Model AI tercepat: bandingkan kecepatan output
Model diurutkan menurut token output per detik. Kecepatan output berbeda dari waktu hingga jawaban pertama dan waktu respons total, terutama pada model penalaran. Model tanpa pengukuran dikecualikan.
Sebaiknya pilih yang mana?
Satu benchmark tidak mencakup semua kebutuhan. Uji pertanyaan Anda sendiri dan bandingkan akurasi, waktu respons, dukungan input/output, serta tagihan sebenarnya.
Model AI
| Model | Skor kecerdasan | Biaya benchmark (USD) | Harga input / 1 juta token (USD) | Harga output / 1 juta token (USD) | Kecepatan output |
|---|---|---|---|---|---|
| Celeris-1Celeris | 12.40 | $157 | 0.20 | 0.70 | 1596 tok/dtk |
| Mercury 2Inception | 21.90 | $97.5 | 0.25 | 0.75 | 835 tok/dtk |
| LFM2.5-8B-A1BLiquid AI | 8.10 | - | 0.00 | 0.00 | 339 tok/dtk |
| Gemini 3.5 Flash-LiteGoogle | 37.40 | $153 | 0.30 | 2.50 | 332 tok/dtk |
| Gemini 3.7 Flash (high)GoogleModel dengan nilai terbaik | 56.00 | $485 | 0.75 | 3.75 | 323 tok/dtk |
| Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA | 15.00 | - | 0.07 | 0.30 | 323 tok/dtk |
| Gemini 3.7 Flash (medium)GoogleModel dengan nilai terbaik | 53.40 | $278 | 0.75 | 3.75 | 317 tok/dtk |
| Gemini 2.5 Flash-Lite (Reasoning)Google | 11.40 | - | 0.10 | 0.40 | 312 tok/dtk |
| Gemini 3.7 Flash (low)GoogleModel dengan nilai terbaik | 50.90 | $165 | 0.75 | 3.75 | 303 tok/dtk |
| Gemini 3.1 Flash-LiteGoogle | 25.60 | $93.8 | 0.25 | 1.50 | 303 tok/dtk |
| Nemotron 3.5 LightningNVIDIA | 23.60 | $71.5 | 0.07 | 0.22 | 302 tok/dtk |
| Nova MicroAmazon | 4.40 | - | 0.04 | 0.14 | 282 tok/dtk |
| LFM2.5-VL-1.6BLiquid AI | 1.00 | - | 0.00 | 0.00 | 265 tok/dtk |
| Qwen3.5 Omni FlashAlibaba | 19.20 | - | 0.10 | 0.80 | 238 tok/dtk |
| Gemini 2.5 Flash-Lite (Non-reasoning)Google | 6.70 | - | 0.10 | 0.40 | 232 tok/dtk |
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA | 14.50 | $39.4 | 0.05 | 0.20 | 230 tok/dtk |
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA | 7.20 | - | 0.05 | 0.20 | 225 tok/dtk |
| Gemini 2.5 Flash (Reasoning)Google | 20.30 | - | 0.30 | 2.50 | 225 tok/dtk |
| Step 3.5 FlashStepFun | 26.00 | - | 0.10 | 0.30 | 224 tok/dtk |
| o3-miniOpenAI | 19.20 | - | 1.10 | 4.40 | 221 tok/dtk |
| o3-mini (high)OpenAI | 15.70 | - | 1.10 | 4.40 | 220 tok/dtk |
| Step 3.5 Flash 2603StepFun | 26.50 | - | 0.10 | 0.30 | 214 tok/dtk |
| Ministral 3 3BMistral | 7.10 | $91.6 | 0.10 | 0.10 | 203 tok/dtk |
| Qwen3.7 MaxAlibaba | 46.70 | $1064 | 2.50 | 7.50 | 201 tok/dtk |
| Gemini 2.5 Flash (Non-reasoning)Google | 14.20 | - | 0.30 | 2.50 | 200 tok/dtk |
| Muse Spark 1.1 (xhigh)Meta | 53.20 | $547 | 1.25 | 4.25 | 200 tok/dtk |
| Gemini 3.6 Flash (high)Google | 51.60 | $412 | 0.75 | 3.75 | 199 tok/dtk |
| Qwen3 Next 80B A3B (Reasoning)Alibaba | 16.90 | $84.0 | 0.15 | 1.20 | 198 tok/dtk |
| Trinity Large ThinkingArcee AI | 18.70 | $255 | 0.23 | 0.88 | 197 tok/dtk |
| NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA | 8.70 | - | 0.04 | 0.16 | 186 tok/dtk |
| GPT-5.4 nano (xhigh)OpenAI | 39.70 | $277 | 0.20 | 1.25 | 185 tok/dtk |
