LLMリーダーボード - OpenAI、Anthropic、Google、SpaceXAIなどのAIモデルを比較
250以上のAIモデル（LLM）を、知能、料金、性能、速度（出力速度 - 1秒あたりのトークン数、遅延 - TTFT）、コンテキストウィンドウなどの主要指標で比較し、順位付けします。
方法論などの詳細は、よくある質問をご覧ください。
知能
知能が最も高いモデルはClaude Opus 5 (max)とClaude Opus 5 (xhigh)で、Claude Fable 5 (with fallback)とClaude Opus 5 (high)が続きます。
出力速度
最速のモデルはCeleris-1とMercury 2で、Gemini 2.5 Flash-LiteとLing 3.0 Flashが続きます。
遅延
遅延が最も短いモデルはGemini 2.5 Flash-LiteとCommand A+で、Gemini 2.5 FlashとNorth Mini Codeが続きます。
タスクあたりの費用
タスクあたりの費用が最も低いモデルはGPT-5.6 Luna (low)とMiMo-V2.5で、Llama 4 ScoutとGPT-5.6 Luna (medium)が続きます。
コンテキストウィンドウ
最大のコンテキストウィンドウに対応するモデルはLlama 4 ScoutとGrok 4.20 0309で、Gemini 1.5 Pro (May)とGrok 4.1 Fastが続きます。
詳細分析 | ||||||||
|---|---|---|---|---|---|---|---|---|
Claude Opus 5 (max) | 1M | Anthropic | 63 | $2.34 | 59 | 54.31 | 62.81 | |
Claude Opus 5 (xhigh) | 1M | Anthropic | 63 | $1.80 | 55 | 38.79 | 47.81 | |
Claude Fable 5 (with fallback) | 1M | Anthropic | 62 | $3.14 | 71 | 122.01 | 129.06 | |
Claude Opus 5 (high) | 1M | Anthropic | 61 | $1.23 | 58 | 22.05 | 30.71 | |
GPT-5.6 Sol (max) | 1M | OpenAI | 61 | $0.96 | 74 | 162.41 | 169.14 | |
Grok 4.6 (high) | 500k | SpaceXAI | 61 | $0.84 | 62 | 44.82 | 52.89 | |
Grok 4.6 (xhigh) | 500k | SpaceXAI | 60 | $1.04 | 63 | 47.17 | 55.12 | |
Kimi K3 (max) | 1.05M |  Kimi | 60 | $0.84 | 35 | 4.05 | 75.53 | |
GLM-5.3 (max) | 1M |  Z AI | 60 | $0.68 | 90 | 1.22 | 29.01 | |
GPT-5.6 Sol (xhigh) | 1M | OpenAI | 59 | $0.64 | 68 | 51.47 | 58.87 | |
Grok 4.6 (medium) | 500k | SpaceXAI | 59 | $0.67 | 60 | 33.87 | 42.20 | |
Claude Opus 5 (medium) | 1M | Anthropic | 59 | $0.72 | 55 | 6.55 | 15.57 | |
Qwen3.8 Max | 1M |  Alibaba | 58 | $1.13 | 24 | 4.20 | 106.27 | |
Qwen3.8 2.4T A95B | 984k | Alibaba | 58 | $1.09 | 21 | 2.63 | 121.72 | |
GPT-5.6 Sol (high) | 1M | OpenAI | 57 | $0.43 | 67 | 18.89 | 26.34 | |
Muse Spark 1.2 (xhigh) | 1.05M | Meta | 57 | $0.40 | -- | -- | -- | |
GPT-5.6 Terra (max) | 1M | OpenAI | 57 | $0.51 | 122 | 199.42 | 203.51 | |
Gemini 3.7 Flash (high) | 1M | Google | 56 | $0.40 | 362 | 12.29 | 13.67 | |
Grok 4.5 (high) | 500k | SpaceXAI | 56 | $0.36 | 61 | 10.01 | 18.20 | |
GPT-5.6 Sol (medium) | 1M | OpenAI | 56 | $0.30 | 69 | 5.11 | 12.40 | |
Claude Sonnet 5 (max) | 1M | Anthropic | 55 | $1.72 | 77 | 161.41 | 167.89 | |
Gemini 3.7 Flash (medium) | 1M | Google | 53 | $0.26 | 372 | 4.39 | 5.73 | |
DeepSeek V4 Pro 0813 (max) | 1M |  DeepSeek | 53 | $0.25 | 72 | 1.81 | 36.66 | |
GPT-5.6 Terra (xhigh) | 1M | OpenAI | 53 | $0.31 | 115 | 30.38 | 34.72 | |
GLM-5.2 (max) | 1M | Z AI | 53 | $0.44 | 79 | 1.75 | 33.41 | |
Claude Opus 5 (low) | 1M | Anthropic | 52 | $0.43 | 55 | 3.55 | 12.68 | |
