimi25.80$9930.954.00Tok/s 62
Kimi K3 (Low)Kimi30.10$11903.0015.00Tok/s 40
Kimi K3 (Max)Kimi43.60$36583.0015.00Tok/s 42
Kimi Linear 48B A3B InstructKimi7.30----
LFM2 1.2BLiquid AI4.80----
LFM2 2.6BLiquid AI5.20----
LFM2 24B A2BLiquid AI5.90----
LFM2 8B A1BLiquid AI4.90----
LFM2.5-1.2B-InstructLiquid AI5.20----
LFM2.5-1.2B-ThinkingLiquid AI5.20----
LFM2.5-2.6BLiquid AI8.40----
LFM2.5-8B-A1BLiquid AI7.20----
LFM2.5-VL-1.6BLiquid AI4.80----
Ling 2.6 FlashInclusionAI9.70----
Ling 3.0 FlashInclusionAI20.10-0.070.22Tok/s 320
Ling 3.1 FlashInclusionAI41.10$10150.300.90Tok/s 213
Ling-1TInclusionAI9.20----
Ling-2.6-1TInclusionAI17.00-0.302.50-
Ling-3.0-flash-FinInclusionAI22.60----
Ling-3.0-flash-VLInclusionAI24.60----
Ling-flash-2.0InclusionAI7.80-0.140.57Tok/s 5
Ling-mini-2.0InclusionAI5.50----
Llama 2 Chat 13BMeta5.30----
Llama 2 Chat 70BMeta5.30----
Llama 2 Chat 7BMeta5.70-0.050.25-
Llama 3 Instruct 70BMeta5.50-0.652.75-
Llama 3 Instruct 8BMeta4.80-0.040.14-
Llama 3.1 Instruct 405BMeta7.30----
Llama 3.1 Instruct 70BMeta6.60-0.560.56Tok/s 40
Llama 3.1 Instruct 8BMeta6.90-0.040.07Tok/s 135
Llama 3.1 Nemotron Instruct 70BNVIDIA6.90----
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)NVIDIA7.30----
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA7.50----
Llama 3.1 Tulu3 405BAllen Institute for AI7.20----
Llama 3.2 Instruct 11B (Vision)Meta5.40-0.340.34Tok/s 24
Llama 3.2 Instruct 1BMeta4.80----
Llama 3.2 Instruct 3BMeta5.70----
Llama 3.2 Instruct 90B (Vision)Meta6.40----
Llama 3.3 Instruct 70BMeta7.70-0.660.71Tok/s 90
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)NVIDIA7.30----
Llama 3.3 Nemotron Super 49B v1 (Reasoning)NVIDIA8.90----
Llama 4 MaverickMeta9.30$44.00.250.92Tok/s 49
Llama 4 ScoutMeta6.50$73.60.180.66Tok/s 115
Llama 65BMeta5.00----
Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA7.40----
Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA9.00----
LongCat 2.0LongCat19.10$5450.752.95Tok/s 76
LongCat Flash LiteLongCat11.50----
Magistral Small 1Mistral8.20----
Magistral Small 1.2Mistral8.60-0.501.50Tok/s 76
MiMo-V2-Flash (Feb 2026)Xiaomi22.40----
MiMo-V2-Flash (Non-reasoning)Xiaomi16.00----
MiMo-V2-Flash (Reasoning)Xiaomi20.80-0.100.30-
MiMo-V2.5Xiaomi21.80$61.90.130.27Tok/s 62
MiMo-V2.5-Pro (Non-reasoning)Xiaomi18.30-0.391.17Tok/s 52
MiMo-V2.5-Pro (Reasoning)Xiaomi26.00$2310.411.02Tok/s 52
MiMo-V2.6-FlashXiaomiMelhor custo-benefício37.90$1100.140.28Tok/s 56
MiMo-V2.6-ProXiaomiMelhor custo-benefício46.30$2070.430.87Tok/s 55