| Qwen3 Next 80B A3B InstructAlibaba | 13.80 | - | 0.15 | 1.20 | 183 tok/dtk |
| Gemini 3.5 Flash (medium)Google | 46.70 | - | 1.50 | 9.00 | 180 tok/dtk |
| GPT-5.4 nano (medium)OpenAI | 30.80 | - | 0.20 | 1.25 | 177 tok/dtk |
| Gemini 3 Flash Preview (Non-reasoning)Google | 27.90 | - | 0.50 | 3.00 | 171 tok/dtk |
| Gemini 3.5 Flash (high)Google | 52.00 | $1042 | 1.50 | 9.00 | 171 tok/dtk |
| gpt-oss-20b (low)OpenAI | 14.40 | - | 0.07 | 0.20 | 170 tok/dtk |
| Nova 2.0 Lite (medium)Amazon | 19.20 | - | 0.30 | 2.50 | 170 tok/dtk |
| Qwen3.5 35B A3B (Non-reasoning)Alibaba | 24.30 | $228 | 0.25 | 2.00 | 169 tok/dtk |
| GPT-5.4 nano (Non-Reasoning)OpenAI | 17.80 | - | 0.20 | 1.25 | 168 tok/dtk |
| NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA | 7.20 | - | 0.05 | 0.20 | 168 tok/dtk |
| GPT-5 nano (high)OpenAI | 20.10 | - | 0.05 | 0.40 | 167 tok/dtk |
| Nova 2.0 Lite (low)Amazon | 18.00 | - | 0.30 | 2.50 | 164 tok/dtk |
| GPT-5.4 mini (xhigh)OpenAI | 40.90 | $1096 | 0.75 | 4.50 | 163 tok/dtk |
| NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA | 4.20 | - | 0.20 | 0.60 | 163 tok/dtk |
| GPT-5.4 mini (Non-Reasoning)OpenAI | 16.80 | - | 0.75 | 4.50 | 162 tok/dtk |
| GPT-5 nano (minimal)OpenAI | 7.80 | - | 0.05 | 0.40 | 161 tok/dtk |
| Gemini 3 Flash Preview (Reasoning)Google | 38.70 | - | 0.50 | 3.00 | 161 tok/dtk |
| gpt-oss-120b (high)OpenAI | 24.10 | $95.0 | 0.15 | 0.60 | 161 tok/dtk |
| gpt-oss-120b (low)OpenAI | 14.90 | $24.2 | 0.15 | 0.59 | 160 tok/dtk |
| Mistral Small 4 (Reasoning)Mistral | 19.70 | $87.7 | 0.15 | 0.60 | 160 tok/dtk |
| GPT-5.4 mini (medium)OpenAI | 30.50 | - | 0.75 | 4.50 | 160 tok/dtk |
| GPT-5 nano (medium)OpenAI | 19.20 | - | 0.05 | 0.40 | 159 tok/dtk |
| GPT-5.6 Luna (max)OpenAIModel dengan nilai terbaik | 52.30 | $172 | 0.20 | 1.20 | 159 tok/dtk |
| GPT-5.6 Luna (xhigh)OpenAIModel dengan nilai terbaik | 50.10 | $95.1 | 0.20 | 1.20 | 158 tok/dtk |
| Mistral Small (Sep '24)Mistral | 4.30 | - | 0.20 | 0.60 | 156 tok/dtk |
| Nova LiteAmazon | 6.70 | - | 0.06 | 0.24 | 155 tok/dtk |
| Gemini 3.5 Flash (minimal)Google | 35.80 | - | 1.50 | 9.00 | 154 tok/dtk |
| Nova 2.0 Lite (Non-reasoning)Amazon | 11.80 | - | 0.30 | 2.50 | 153 tok/dtk |
| Nova 2.0 Lite (high)Amazon | 20.80 | - | 0.30 | 2.50 | 152 tok/dtk |
| Solar Pro 3Upstage | 14.50 | $158 | 0.15 | 0.60 | 152 tok/dtk |
| Qwen3.5 35B A3B (Reasoning)Alibaba | 29.90 | - | 0.25 | 2.00 | 151 tok/dtk |
| Mistral Small 3.2Mistral | 10.70 | $129 | 0.10 | 0.30 | 151 tok/dtk |
| Mistral Small (Feb '24)Mistral | 3.20 | - | 0.15 | 0.60 | 150 tok/dtk |
| Mistral Small 3.1Mistral | 14.90 | $29.8 | 0.10 | 0.30 | 149 tok/dtk |
| GPT-5.6 Luna (Non-reasoning)OpenAIModel dengan nilai terbaik | 26.80 | $10.2 | 0.20 | 1.20 | 145 tok/dtk |
| GPT-5.6 Luna (high)OpenAIModel dengan nilai terbaik | 47.00 | $55.0 | 0.20 | 1.20 | 144 tok/dtk |
| GPT-5.6 Luna (medium)OpenAIModel dengan nilai terbaik | 38.90 | $21.1 | 0.20 | 1.20 | 144 tok/dtk |
| Magistral Small 1.2Mistral | 11.50 | $301 | 0.50 | 1.50 | 143 tok/dtk |
| Qwen3.5 122B A10B (Non-reasoning)Alibaba | 28.20 | $221 | 0.40 | 3.20 | 143 tok/dtk |