GPT-5.6 Luna (max) | 1M | OpenAI | 52 | $0.05 | 141 | 150.68 | 154.24 | |
Qwen3.8 27B (xhigh) | 256k | Alibaba | 52 | $0.25 | 52 | 3.00 | 50.93 | |
DeepSeek V4 Flash 0731 (max) | 1M | DeepSeek | 52 | $0.11 | 125 | 1.05 | 21.03 | |
Grok 4.6 (low) | 500k | SpaceXAI | 52 | $0.22 | 61 | 6.83 | 15.03 | |
Gemini 3.6 Flash | 1M | Google | 52 | $0.34 | 210 | 13.95 | 16.33 | |
DeepSeek V4 Flash Vision (max) | 1M | DeepSeek | 51 | $0.12 | 120 | 0.91 | 21.74 | |
Gemini 3.7 Flash (low) | 1M | Google | 51 | $0.16 | 367 | 0.99 | 2.35 | |
GPT-5.6 Sol (low) | 1M | OpenAI | 51 | $0.19 | 66 | 2.98 | 10.50 | |
GPT-5.6 Terra (high) | 1M | OpenAI | 50 | $0.22 | 117 | 3.07 | 7.33 | |
GPT-5.6 Luna (xhigh) | 1M | OpenAI | 50 | $0.03 | 133 | 68.08 | 71.86 | |
Kimi K3 (low) | 1.05M | Kimi | 48 | $0.24 | 35 | 3.87 | 75.03 | |
Gemini 3.1 Pro Preview | 1M | Google | 48 | $0.33 | 124 | 28.63 | 32.66 | |
Motif 3 | 262k |  Motif Technologies | 47 | -- | -- | -- | -- | |
GPT-5.6 Luna (high) | 1M | OpenAI | 47 | $0.02 | 132 | 12.92 | 16.69 | |
GPT-5.6 Terra (medium) | 1M | OpenAI | 47 | $0.12 | 100 | 1.80 | 6.80 | |
Gemini 3.5 Flash (medium) | 1M | Google | 47* | -- | 209 | 14.87 | 17.26 | |
GPT-5.3 Codex (xhigh) | 400k | OpenAI | 46* | -- | 143 | 61.83 | 65.33 | |
MiniMax-M3 | 1M |  MiniMax | 45 | $0.14 | 124 | 1.31 | 21.47 | |
Motif 3 (Beta) | 262k | Motif Technologies | 45* | -- | -- | -- | -- | |
DeepSeek V4 Pro (max) | 1M | DeepSeek | 45 | $0.05 | 74 | 1.76 | 67.65 | |
Qwen3.8 27B (medium) | 256k | Alibaba | 44 | $0.19 | 61 | 3.03 | 43.80 | |
DeepSeek V4 Pro (high) | 1M | DeepSeek | 44 | $0.04 | 70 | 1.71 | 37.06 | |
Kimi K2.7 Code | 256k | Kimi | 43 | $0.22 | 50 | 2.89 | 57.51 | |
MiMo-V2.5-Pro | 1M | Xiaomi | 43 | $0.03 | 52 | 3.26 | 51.13 | |
Qwen3.8 27B (low) | 256k | Alibaba | 43 | $0.17 | 64 | 2.99 | 41.78 | |
Claude Sonnet 5 (Non-reasoning) | 1M | Anthropic | 43 | $0.42 | 70 | 1.75 | 8.91 | |
Inkling | 1M |  Thinking Machines | 42 | $0.34 | 50 | 2.73 | 52.49 | |
Hy3 | 256k |  Tencent | 42 | $0.04 | 80 | 2.90 | 34.06 | |
GPT-5.6 Sol (Non-reasoning) | 1M | OpenAI | 42 | $0.19 | 61 | 1.40 | 9.62 | |
Nex-N2-Pro | 262k |  Nex AGI | 42 | -- | 134 | 1.61 | 20.25 | |
Solar Pro 4 | 512k |  Upstage | 42 | $0.22 | 59 | 2.30 | 44.61 | |
GPT-5.6 Terra (low) | 1M | OpenAI | 41 | $0.09 | 116 | 1.41 | 5.74 | |
Inkling Small | 1M | Thinking Machines | 41 | $0.07 | 142 | 2.05 | 19.66 | |
JT-4.1 Flash 236B A21B | 256k |  China Mobile | 40* | -- | -- | -- | -- | |
Agnes 2.5 Pro Alpha | 1M |  Sapiens AI | 40 | -- | 130 | 2.14 | 21.44 | |
Qwen3.7 Plus | 1M | Alibaba | 39 | $0.24 | 56 | 2.11 | 47.13 | |