MiniCPM-V 4.6 1.3BOpenBMB5.70----
MiniCPM5-1B (Non-reasoning)OpenBMB8.70----
MiniCPM5-1B (Reasoning)OpenBMB8.80----
MiniCPM5-2BOpenBMB12.50----
MiniMax M1 40kMiniMax10.00----
MiniMax M1 80kMiniMax11.70-0.552.20Tok/s 96
MiniMax-M2MiniMax18.60-0.301.20Tok/s 101
MiniMax-M2.1MiniMax20.90-0.301.20Tok/s 64
MiniMax-M2.5MiniMax22.80-0.301.20Tok/s 61
MiniMax-M2.7MiniMax22.80-0.301.20Tok/s 51
MiniMax-M3MiniMax29.20$5380.301.20Tok/s 98
Ministral 3 14BMistral6.00$37.60.200.20Tok/s 83
Ministral 3 3BMistral4.80$12.20.100.10Tok/s 208
Ministral 3 8BMistral5.50$27.50.150.15Tok/s 111
Mistral 7B InstructMistral5.00-0.150.20-
Mistral Large 2 (Jul '24)Mistral6.80-2.006.00-
Mistral Large 2 (Nov '24)Mistral7.60----
Mistral Large 3Mistral9.30$46.40.501.50Tok/s 82
Mistral Medium 3.5Mistral14.20$12641.507.50Tok/s 159
Mistral Small (Sep '24)Mistral5.80----
Mistral Small 3Mistral6.70-0.050.08Tok/s 44
Mistral Small 3.1Mistral7.10$27.80.080.14Tok/s 45
Mistral Small 3.2Mistral7.00$1220.070.20Tok/s 43
Mistral Small 4 (Non-reasoning)Mistral9.00-0.150.60Tok/s 174
Mistral Small 4 (Reasoning)Mistral11.30$42.50.150.60Tok/s 183
Mixtral 8x22B InstructMistral5.70----
Mixtral 8x7B InstructMistral5.10-0.450.70Tok/s 25
Molmo 7B-DAllen Institute for AI5.60----
Molmo2-8BAllen Institute for AI5.00----
Motif 3Motif Technologies33.60----
Muse Glimmer (High)Meta17.50$1460.301.20Tok/s 105
Muse Spark Open (Xhigh)Meta38.90$11851.254.25Tok/s 151
Nanbeige4.1-3BNanbeige8.40----
Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA10.30-0.401.36Tok/s 234
Nemotron 3 Super 120B A12B (Reasoning)NVIDIA12.80$13190.300.90Tok/s 169
Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA22.90$6970.602.70Tok/s 156
Nemotron 3.5 Bolt 74B-A9BNVIDIA21.40----
Nemotron 3.5 LightningNVIDIA12.90$92.80.060.20Tok/s 291
Nemotron 3.5 Super VLNVIDIA26.50$2860.230.57Tok/s 444
Nemotron Cascade 2 30B A3BNVIDIA11.70----
Nex-N2-Pro (Based on Qwen3.5-397B-A17B)Nex AGI28.20----
NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA6.80-0.050.20Tok/s 275
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA8.90$63.70.050.20Tok/s 235
NVIDIA Nemotron 3 Nano 4BNVIDIA4.80----
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA5.80-0.200.60Tok/s 203
NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA7.50----
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA6.80-0.050.20Tok/s 167
NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA7.40-0.040.16Tok/s 101
OLMo 2 32BAllen Institute for AI6.00----
OLMo 2 7BAllen Institute for AI5.60----