| o4-mini (high)OpenAI | 26.10 | - | 1.10 | 4.40 | 143 tok/dtk |
| Mistral Small 3Mistral | 6.70 | - | 0.10 | 0.30 | 142 tok/dtk |
| GPT-4.1OpenAI | 19.60 | - | 2.00 | 8.00 | 142 tok/dtk |
| Qwen3 30B A3B 2507 InstructAlibaba | 8.90 | - | 0.20 | 0.80 | 140 tok/dtk |
| GLM-5.2 (Non-reasoning)Z AI | 34.80 | - | 1.40 | 4.40 | 140 tok/dtk |
| Nex-N2-ProNex AGI | 41.70 | - | 0.50 | 2.50 | 138 tok/dtk |
| Qwen3.6 35B A3B (Non-reasoning)Alibaba | 24.60 | $530 | 0.38 | 2.25 | 138 tok/dtk |
| Qwen3 30B A3B 2507 (Reasoning)Alibaba | 14.60 | $152 | 0.20 | 2.40 | 138 tok/dtk |
| GPT-5.6 Luna (low)OpenAIModel dengan nilai terbaik | 33.90 | $13.7 | 0.20 | 1.20 | 138 tok/dtk |
| Mistral Small 4 (Non-reasoning)Mistral | 12.30 | - | 0.15 | 0.60 | 137 tok/dtk |
| Llama 3.1 Instruct 8BMeta | 7.40 | - | 0.02 | 0.05 | 137 tok/dtk |
| gpt-oss-20b (high)OpenAI | 15.20 | $32.7 | 0.06 | 0.19 | 136 tok/dtk |
| Mistral MediumMistral | 3.20 | - | 1.50 | 7.50 | 135 tok/dtk |
| Llama 4 ScoutMeta | 10.30 | $11.6 | 0.18 | 0.66 | 135 tok/dtk |
| Gemini 2.5 ProGoogle | 25.90 | $611 | 1.25 | 10.00 | 133 tok/dtk |
| Agnes 2.5 Pro AlphaSapiens AI | 39.70 | - | 0.45 | 0.90 | 132 tok/dtk |
| Mistral Medium 3.5Mistral | 30.40 | $883 | 1.50 | 7.50 | 132 tok/dtk |
| Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA | 38.30 | $534 | 0.60 | 2.75 | 132 tok/dtk |
| GPT-4o (Nov '24)OpenAI | 11.10 | - | 2.50 | 10.00 | 131 tok/dtk |
| GPT-5.4 (xhigh)OpenAI | 53.10 | $2183 | 2.50 | 15.00 | 131 tok/dtk |
| Qwen3.5 122B A10B (Reasoning)Alibaba | 32.80 | $444 | 0.40 | 3.20 | 130 tok/dtk |
| Nemotron 3 Super 120B A12B (Reasoning)NVIDIA | 25.70 | $254 | 0.20 | 0.80 | 129 tok/dtk |
| Qwen3 Coder NextAlibaba | 21.30 | $250 | 0.35 | 1.20 | 128 tok/dtk |
| Magistral Medium 1.2Mistral | 18.00 | $920 | 2.00 | 5.00 | 127 tok/dtk |
| GPT-5.3 Codex (xhigh)OpenAI | 45.50 | - | 1.75 | 14.00 | 125 tok/dtk |
| GPT-4.1 nanoOpenAI | 9.60 | $36.7 | 0.10 | 0.40 | 125 tok/dtk |
| Mistral 7B InstructMistral | 1.70 | - | 0.25 | 0.25 | 122 tok/dtk |
| Kimi K2 ThinkingKimi | 33.50 | - | 0.60 | 2.50 | 121 tok/dtk |
| Ministral 3 8BMistral | 9.00 | $114 | 0.15 | 0.15 | 120 tok/dtk |
| GPT-5.6 Terra (max)OpenAI | 56.60 | $1390 | 2.00 | 12.00 | 119 tok/dtk |
| Qwen3.6 35B A3B (Reasoning)Alibaba | 32.10 | $505 | 0.38 | 2.25 | 118 tok/dtk |
| Grok 4.3 (high)SpaceXAI | 37.90 | $288 | 1.25 | 2.50 | 118 tok/dtk |
| Step 3.7 FlashStepFun | 30.90 | $320 | 0.20 | 1.15 | 117 tok/dtk |
| GPT-5.5 Instant (June 2026)OpenAI | 29.20 | $423 | 5.00 | 30.00 | 117 tok/dtk |
| Granite 4.1 8BIBM | 6.40 | - | 0.05 | 0.10 | 115 tok/dtk |
| Nova 2.0 Pro Preview (medium)Amazon | 22.10 | - | 1.25 | 10.00 | 115 tok/dtk |
| Nova 2.0 Pro Preview (low)Amazon | 19.80 | - | 1.25 | 10.00 | 115 tok/dtk |
| Gemma 4 12B (Non-reasoning)Google | 13.20 | - | 0.10 | 0.30 | 114 tok/dtk |
| Qwen3 VL 8B (Reasoning)Alibaba | 10.50 | - | 0.18 | 2.10 | 114 tok/dtk |
| Llama 4 MaverickMeta | 14.50 | $35.9 | 0.27 | 0.85 | 113 tok/dtk |
| Grok 4.3 (medium)SpaceXAI | 36.90 | - | 1.25 | 2.50 | 113 tok/dtk |
| GLM-5.2 (max)Z AI | 52.60 | $843 | 1.40 | 4.40 | 113 tok/dtk |