GPT-5.6 Luna (medium) | 1M | OpenAI | 39 | $0.01 | 132 | 2.33 | 6.11 | |
Nemotron 3 Ultra | 262k |  NVIDIA | 38 | $0.38 | 167 | 1.85 | 18.47 | |
MiMo-V2.5 | 1M | Xiaomi | 38 | $0.01 | 66 | 4.08 | 41.77 | |
Ling 3.0 Flash | 262k | InclusionAI | 38 | $0.04 | 387 | 2.44 | 8.90 | |
Qwen3.6 27B | 262k | Alibaba | 38 | $0.29 | 57 | 3.70 | 111.79 | |
Gemini 3.5 Flash-Lite | 1M | Google | 37 | $0.10 | 373 | 8.12 | 9.46 | |
Solar Open2 250B | 1.05M | Upstage | 37 | -- | -- | -- | -- | |
MiMo-V2-Omni-0327 | 256k | Xiaomi | 37* | -- | -- | -- | -- | |
Grok 4.3 (medium) | 1M | SpaceXAI | 37* | -- | 147 | 11.71 | 15.11 | |
Grok 4.3 (low) | 1M | SpaceXAI | 36* | -- | 135 | 5.37 | 9.08 | |
MiMo-V2-Omni | 256k | Xiaomi | 36* | -- | -- | -- | -- | |
Gemini 3.5 Flash (minimal) | 1M | Google | 36* | -- | 185 | 0.79 | 3.49 | |
Claude Sonnet 4.6 (Non-reasoning, Low Effort) | 1M | Anthropic | 35* | -- | 48 | 1.50 | 12.01 | |
Muse Glimmer (high) | 131k | Meta | 35 | $0.07 | 107 | 0.78 | 24.04 | |
A.X-K2 | 262k |  SK Telecom | 35 | -- | -- | -- | -- | |
GLM-5.2 | 1M | Z AI | 35 | -- | 122 | 1.89 | 6.00 | |
Qwen3.8 27B | 256k | Alibaba | 35 | $0.21 | 65 | 3.03 | 10.75 | |
GPT-5.6 Terra (Non-reasoning) | 1M | OpenAI | 35 | $0.10 | 109 | 0.78 | 5.35 | |
Qwen3.5 397B A17B | 262k | Alibaba | 34 | $0.36 | 79 | 2.17 | 48.87 | |
MiMo-V2-Flash (Feb 2026) | 256k | Xiaomi | 34* | -- | -- | -- | -- | |
G9v3-39A5B | 131k |  AI9Stars | 34 | $0.00 | -- | -- | -- | |
LongCat 2.0 | 1M |  LongCat | 34 | $0.12 | 42 | 2.80 | 61.87 | |
GPT-5.6 Luna (low) | 1M | OpenAI | 34 | $0.01 | 132 | 1.61 | 5.40 | |
KAT-Coder-Pro V2 | 256k |  KwaiKAT | 34 | -- | 104 | 1.40 | 6.23 | |
Qwen3.5 122B A10B | 262k | Alibaba | 33 | $0.25 | 130 | 2.33 | 21.49 | |
Qwen3.5 397B A17B | 262k | Alibaba | 33* | -- | 77 | 2.20 | 8.70 | |
Qwen3.6 35B A3B | 262k | Alibaba | 32 | $0.29 | 122 | 2.06 | 50.35 | |
DeepSeek V4 Pro | 1M | DeepSeek | 32* | -- | 72 | 1.83 | 8.78 | |
Ring-2.6-1T | 262k | InclusionAI | 32 | $0.36 | 130 | 4.06 | 23.31 | |
Qwen3.5 Omni Plus | 256k | Alibaba | 31* | -- | 49 | 2.39 | 12.58 | |
Qwen3.6 27B | 262k | Alibaba | 31 | $0.40 | 58 | 3.81 | 12.50 | |
o3 | 200k | OpenAI | 31* | -- | 144 | 7.43 | 10.91 | |
K-EXAONE 2.0 | 262k |  LG AI Research | 31 | -- | -- | -- | -- | |
Step 3.7 Flash | 262k |  StepFun | 31 | $0.09 | 128 | 2.72 | 22.30 | |
Mistral Medium 3.5 | 256k |  Mistral | 30 | $0.46 | 148 | 2.20 | 19.06 | |
Claude 4.5 Haiku | 200k | Anthropic | 30 | $0.22 | 118 | 23.78 | 28.01 | |
Gemma 4 31B | 256k | Google | 30 | $0.00 | 35 | 1.06 | 64.96 | |
DeepSeek V4 Flash | 1M | DeepSeek | 29* | -- | -- | -- | -- | |