Olmo 3 32B ThinkAllen Institute for AI6.50----
Olmo 3 7B InstructAllen Institute for AI5.20----
Olmo 3 7B ThinkAllen Institute for AI5.60----
Olmo 3.1 32B InstructAllen Institute for AI6.50----
Olmo 3.1 32B ThinkAllen Institute for AI7.10----
OpenChat 3.5 (1210)OpenChat5.30----
Phi-3 Mini Instruct 3.8BMicrosoft5.80----
Phi-4Microsoft5.90-0.130.50Tok/s 39
Phi-4 Mini InstructMicrosoft6.30-0.070.30Tok/s 46
Phi-4 Multimodal InstructMicrosoft5.80-0.080.32-
Pixtral LargeMistral7.10----
Qwen Chat 14BAlibaba5.00----
Qwen Chat 72BAlibaba5.40----
Qwen1.5 Chat 110BAlibaba5.70----
Qwen2 Instruct 72BAlibaba6.30----
Qwen2.5 Coder Instruct 32BAlibaba6.70----
Qwen2.5 Coder Instruct 7BAlibaba5.80----
Qwen2.5 Instruct 32BAlibaba6.90----
Qwen2.5 Instruct 72BAlibaba7.70-0.470.49Tok/s 27
Qwen3 0.6B (Non-reasoning)Alibaba4.80----
Qwen3 0.6B (Reasoning)Alibaba4.80----
Qwen3 1.7B (Non-reasoning)Alibaba4.90----
Qwen3 1.7B (Reasoning)Alibaba5.20----
Qwen3 14B (Non-reasoning)Alibaba6.70-0.120.24Tok/s 82
Qwen3 14B (Reasoning)Alibaba6.40-0.120.24Tok/s 81
Qwen3 235B A22B (Non-reasoning)Alibaba8.30----
Qwen3 235B A22B (Reasoning)Alibaba9.50----
Qwen3 235B A22B 2507 (Reasoning)Alibaba12.70-0.232.30Tok/s 82
Qwen3 235B A22B 2507 InstructAlibaba12.00-0.210.84Tok/s 39
Qwen3 30B A3B (Non-reasoning)Alibaba6.60-0.120.50Tok/s 159
Qwen3 30B A3B (Reasoning)Alibaba7.60-0.140.55Tok/s 163
Qwen3 30B A3B 2507 (Reasoning)Alibaba9.80----
Qwen3 30B A3B 2507 InstructAlibaba7.50-0.100.30Tok/s 200
Qwen3 32B (Non-reasoning)Alibaba7.30-0.150.60Tok/s 60
Qwen3 32B (Reasoning)Alibaba7.20-0.240.54Tok/s 23
Qwen3 4B (Non-reasoning)Alibaba6.60----
Qwen3 4B (Reasoning)Alibaba7.20----
Qwen3 4B 2507 (Reasoning)Alibaba8.80----
Qwen3 4B 2507 InstructAlibaba6.70----
Qwen3 8B (Non-reasoning)Alibaba6.00-0.200.20-
Qwen3 8B (Reasoning)Alibaba5.20----
Qwen3 Coder 30B A3B InstructAlibaba9.60-0.190.77Tok/s 255
Qwen3 Coder 480B A35B InstructAlibaba11.90-0.381.40Tok/s 83
Qwen3 Coder NextAlibaba9.20$4050.311.00Tok/s 91
Qwen3 Next 80B A3B (Reasoning)Alibaba11.20----
Qwen3 Next 80B A3B InstructAlibaba9.60-0.101.10Tok/s 113
Qwen3 Omni 30B A3B (Reasoning)Alibaba7.80-0.250.97Tok/s 102
Qwen3 Omni 30B A3B InstructAlibaba6.00-0.250.97Tok/s 96
Qwen3 VL 235B A22B (Reasoning)Alibaba13.40----
Qwen3 VL 235B A22B InstructAlibaba9.90-0.211.39Tok/s 41
Qwen3 VL 30B A3B (Reasoning)Alibaba9.50-0.500.50-
Qwen3 VL 30B A3B InstructAlibaba7.90-0.350.60Tok/s 29
Qwen3 VL 32B (Reasoning)Alibaba11.90----
Qwen3 VL 32B InstructAlibaba8.40----