| o3OpenAI | 31.10 | - | 2.00 | 8.00 | 112 tok/dtk |
| GPT-5.1 (high)OpenAI | 37.50 | $782 | 1.25 | 10.00 | 112 tok/dtk |
| Qwen3 VL 30B A3B (Reasoning)Alibaba | 13.40 | - | 0.20 | 2.40 | 111 tok/dtk |
| Muse Glimmer (high)Meta | 35.10 | $105 | 0.32 | 1.35 | 111 tok/dtk |
| Gemma 4 12B (Reasoning)Google | 22.20 | - | 0.10 | 0.30 | 109 tok/dtk |
| Qwen3 VL 30B A3B InstructAlibaba | 9.90 | - | 0.20 | 0.80 | 109 tok/dtk |
| Llama 3.1 Nemotron Instruct 70BNVIDIA | 7.40 | - | 1.20 | 1.20 | 109 tok/dtk |
| GLM-4.7 (Non-reasoning)Z AI | 27.10 | - | 0.60 | 2.20 | 108 tok/dtk |
| Gemini 3.1 Pro PreviewGoogle | 47.70 | $812 | 2.00 | 12.00 | 108 tok/dtk |
| Qwen2.5 TurboAlibaba | 6.00 | - | 0.05 | 0.20 | 108 tok/dtk |
| Qwen3 VL 8B InstructAlibaba | 8.20 | - | 0.18 | 0.70 | 107 tok/dtk |
| KAT Coder Pro V2KwaiKAT | 33.70 | - | 0.30 | 1.20 | 107 tok/dtk |
| Qwen3 30B A3B (Non-reasoning)Alibaba | 6.60 | - | 0.20 | 0.80 | 107 tok/dtk |
| GLM-4.7 (Reasoning)Z AI | 34.50 | $607 | 0.60 | 2.20 | 107 tok/dtk |
| Mistral Medium 3.1Mistral | 14.70 | $134 | 0.40 | 2.00 | 106 tok/dtk |
| Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA | 12.40 | - | 0.40 | 0.40 | 106 tok/dtk |
| Qwen3 32B (Non-reasoning)Alibaba | 8.50 | - | 0.16 | 0.64 | 104 tok/dtk |
| GPT-5.6 Terra (high)OpenAI | 50.10 | $395 | 2.00 | 12.00 | 104 tok/dtk |
| GLM-4.7-Flash (Non-reasoning)Z AI | 15.60 | - | 0.07 | 0.40 | 104 tok/dtk |
| DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeek | 51.80 | $323 | 0.44 | 1.32 | 103 tok/dtk |
| Qwen3 30B A3B (Reasoning)Alibaba | 9.20 | - | 0.20 | 2.40 | 103 tok/dtk |
| GPT-5.6 Terra (xhigh)OpenAI | 52.80 | $590 | 2.00 | 12.00 | 102 tok/dtk |
| GPT-4.1 miniOpenAI | 14.80 | $64.2 | 0.40 | 1.60 | 102 tok/dtk |
| Qwen3 32B (Reasoning)Alibaba | 11.40 | - | 0.16 | 0.64 | 101 tok/dtk |
| GPT-4o miniOpenAI | 6.70 | - | 0.15 | 0.60 | 101 tok/dtk |
| NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA | 8.80 | - | 0.20 | 0.60 | 101 tok/dtk |
| Grok 4.3 (low)SpaceXAI | 36.30 | - | 1.25 | 2.50 | 100 tok/dtk |
| Qwen3 Omni 30B A3B (Reasoning)Alibaba | 9.50 | - | 0.25 | 0.97 | 99 tok/dtk |
| Grok 4.20 0309 v2 (Reasoning)SpaceXAI | 38.00 | - | 1.25 | 2.50 | 99 tok/dtk |
| GPT-5.6 Terra (Non-reasoning)OpenAI | 34.60 | $98.5 | 2.00 | 12.00 | 98 tok/dtk |
| Grok 4.3 (Non-reasoning)SpaceXAI | 25.00 | $201 | 1.25 | 2.50 | 98 tok/dtk |
| GPT-5.6 Terra (medium)OpenAI | 46.80 | $192 | 2.00 | 12.00 | 98 tok/dtk |
| Nova 2.0 Pro Preview (Non-reasoning)Amazon | 14.40 | - | 1.25 | 10.00 | 98 tok/dtk |
| GPT-5.1 (Non-reasoning)OpenAI | 20.70 | - | 1.25 | 10.00 | 96 tok/dtk |
| MiniMax-M2.5MiniMax | 34.50 | - | 0.30 | 1.20 | 94 tok/dtk |
| GPT-5.4 (low)OpenAI | 40.20 | - | 2.50 | 15.00 | 94 tok/dtk |
| GPT-5 mini (minimal)OpenAI | 14.30 | - | 0.25 | 2.00 | 94 tok/dtk |
| GPT-5.6 Terra (low)OpenAI | 41.30 | $130 | 2.00 | 12.00 | 94 tok/dtk |
| Ministral 3 14BMistral | 11.20 | $119 | 0.20 | 0.20 | 94 tok/dtk |
| GLM-4.7-Flash (Reasoning)Z AI | 23.30 | - | 0.07 | 0.40 | 93 tok/dtk |
| Qwen3 Omni 30B A3B InstructAlibaba | 4.80 | - | 0.25 | 0.97 | 93 tok/dtk |