GPT-5.5 Instant (June 2026) | 400k | OpenAI | 29 | $0.54 | 144 | 1.02 | 18.35 | |
JT-35B-Flash | 256k | China Mobile | 29* | -- | -- | -- | -- | |
MiMo-V2.5-Pro | 1M | Xiaomi | 28* | -- | 48 | 3.97 | 14.46 | |
Qwen3.5 122B A10B | 262k | Alibaba | 28 | $0.20 | 148 | 2.31 | 5.68 | |
GPT-5.6 Luna (Non-reasoning) | 1M | OpenAI | 27 | $0.01 | 129 | 0.67 | 4.53 | |
Doubao Seed Code | 256k |  ByteDance Seed | 26* | -- | -- | -- | -- | |
Gemma 4 26B A4B | 256k | Google | 26 | $0.04 | -- | -- | -- | |
Nemotron 3 Super | 1M | NVIDIA | 26 | $0.23 | 142 | 1.76 | 19.37 | |
MiMo-V2-Flash | 256k | Xiaomi | 25* | -- | -- | -- | -- | |
Grok 4.3 (Non-reasoning) | 1M | SpaceXAI | 25 | $0.29 | 132 | 0.73 | 4.51 | |
Qwen3.6 35B A3B | 262k | Alibaba | 25 | $0.63 | 140 | 2.00 | 5.58 | |
Ling 3.0 Tiny | 262k | InclusionAI | 25 | $0.00 | 162 | 2.82 | 18.23 | |
Qwen3.5 35B A3B | 262k | Alibaba | 24 | $0.24 | 172 | 2.03 | 4.94 | |
Claude 4.5 Haiku | 200k | Anthropic | 24* | -- | 94 | 0.77 | 6.08 | |
gpt-oss-120b (high) | 131k | OpenAI | 24 | $0.07 | 188 | 0.81 | 14.12 | |
Nemotron 3.5 Lightning | 1M | NVIDIA | 24 | $0.08 | 317 | 1.49 | 9.39 | |
Command A+ | 192k | Cohere | 23 | $0.00 | 252 | 0.40 | 10.31 | |
K-EXAONE | 256k | LG AI Research | 22* | -- | -- | -- | -- | |
ERNIE 5.0 Thinking Preview | 128k |  Baidu | 22* | -- | -- | -- | -- | |
Gemma 4 31B | 256k | Google | 22 | $0.04 | 91 | 1.29 | 6.77 | |
Gemma 4 12B | 256k | Google | 22* | -- | 112 | 2.28 | 24.55 | |
Nova 2.0 Pro Preview (medium) | 256k |  Amazon | 22* | -- | 125 | 15.86 | 35.80 | |
Mercury 2 | 128k | Inception | 22 | $0.08 | 963 | 3.95 | 4.47 | |
Qwen3.5 9B | 262k | Alibaba | 22 | $0.24 | 77 | 2.04 | 34.38 | |
Qwen3 Coder Next | 256k | Alibaba | 21 | $0.34 | 143 | 0.99 | 4.49 | |
Nova 2.0 Omni (medium) | 1M | Amazon | 21* | -- | -- | -- | -- | |
Apriel-v1.6-15B-Thinker | 128k |  ServiceNow | 21* | -- | -- | -- | -- | |
Nova 2.0 Lite (high) | 1M | Amazon | 21* | -- | 179 | 16.04 | 29.99 | |
Qwen3.5 9B | 262k | Alibaba | 21* | -- | 88 | 0.80 | 6.51 | |
EXAONE 4.5 33B | 262k | LG AI Research | 21* | -- | -- | -- | -- | |
Gemma 4 26B A4B | 256k | Google | 20* | -- | 76 | 1.09 | 7.70 | |
Qwen3.5 4B | 262k | Alibaba | 20* | -- | 18 | 0.83 | 139.26 | |
North Mini Code | 256k | Cohere | 20 | $0.00 | 27 | 0.49 | 93.20 | |
Nova 2.0 Pro Preview (low) | 256k | Amazon | 20* | -- | 130 | 11.16 | 30.33 | |
Mistral Small 4 | 256k | Mistral | 20 | $0.10 | 176 | 0.74 | 14.92 | |
Devstral 2 | 256k | Mistral | 19 | $0.00 | 48 | 1.44 | 11.83 | |
Nova 2.0 Lite (medium) | 1M | Amazon | 19* | -- | 193 | 17.89 | 30.85 | |