Qwen3 VL 4B (Reasoning)Alibaba7.00----
Qwen3 VL 4B InstructAlibaba5.70----
Qwen3 VL 8B (Reasoning)Alibaba8.20----
Qwen3 VL 8B InstructAlibaba7.30----
Qwen3.5 0.8B (Non-reasoning)Alibaba5.40----
Qwen3.5 0.8B (Reasoning)Alibaba6.10----
Qwen3.5 122B A10B (Non-reasoning)Alibaba17.70-0.403.20Tok/s 143
Qwen3.5 122B A10B (Reasoning)Alibaba15.60$6610.403.20Tok/s 128
Qwen3.5 27B (Non-reasoning)Alibaba19.40-0.302.40Tok/s 81
Qwen3.5 27B (Reasoning)Alibaba22.90-0.302.40Tok/s 77
Qwen3.5 2B (Non-reasoning)Alibaba6.20----
Qwen3.5 2B (Reasoning)Alibaba6.90----
Qwen3.5 35B A3B (Non-reasoning)Alibaba15.10-0.252.00Tok/s 167
Qwen3.5 35B A3B (Reasoning)Alibaba19.30-0.252.00Tok/s 145
Qwen3.5 397B A17B (Non-reasoning)Alibaba21.40-0.603.60Tok/s 59
Qwen3.5 397B A17B (Reasoning)Alibaba18.40$9410.603.60Tok/s 59
Qwen3.5 4B (Non-reasoning)Alibaba10.80-0.030.15Tok/s 11
Qwen3.5 4B (Reasoning)Alibaba13.10-0.030.15Tok/s 15
Qwen3.5 9B (Non-reasoning)Alibaba13.30-0.170.25Tok/s 80
Qwen3.5 9B (Reasoning)Alibaba11.20$3290.140.20Tok/s 61
Qwen3.6 27B (Non-reasoning)Alibaba19.80-0.603.60Tok/s 57
Qwen3.6 27B (Reasoning)Alibaba21.40$11450.603.60Tok/s 57
Qwen3.6 35B A3B (Non-reasoning)Alibaba15.20-0.382.25Tok/s 147
Qwen3.6 35B A3B (Reasoning)Alibaba18.20$8960.382.25Tok/s 131
Qwen3.8 2.4T A95BAlibaba39.90$26322.006.00Tok/s 43
Qwen3.8 27B (Low)Alibaba26.20$10600.503.00Tok/s 50
Qwen3.8 27B (Medium)Alibaba27.60$11650.503.00Tok/s 49
Qwen3.8 27B (Non-reasoning)Alibaba20.20$20220.503.00Tok/s 49
Qwen3.8 27B (Xhigh)Alibaba33.70$13360.503.00Tok/s 44
Qwen3.8-Flash-NextAlibaba39.80$3630.150.47Tok/s 52
QwQ 32BAlibaba9.50----
QwQ 32B-PreviewAlibaba7.60----
R1 1776Perplexity6.40----
Reka Flash 3Reka AI5.60-0.200.80Tok/s 88
Ring-1TInclusionAI10.90----
Ring-2.6-1TInclusionAI16.60$5760.302.50Tok/s 121
Ring-flash-2.0InclusionAI7.20----
Sarvam 105B (High)Sarvam8.80-0.040.17Tok/s 192
Sarvam 30B (High)Sarvam6.60----
Sarvam M (Reasoning, Based on Mistral Small 3.1)Sarvam5.30-0.000.00-
Seed-OSS-36B-InstructByteDance Seed12.10-0.210.57Tok/s 40
Solar MiniUpstage6.40-0.150.15-
Solar Open 100B (Reasoning)Upstage10.40----
Solar Open2 250BUpstage24.70----
Step 3.5 FlashStepFun16.60-0.100.30Tok/s 144
Step 3.7 FlashStepFun19.50-0.201.15Tok/s 157
Step 5 PreviewStepFun43.70$11901.002.70Tok/s 229
Step3 VL 10BStepFun7.70----
Tiny Aya GlobalCohere4.80-0.000.00-
Tri-21B-ThinkTrillion Labs9.00----
Tri-21B-think PreviewTrillion Labs9.60----
Trinity Large ThinkingArcee AI10.80$2330.250.80Tok/s 355

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.