| GPT-4o (Aug '24)OpenAI | 9.40 | - | 2.50 | 10.00 | 93 tok/dtk |
| GLM-4.5V (Non-reasoning)Z AI | 6.80 | - | 0.60 | 1.80 | 92 tok/dtk |
| Ling 2.6 FlashInclusionAI | 14.20 | - | 0.10 | 0.30 | 91 tok/dtk |
| GPT-4o (May '24)OpenAI | 8.40 | - | 5.00 | 15.00 | 91 tok/dtk |
| Qwen3 Coder 30B A3B InstructAlibaba | 13.60 | - | 0.45 | 2.25 | 91 tok/dtk |
| GPT-5.4 (Non-reasoning)OpenAI | 28.30 | - | 2.50 | 15.00 | 90 tok/dtk |
| MiniMax-M3MiniMax | 45.40 | $205 | 0.30 | 1.20 | 90 tok/dtk |
| Claude 4.5 Haiku (Non-reasoning)Anthropic | 24.10 | - | 1.00 | 5.00 | 90 tok/dtk |
| Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA | 8.50 | - | 0.40 | 0.40 | 90 tok/dtk |
| Qwen3 VL 32B (Reasoning)Alibaba | 18.10 | - | 0.16 | 0.64 | 90 tok/dtk |
| Claude 4.5 Haiku (Reasoning)Anthropic | 29.90 | $471 | 1.00 | 5.00 | 89 tok/dtk |
| MiniMax-M2MiniMax | 28.90 | - | 0.30 | 1.20 | 89 tok/dtk |
| MiniMax-M2.1MiniMax | 32.10 | - | 0.30 | 1.20 | 88 tok/dtk |
| Qwen3.5 397B A17B (Reasoning)Alibaba | 34.30 | $527 | 0.60 | 3.60 | 88 tok/dtk |
| Llama 3.3 Instruct 70BMeta | 9.30 | - | 0.66 | 0.72 | 88 tok/dtk |
| Qwen3.5 9B (Non-reasoning)Alibaba | 20.60 | - | 0.17 | 0.25 | 87 tok/dtk |
| GPT-5 mini (medium)OpenAI | 31.60 | - | 0.25 | 2.00 | 85 tok/dtk |
| GPT-5.5 (xhigh)OpenAI | 56.30 | $2778 | 5.00 | 30.00 | 85 tok/dtk |
| GLM-5.3 (max)Z AI | 59.50 | $1239 | 1.40 | 4.40 | 85 tok/dtk |
| Grok 4.20 0309 v2 (Non-reasoning)SpaceXAI | 22.20 | - | 1.25 | 2.50 | 85 tok/dtk |
| Ling-flash-2.0InclusionAI | 9.60 | - | 0.14 | 0.57 | 84 tok/dtk |
| GLM-4.5V (Reasoning)Z AI | 9.00 | - | 0.60 | 1.80 | 83 tok/dtk |
| GPT-5 mini (high)OpenAI | 25.80 | $130 | 0.25 | 2.00 | 83 tok/dtk |
| Qwen3.5 397B A17B (Non-reasoning)Alibaba | 32.70 | - | 0.60 | 3.60 | 83 tok/dtk |
| GLM-5.1 (Reasoning)Z AI | 41.00 | $700 | 1.39 | 4.40 | 83 tok/dtk |
| Gemma 4 31B (Non-reasoning)Google | 22.30 | $33.8 | 0.15 | 0.40 | 82 tok/dtk |
| GPT-5 (medium)OpenAI | 34.60 | - | 1.25 | 10.00 | 82 tok/dtk |
| Qwen3.5 27B (Non-reasoning)Alibaba | 30.00 | - | 0.30 | 2.40 | 82 tok/dtk |
| Qwen3.5 9B (Reasoning)Alibaba | 21.80 | $240 | 0.14 | 0.20 | 81 tok/dtk |
| GPT-5 (high)OpenAI | 35.30 | $789 | 1.25 | 10.00 | 81 tok/dtk |
| GPT-5.5 (medium)OpenAI | 51.40 | $939 | 5.00 | 30.00 | 79 tok/dtk |
| GPT-5.2 (xhigh)OpenAI | 43.30 | - | 1.75 | 14.00 | 78 tok/dtk |
| GPT-5 (minimal)OpenAI | 17.30 | - | 1.25 | 10.00 | 78 tok/dtk |
| GLM-4.5-AirZ AI | 16.70 | - | 0.17 | 0.98 | 77 tok/dtk |
| Qwen3.5 27B (Reasoning)Alibaba | 34.60 | - | 0.30 | 2.40 | 77 tok/dtk |
| DeepSeek V4 Pro (Non-reasoning)DeepSeek | 31.90 | - | 0.43 | 0.87 | 76 tok/dtk |
| Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Anthropic | 55.30 | $4011 | 2.00 | 10.00 | 76 tok/dtk |
| DeepSeek V4 Pro (Reasoning, High Effort)DeepSeek | 43.70 | $109 | 0.43 | 0.87 | 75 tok/dtk |
| Gemma 4 26B A4B (Non-reasoning)Google | 20.40 | - | 0.13 | 0.40 | 75 tok/dtk |
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek | 53.20 | $605 | 1.32 | 3.96 | 74 tok/dtk |
| GPT-5.5 (high)OpenAI | 54.70 | $1721 | 5.00 | 30.00 | 74 tok/dtk |
| Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research | 9.90 | - | 0.13 | 0.40 | 74 tok/dtk |
| Inkling (xhigh)Thinking Machines | 42.30 | $698 | 1.00 | 4.05 | 74 tok/dtk |
| DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek | 45.30 | $176 | 0.43 | 0.87 | 74 tok/dtk |
| GPT-5.5 (low)OpenAI | 44.50 | $374 | 5.00 | 30.00 | 74 tok/dtk |
| GLM-4.6V (Non-reasoning)Z AI | 10.90 | - | 0.30 | 0.90 | 73 tok/dtk |
| Grok 3 mini Reasoning (high)SpaceXAI | 22.90 | - | 0.30 | 0.50 | 72 tok/dtk |
| Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)Anthropic | - | - | 2.00 | 10.00 | 71 tok/dtk |
| GLM-4.6V (Reasoning)Z AI | 16.90 | - | 0.30 | 0.90 | 70 tok/dtk |
| GPT-5.5 (Non-reasoning)OpenAI | 35.80 | $212 | 5.00 | 30.00 | 68 tok/dtk |
| GPT-5.2 (Non-reasoning)OpenAI | 26.50 | - | 1.75 | 14.00 | 68 tok/dtk |
| GPT-5 (low)OpenAI | 31.90 | - | 1.25 | 10.00 | 68 tok/dtk |
| Qwen3 VL 32B InstructAlibaba | 11.00 | - | 0.16 | 0.64 | 67 tok/dtk |
| Hy3Tencent | 42.20 | $93.2 | 0.14 | 0.55 | 67 tok/dtk |
| Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic | 62.10 | $5455 | 10.00 | 50.00 | 67 tok/dtk |
| Inkling SmallThinking Machines | 41.20 | $193 | 0.30 | 1.20 | 67 tok/dtk |
| Qwen3 Coder 480B A35B InstructAlibaba | 18.20 | - | 1.50 | 7.50 | 66 tok/dtk |
| GPT-5.6 Sol (max)OpenAI | 60.90 | $2823 | 5.00 | 30.00 | 65 tok/dtk |
| Qwen3 235B A22B 2507 (Reasoning)Alibaba | 19.90 | $170 | 0.23 | 2.30 | 64 tok/dtk |
| GPT-5.6 Sol (high)OpenAIModel dengan nilai terbaik | 57.30 | $955 | 5.00 | 30.00 | 63 tok/dtk |
| GPT-5.6 Sol (medium)OpenAI | 55.60 | $580 | 5.00 | 30.00 | 63 tok/dtk |
| GPT-5.6 Sol (xhigh)OpenAI | 59.00 | $1525 | 5.00 | 30.00 | 63 tok/dtk |
| Claude Sonnet 5 (Adaptive Reasoning, High Effort)Anthropic | - | - | 2.00 | 10.00 | 62 tok/dtk |
| GLM-5.1 (Non-reasoning)Z AI | 36.30 | - | 1.39 | 4.40 | 62 tok/dtk |
| Qwen3.6 Max PreviewAlibaba | 41.10 | - | 1.30 | 7.80 | 62 tok/dtk |
| Qwen3 235B A22B (Reasoning)Alibaba | 13.50 | - | 0.70 | 8.40 | 61 tok/dtk |
| MiniMax-M2.7MiniMax | 38.90 | $143 | 0.30 | 1.20 | 61 tok/dtk |
| Command ACohere | 7.50 | - | 2.50 | 10.00 | 60 tok/dtk |
| Qwen3 14B (Non-reasoning)Alibaba | 6.80 | - | 0.35 | 1.40 | 60 tok/dtk |
| GPT-5.6 Sol (Non-reasoning)OpenAI | 41.90 | $240 | 5.00 | 30.00 | 59 tok/dtk |
| Qwen3 235B A22B (Non-reasoning)Alibaba | 10.80 | - | 0.70 | 2.80 | 59 tok/dtk |
| Qwen3 14B (Reasoning)Alibaba | 10.40 | - | 0.35 | 4.20 | 59 tok/dtk |
| MiMo-V2.5-ProXiaomi | 42.90 | $98.9 | 0.43 | 0.87 | 59 tok/dtk |
| Qwen3 Max (Preview)Alibaba | 19.40 | - | 1.20 | 6.00 | 59 tok/dtk |
| Claude Sonnet 5 (Non-reasoning, High Effort)Anthropic | 42.60 | $416 | 2.00 | 10.00 | 58 tok/dtk |
| Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)Anthropic | - | - | 2.00 | 10.00 | 58 tok/dtk |
| Claude Sonnet 5 (Adaptive Reasoning, Low Effort)Anthropic | - | - | 2.00 | 10.00 | 58 tok/dtk |
| Qwen3 MaxAlibaba | 24.50 | - | 1.20 | 6.00 | 58 tok/dtk |
| Qwen3 VL 235B A22B (Reasoning)Alibaba | 20.90 | - | 0.40 | 4.00 | 57 tok/dtk |
| GPT-5.6 Sol (low)OpenAI | 50.70 | $344 | 5.00 | 30.00 | 57 tok/dtk |