Qwen3.5 Omni Flash | 256k | Alibaba | 19* | -- | 246 | 1.81 | 3.84 | |
JT-MINI | 128k | China Mobile | 19* | -- | -- | -- | -- | |
Trinity Large Thinking | 512k |  Arcee AI | 19 | $0.16 | 190 | 1.05 | 14.20 | |
HyperNova 60B 2605 | 131k |  Multiverse Computing | 18 | $0.02 | 363 | 0.89 | 7.79 | |
Magistral Medium 1.2 | 128k | Mistral | 18 | -- | -- | -- | -- | |
Nova 2.0 Lite (low) | 1M | Amazon | 18* | -- | 184 | 9.10 | 22.66 | |
Nemotron Cascade 2 30B A3B | 1M | NVIDIA | 18* | -- | -- | -- | -- | |
Devstral Small 2 | 256k | Mistral | 18 | $0.00 | 137 | 2.23 | 5.88 | |
K2 Think V2 | 262k |  MBZUAI Institute of Foundation Models | 17* | -- | -- | -- | -- | |
LongCat Flash Lite | 256k | LongCat | 17* | -- | -- | -- | -- | |
HyperCLOVA X SEED Think (32B) | 128k |  Naver | 17* | -- | -- | -- | -- | |
K-EXAONE | 256k | LG AI Research | 17* | -- | -- | -- | -- | |
Qwen3 Next 80B A3B | 262k | Alibaba | 17 | $0.04 | 203 | 2.29 | 14.62 | |
Nova 2.0 Omni (low) | 1M | Amazon | 17* | -- | -- | -- | -- | |
Mi:dm K 2.5 Pro | 128k |  Korea Telecom | 17* | -- | -- | -- | -- | |
G9v3-3B | 131k | AI9Stars | 16* | -- | -- | -- | -- | |
Qwen3.5 4B | 262k | Alibaba | 16* | -- | 16 | 0.81 | 31.87 | |
Mistral Large 3 | 256k | Mistral | 16 | $0.08 | 46 | 1.19 | 11.97 | |
INTELLECT-3 | 131k |  Prime Intellect | 16* | -- | -- | -- | -- | |
Solar Open 100B | 128k | Upstage | 15* | -- | -- | -- | -- | |
gpt-oss-20b (high) | 131k | OpenAI | 15 | $0.02 | 116 | 1.00 | 22.60 | |
Nemotron 3 Nano Omni 30B A3B | 256k | NVIDIA | 15* | -- | 321 | 1.00 | 8.78 | |
gpt-oss-120b (low) | 131k | OpenAI | 15 | $0.02 | 246 | 0.84 | 11.02 | |
Nemotron 3 Nano | 1M | NVIDIA | 15 | $0.02 | 276 | 1.10 | 10.15 | |
Solar Pro 3 | 128k | Upstage | 14 | $0.15 | 148 | 2.30 | 19.17 | |
Llama 4 Maverick | 1M | Meta | 14 | $0.03 | 99 | 0.89 | 5.95 | |
Nova 2.0 Pro Preview | 256k | Amazon | 14* | -- | 118 | 1.09 | 5.33 | |
gpt-oss-20b (low) | 131k | OpenAI | 14* | -- | 109 | 1.10 | 23.99 | |
K2-V2 (high) | 512k | MBZUAI Institute of Foundation Models | 14* | -- | -- | -- | -- | |
Qwen3 Next 80B A3B | 262k | Alibaba | 14* | -- | 189 | 2.13 | 4.77 | |
DiffusionGemma 26B A4B | 256k | Google | 13* | -- | -- | -- | -- | |
Gemma 4 12B (Non-reasoning) | 262k | Google | 13* | -- | 112 | 2.28 | 6.75 | |
Motif-2-12.7B | 128k | Motif Technologies | 13* | -- | -- | -- | -- | |
Nova Premier | 1M | Amazon | 13* | -- | 33 | 2.87 | 18.01 | |
K2-V2 (medium) | 512k | MBZUAI Institute of Foundation Models | 12* | -- | -- | -- | -- | |
Llama Nemotron Super 49B v1.5 | 128k | NVIDIA | 12* | -- | 61 | 8.62 | 49.33 | |
Celeris-1 | 131k | Celeris | 12 | $0.26 | 1,573 | 0.57 | 0.88 | |