| Mistral Medium 3Mistral | 12.50 | - | 0.40 | 2.00 | 57 tok/dtk |
| Qwen3.7 PlusAlibaba | 39.40 | $322 | 0.40 | 1.60 | 57 tok/dtk |
| Grok 4.6 (high)SpaceXAIModel dengan nilai terbaik | 60.90 | $1068 | 2.00 | 6.00 | 56 tok/dtk |
| Qwen3 235B A22B 2507 InstructAlibaba | 18.40 | - | 0.23 | 0.92 | 56 tok/dtk |
| Qwen3.6 PlusAlibaba | 40.50 | $526 | 0.50 | 3.00 | 56 tok/dtk |
| Qwen3 Max Thinking (Preview)Alibaba | 25.50 | - | 1.20 | 6.00 | 56 tok/dtk |
| Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research | 6.70 | - | 0.13 | 0.40 | 56 tok/dtk |
| Reka Flash (Sep '24)Reka AI | 6.00 | - | 0.20 | 0.80 | 56 tok/dtk |
| MiMo-V2.5-Pro (Non-reasoning)Xiaomi | 28.40 | - | 0.43 | 0.87 | 56 tok/dtk |
| MiMo-V2.5Xiaomi | 38.00 | $25.2 | 0.14 | 0.28 | 56 tok/dtk |
| Gemma 3n E4B InstructGoogle | 1.00 | - | 0.06 | 0.12 | 55 tok/dtk |
| Qwen3.6 27B (Non-reasoning)Alibaba | 31.30 | $359 | 0.60 | 3.60 | 55 tok/dtk |
| GLM-4.6 (Non-reasoning)Z AI | 23.40 | - | 0.57 | 2.20 | 55 tok/dtk |
| Qwen3.6 27B (Reasoning)Alibaba | 37.70 | $667 | 0.60 | 3.60 | 55 tok/dtk |
| Grok Build 0.1 0616SpaceXAI | 40.70 | $377 | 1.00 | 2.00 | 55 tok/dtk |
| Llama 3.1 Instruct 70BMeta | 6.50 | - | 0.56 | 0.56 | 55 tok/dtk |
| Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Anthropic | 48.40 | $3355 | 3.00 | 15.00 | 55 tok/dtk |
| Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic | 57.30 | $3752 | 5.00 | 25.00 | 54 tok/dtk |
| Gemma 4 E4B (Reasoning)Google | 12.20 | - | 0.02 | 0.10 | 54 tok/dtk |
| Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)AnthropicModel dengan nilai terbaik | 62.50 | $2909 | 5.00 | 25.00 | 54 tok/dtk |
| Claude Opus 5 (Adaptive Reasoning, Max Effort)AnthropicModel dengan nilai terbaik | 63.10 | $3836 | 5.00 | 25.00 | 53 tok/dtk |
| Gemma 4 E4B (Non-reasoning)Google | 8.70 | - | 0.02 | 0.10 | 52 tok/dtk |
| Claude Opus 5 (Adaptive Reasoning, High Effort)AnthropicModel dengan nilai terbaik | 61.50 | $1974 | 5.00 | 25.00 | 51 tok/dtk |
| Grok 4.5 (high)SpaceXAI | 55.80 | $579 | 2.00 | 6.00 | 50 tok/dtk |
| GLM-4.6 (Reasoning)Z AI | 29.30 | $314 | 0.55 | 2.20 | 50 tok/dtk |
| Claude Opus 5 (Adaptive Reasoning, Medium Effort)Anthropic | 58.60 | $1116 | 5.00 | 25.00 | 50 tok/dtk |
| Qwen3.5 Omni PlusAlibaba | 31.30 | - | 0.40 | 4.80 | 49 tok/dtk |
| Claude Opus 5 (Adaptive Reasoning, Low Effort)Anthropic | 52.50 | $555 | 5.00 | 25.00 | 49 tok/dtk |
| Mistral Large 3Mistral | 15.90 | $71.1 | 0.50 | 1.50 | 48 tok/dtk |
| Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA | 8.90 | - | 0.60 | 1.80 | 48 tok/dtk |
| Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Anthropic | 55.00 | $3743 | 5.00 | 25.00 | 48 tok/dtk |
| Llama 3.2 Instruct 11B (Vision)Meta | 3.00 | - | 0.34 | 0.34 | 47 tok/dtk |
| Qwen3 VL 235B A22B InstructAlibaba | 14.40 | - | 0.40 | 1.60 | 47 tok/dtk |
| Solar Pro 4Upstage | 41.60 | $321 | 0.30 | 1.20 | 47 tok/dtk |
| Qwen3.8 2.4T A95BAlibaba | 57.70 | $1672 | 2.00 | 6.00 | 46 tok/dtk |
| GLM-5 (Reasoning)Z AI | 40.60 | - | 1.00 | 3.20 | 46 tok/dtk |
| Kimi K2.6Kimi | 45.10 | $841 | 0.95 | 4.00 | 46 tok/dtk |