Mistral Small 4 | 256k | Mistral | 12* | -- | 170 | 0.82 | 3.77 | |
Tri-21B-Think | 32k |  Trillion Labs | 12* | -- | -- | -- | -- | |
Gemma 4 E4B | 128k | Google | 12* | -- | 46 | 0.78 | 55.21 | |
MiniCPM5-1B | 128k |  OpenBMB | 12* | -- | -- | -- | -- | |
Sarvam 105B (high) | 128k |  Sarvam | 12* | -- | -- | -- | -- | |
Nova 2.0 Lite | 1M | Amazon | 12* | -- | 185 | 1.06 | 3.76 | |
MiniCPM5-1B | 128k | OpenBMB | 12* | -- | -- | -- | -- | |
Magistral Small 1.2 | 128k | Mistral | 11 | $0.30 | -- | -- | -- | |
Ministral 3 14B | 256k | Mistral | 11 | $0.16 | 99 | 0.96 | 6.02 | |
Nanbeige4.1-3B | 256k |  Nanbeige | 11* | -- | -- | -- | -- | |
LFM2.5-2.6B | 128k |  Liquid AI | 11 | $0.00 | -- | -- | -- | |
EXAONE 4.0 32B | 131k | LG AI Research | 11* | -- | -- | -- | -- | |
Nova 2.0 Omni | 1M | Amazon | 10* | -- | -- | -- | -- | |
Llama 4 Scout | 10M | Meta | 10 | $0.01 | 133 | 0.74 | 4.50 | |
Hermes 4 70B | 128k |  Nous Research | 10* | -- | 88 | 1.45 | 29.81 | |
Falcon-H1R-7B | 256k |  TII UAE | 10* | -- | -- | -- | -- | |
Gemma 4 E2B | 128k | Google | 10* | -- | -- | -- | -- | |
Qwen3 Omni 30B A3B | 65.5k | Alibaba | 10* | -- | 101 | 1.90 | 26.77 | |
Step3 VL 10B | 65.5k | StepFun | 9* | -- | -- | -- | -- | |
Llama 3.3 70B | 128k | Meta | 9* | -- | 88 | 1.64 | 7.32 | |
Ministral 3 8B | 256k | Mistral | 9 | $0.18 | 123 | 0.79 | 4.85 | |
Llama Nemotron Ultra | 128k | NVIDIA | 9* | -- | 52 | 2.40 | 50.06 | |
ERNIE 4.5 300B A47B | 131k | Baidu | 9* | -- | -- | -- | -- | |
Hermes 4 405B | 128k | Nous Research | 9* | -- | 37 | 2.54 | 69.50 | |
NVIDIA Nemotron Nano 12B v2 VL | 128k | NVIDIA | 9* | -- | 141 | 4.31 | 22.02 | |
Gemma 4 E4B | 128k | Google | 9* | -- | 46 | 0.74 | 11.55 | |
Granite 4.1 30B | 131k |  IBM | 9* | -- | -- | -- | -- | |
NVIDIA Nemotron Nano 9B V2 | 131k | NVIDIA | 9* | -- | 228 | 3.50 | 14.44 | |
Hermes 4 405B | 128k | Nous Research | 9* | -- | 36 | 2.41 | 16.38 | |
Nemotron 3 Nano 4B | 262k | NVIDIA | 9* | -- | -- | -- | -- | |
Llama Nemotron Super 49B v1.5 | 128k | NVIDIA | 9* | -- | 79 | 9.47 | 15.80 | |
K2-V2 (low) | 512k | MBZUAI Institute of Foundation Models | 8* | -- | -- | -- | -- | |
Kimi Linear 48B A3B Instruct | 1M | Kimi | 8* | -- | -- | -- | -- | |
Llama 3.1 405B | 128k | Meta | 8* | -- | -- | -- | -- | |
LFM2.5-8B-A1B | 32.8k | Liquid AI | 8* | -- | 339 | 1.82 | 9.20 | |
Ring-flash-2.0 | 128k | InclusionAI | 8* | -- | -- | -- | -- | |
Olmo 3.1 32B Think | 65.5k |  Allen Institute for AI | 8* | -- | -- | -- | -- | |
Command A | 256k | Cohere | 7* | -- | 70 | 1.58 | 8.71 | |