| Claude Opus 4.5 (Reasoning)Anthropic | 41.90 | - | 5.00 | 25.00 | 46 tok/dtk |
| Claude Opus 4.5 (Non-reasoning)Anthropic | 35.60 | - | 5.00 | 25.00 | 45 tok/dtk |
| Kimi K2.5 (Non-reasoning)Kimi | 30.10 | - | 0.60 | 3.00 | 45 tok/dtk |
| Qwen3.8 MaxAlibaba | 58.10 | $1741 | 2.00 | 6.00 | 45 tok/dtk |
| Phi-4 Mini InstructMicrosoft | 5.70 | - | 0.00 | 0.00 | 44 tok/dtk |
| Claude Opus 4.7 (Non-reasoning, High Effort)Anthropic | 43.90 | - | 5.00 | 25.00 | 44 tok/dtk |
| Claude Sonnet 4.6 (Non-reasoning, Low Effort)Anthropic | 35.10 | - | 3.00 | 15.00 | 44 tok/dtk |
| Claude Sonnet 4.6 (Non-reasoning, High Effort)Anthropic | 36.80 | - | 3.00 | 15.00 | 43 tok/dtk |
| Kimi K2.5 (Reasoning)Kimi | 36.00 | $304 | 0.60 | 3.00 | 43 tok/dtk |
| Kimi K2Kimi | 19.70 | - | 0.57 | 2.30 | 41 tok/dtk |
| Kimi K2 0905Kimi | 24.00 | - | 0.60 | 2.50 | 41 tok/dtk |
| Claude 4.5 Sonnet (Reasoning)Anthropic | 37.40 | $1037 | 3.00 | 15.00 | 40 tok/dtk |
| Kimi K2.6 (Non-reasoning)Kimi | 35.40 | - | 0.95 | 4.00 | 40 tok/dtk |
| GLM-5 (Non-reasoning)Z AI | 33.20 | - | 1.00 | 3.20 | 40 tok/dtk |
| LongCat 2.0LongCat | 34.00 | $442 | 0.75 | 2.95 | 39 tok/dtk |
| Qwen3 8B (Non-reasoning)Alibaba | 4.80 | - | 0.18 | 0.70 | 39 tok/dtk |
| Claude Opus 4.6 (Adaptive Reasoning, Max Effort)Anthropic | 44.90 | - | 5.00 | 25.00 | 39 tok/dtk |
| Phi-4Microsoft | 4.60 | - | 0.13 | 0.50 | 39 tok/dtk |
| Claude 4.5 Sonnet (Non-reasoning)Anthropic | 29.90 | - | 3.00 | 15.00 | 39 tok/dtk |
| Qwen3 8B (Reasoning)Alibaba | 8.30 | - | 0.18 | 2.10 | 39 tok/dtk |
| Kimi K3 (max)Kimi | 59.70 | $2425 | 3.00 | 15.00 | 38 tok/dtk |
| Kimi K2.7 CodeKimi | 43.00 | $545 | 0.95 | 4.00 | 37 tok/dtk |
| Claude Opus 4.6 (Non-reasoning, High Effort)Anthropic | 38.80 | - | 5.00 | 25.00 | 36 tok/dtk |
| Kimi K3 (low)Kimi | 48.30 | $283 | 3.00 | 15.00 | 36 tok/dtk |
| Hermes 3 - Llama-3.1 70BNous Research | 4.80 | - | 0.70 | 0.70 | 34 tok/dtk |
| Nova PremierAmazon | 12.70 | - | 2.50 | 12.50 | 33 tok/dtk |
| GPT-4 TurboOpenAI | 7.70 | - | 10.00 | 30.00 | 32 tok/dtk |
| Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research | 8.80 | - | 1.00 | 3.00 | 30 tok/dtk |
| Qwen3.5 4B (Reasoning)Alibaba | 20.40 | - | 0.03 | 0.15 | 30 tok/dtk |
| Seed-OSS-36B-InstructByteDance Seed | 18.50 | - | 0.21 | 0.57 | 30 tok/dtk |
| Qwen3.5 4B (Non-reasoning)Alibaba | 16.10 | - | 0.03 | 0.15 | 28 tok/dtk |
| DeepSeek R1 Distill Llama 70BDeepSeek | 9.80 | - | 0.70 | 1.10 | 25 tok/dtk |
| Granite 4.0 H SmallIBM | 4.90 | - | 0.06 | 0.25 | 25 tok/dtk |
| Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research | 8.60 | - | 1.00 | 3.00 | 22 tok/dtk |
| Phi-4 Multimodal InstructMicrosoft | 4.20 | - | 0.00 | 0.00 | 17 tok/dtk |
| Granite 3.3 8B (Non-reasoning)IBM | 1.30 | - | 0.03 | 0.25 | 14 tok/dtk |
Panduan
Cara kami membandingkan model
Kecerdasan diukur dengan Artificial Analysis Intelligence Index. Biaya benchmark adalah total biaya menjalankan tes dalam USD, termasuk token penalaran; bukan harga API per token. Semua bahasa memakai data dan perhitungan yang sama. Skor umum tidak mengukur kemampuan dalam bahasa atau tugas tertentu.