Qwen3.5 2B | 262k | Alibaba | 7* | -- | -- | -- | -- | |
Llama 3.1 Nemotron 70B | 128k | NVIDIA | 7* | -- | 102 | 5.28 | 10.20 | |
Nemotron 3 Nano | 1M | NVIDIA | 7* | -- | 263 | 0.88 | 2.78 | |
NVIDIA Nemotron Nano 9B V2 | 131k | NVIDIA | 7* | -- | 169 | 1.25 | 4.21 | |
Ministral 3 3B | 256k | Mistral | 7 | $0.13 | 208 | 0.58 | 2.99 | |
Hermes 4 70B | 128k | Nous Research | 7* | -- | 85 | 1.39 | 7.27 | |
Granite 4.1 8B | 131k | IBM | 6* | -- | 124 | 0.76 | 4.79 | |
Sarvam 30B (high) | 65.5k | Sarvam | 6* | -- | -- | -- | -- | |
Olmo 3.1 32B Instruct | 65.5k | Allen Institute for AI | 6* | -- | -- | -- | -- | |
Gemma 4 E2B | 128k | Google | 6* | -- | -- | -- | -- | |
R1 1776 | 128k |  Perplexity | 6* | -- | -- | -- | -- | |
Llama 3.2 90B (Vision) | 128k | Meta | 6* | -- | -- | -- | -- | |
Phi-4 Mini | 128k |  Microsoft | 6* | -- | 44 | 0.82 | 12.32 | |
EXAONE 4.0 32B | 131k | LG AI Research | 6* | -- | -- | -- | -- | |
Qwen3.5 2B | 262k | Alibaba | 5* | -- | -- | -- | -- | |
Qwen3.5 0.8B | 262k | Alibaba | 5* | -- | -- | -- | -- | |
DeepHermes 3 - Mistral 24B | 32k | Nous Research | 5* | -- | -- | -- | -- | |
Jamba 1.7 Large | 256k |  AI21 Labs | 5* | -- | -- | -- | -- | |
Granite 4.0 H Small | 128k | IBM | 5* | -- | 21 | 24.33 | 48.09 | |
Qwen3 Omni 30B A3B | 65.5k | Alibaba | 5* | -- | 95 | 1.88 | 7.15 | |
LFM2 24B A2B | 32.8k | Liquid AI | 5* | -- | -- | -- | -- | |
Phi-4 | 16k | Microsoft | 5* | -- | 42 | 2.44 | 14.38 | |
Nova Micro | 130k | Amazon | 4* | -- | 296 | 0.86 | 2.55 | |
Granite 4.1 3B | 131k | IBM | 4* | -- | -- | -- | -- | |
NVIDIA Nemotron Nano 12B v2 VL | 128k | NVIDIA | 4* | -- | 155 | 1.64 | 4.86 | |
Phi-4 Multimodal | 128k | Microsoft | 4* | -- | 18 | 0.82 | 29.21 | |
MiniCPM-V 4.6 1.3B | 262k | OpenBMB | 4* | -- | -- | -- | -- | |
Jamba Reasoning 3B | 262k | AI21 Labs | 4* | -- | -- | -- | -- | |
Reka Flash 3 | 128k |  Reka AI | 4* | -- | -- | -- | -- | |
Olmo 3 7B Think | 65.5k | Allen Institute for AI | 4* | -- | -- | -- | -- | |
Molmo 7B-D | 4.1k | Allen Institute for AI | 3* | -- | -- | -- | -- | |
Llama 3.2 11B (Vision) | 128k | Meta | 3* | -- | 65 | 1.05 | 8.71 | |
Qwen3.5 0.8B | 262k | Alibaba | 3* | -- | -- | -- | -- | |
Exaone 4.0 1.2B | 64k | LG AI Research | 3* | -- | -- | -- | -- | |
Olmo 3 7B | 65.5k | Allen Institute for AI | 2* | -- | -- | -- | -- | |
Exaone 4.0 1.2B | 64k | LG AI Research | 2* | -- | -- | -- | -- | |
LFM2.5-1.2B-Thinking | 32k | Liquid AI | 2* | -- | -- | -- | -- | |
Jamba 1.7 Mini | 258k | AI21 Labs | 2* | -- | -- | -- | -- | |
LFM2 2.6B | 32.8k | Liquid AI | 2* | -- | -- | -- | -- | |
LFM2.5-1.2B-Instruct | 32k | Liquid AI | 2* | -- | -- | -- | -- | |
Granite 4.0 H 1B | 128k | IBM | 2* | -- | -- | -- | -- | |
Gemma 3 270M | 32k | Google | 2* | -- | -- | -- | -- | |
Apertus 70B Instruct | 65.5k |  Swiss AI Initiative | 2* | -- | -- | -- | -- | |
Granite 4.0 Micro | 128k | IBM | 2* | -- | -- | -- | -- | |
DeepHermes 3 - Llama-3.1 8B | 128k | Nous Research | 2* | -- | -- | -- | -- | |
Granite 4.0 1B | 128k | IBM | 2* | -- | -- | -- | -- | |
Molmo2-8B | 36.9k | Allen Institute for AI | 2* | -- | -- | -- | -- | |
LFM2 8B A1B | 32.8k | Liquid AI | 1* | -- | -- | -- | -- | |
LFM2.5-VL-1.6B | 32k | Liquid AI | 1* | -- | 354 | 1.26 | 2.67 | |
Granite 4.0 350M | 32.8k | IBM | 1* | -- | -- | -- | -- | |
Tiny Aya Global | 8.19k | Cohere | 1* | -- | -- | -- | -- | |
Apertus 8B Instruct | 65.5k | Swiss AI Initiative | 1* | -- | -- | -- | -- | |
Granite 4.0 H 350M | 32.8k | IBM | 1* | -- | -- | -- | -- | |
Claude Sonnet 5 (low) | 1M | Anthropic | -- | -- | 60 | 2.15 | 10.44 | |
EXAONE 4.5 33B | 262k | LG AI Research | -- | -- | -- | -- | -- | |
Claude Sonnet 5 (xhigh) | 1M | Anthropic | -- | -- | 72 | 29.15 | 36.12 | |
Gemini 3 Deep Think | 128k | Google | -- | -- | -- | -- | -- | |
Claude Sonnet 5 (high) | 1M | Anthropic | -- | -- | 71 | 17.16 | 24.25 | |
GPT-5.5 Pro (xhigh) | 922k | OpenAI | -- | -- | -- | -- | -- | |
Cogito v2.1 | 128k |  Deep Cogito | -- | -- | -- | -- | -- | |
Claude Sonnet 5 (medium) | 1M | Anthropic | -- | -- | 71 | 2.71 | 9.76 | |
主要な定義
よくある質問
現在、Claude Opus 5 (Adaptive Reasoning, Max Effort)がIntelligence Indexスコア63でArtificial Analysis LLM Leaderboardの1位です。順位付けの対象は171モデルです。
Intelligence Indexで上位のモデルは1位：Claude Opus 5 (Adaptive Reasoning, Max Effort)（63）, 2位：Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)（63）, 3位：Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)（62）, 4位：Claude Opus 5 (Adaptive Reasoning, High Effort)（61）, 5位：GPT-5.6 Sol (max)（61）です。
Celeris-1が毎秒1,572.8トークンで最速で、Mercury 2（963.0 t/s）、Gemini 2.5 Flash-Lite (Reasoning)（439.4 t/s）が続きます。
GPT-5.6 Luna (low)がIntelligence Indexのタスクあたり$0.01で最も低く、MiMo-V2.5（$0.01）、Llama 4 Scout（$0.01）が続きます。
Kimi K3 (max)がIntelligence Indexスコア60で、オープンウェイトモデルの最上位です。リーダーボードの全171モデル中、オープンウェイトモデルは91モデルです。
Intelligence Indexで上位のオープンウェイトモデルは1位：Kimi K3 (max)（60）, 2位：Qwen3.8 2.4T A95B（58）, 3位：DeepSeek V4 Pro 0813 (Reasoning, Max Effort)（53）です。
Claude Opus 5 (Adaptive Reasoning, Max Effort)がIntelligence Indexスコア63で、137推論モデルの首位です。推論モデルは回答前に拡張思考を行い、複雑な問題を解きます。
モデルの種類（推論／非推論）、オープン性（オープンウェイト／独自）、その他の条件で結果を絞り込めます。プロンプトオプションを調整し、入力長による性能の違いを確認することもできます。
リーダーボードのモデル名をクリックすると、知能、料金、速度、遅延などの詳細グラフを掲載した専用比較ページを表示できます。モデルごとにAPIプロバイダーを比較することもできます。 すべてのモデルを表示