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Gemini 4 Carbon (high)とClaude Opus 5.5 (max with fallback)で、Gemini 4 Carbon (medium)とClaude Opus 5.5 (xhigh with fallback)が続きます。
出力速度
最速のモデルはCeleris-1とK2 Horizon 375B A23Bで、Nemotron 3.5 Super VLとGemini 3.5 Flash-Liteが続きます。
遅延
遅延が最も短いモデルはNorth Mini CodeとCommand A+で、Qwen3.5 9B (non-reasoning)とNemotron 3 Nano (non-reasoning)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K2 Horizon 375B A23BとCommand A+で、GPT-6 Luna (low)とMistral Small 4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GPT-6 Sol (Daybreak Blue, max)で、Muse Wonder (max)とLing 3.1 Flash 1019が続きます。
詳細分析 | ||||||||
|---|---|---|---|---|---|---|---|---|
Gemini 4 Carbon (high) | 1M | Google | 59 | $7.76 | 94 | 152.52 | 157.83 | |
Claude Opus 5.5 (max with fallback) | 1M | Anthropic | 58 | $10.04 | 96 | 640.87 | 646.10 | |
Gemini 4 Carbon (medium) | 1M | Google | 58 | $6.59 | 87 | 16.18 | 21.96 | |
Claude Opus 5.5 (xhigh with fallback) | 1M | Anthropic | 57 | $6.05 | 80 | 113.98 | 120.20 | |
GPT-6 Astra (max) | 1M | OpenAI | 57 | $6.24 | 73 | 368.87 | 375.76 | |
GPT-6 Astra (xhigh) | 1M | OpenAI | 55 | $3.66 | 68 | 207.97 | 215.30 | |
GPT-6 Astra (high) | 1M | OpenAI | 55 | $3.24 | 63 | 118.09 | 126.00 | |
GPT-6.1 Sol (max) | 1M | OpenAI | 55 | $1.27 | 93 | 323.50 | 328.85 | |
Claude Sonnet 5.5 (max with fallback) | 1M | Anthropic | 54 | $10.02 | 140 | 509.20 | 512.77 | |
Gemini 4 Carbon (low) | 1M | Google | 54 | -- | -- | -- | -- | |
GPT-6.1 Sol (xhigh) | 1M | OpenAI | 52 | $0.76 | 78 | 166.70 | 173.09 | |
Claude Opus 5.5 (high with fallback) | 1M | Anthropic | 52 | $3.46 | 80 | 47.50 | 53.79 | |
GPT-6 Astra (medium) | 1M | OpenAI | 51 | $2.73 | 55 | 7.30 | 16.39 | |
GPT-6.1 Terra (max) | 1M | OpenAI | 51 | $0.96 | 110 | 279.05 | 283.58 | |
Gemini 4 Argon (high) | 1M | Google | 50 | $7.68 | 82 | 41.32 | 47.39 | |
GPT-6.1 Sol (high) | 1M | OpenAI | 50 | $0.59 | 71 | 79.60 | 86.64 | |
Muse Wonder Full (max) | 1M | Meta | 50 | -- | -- | -- | -- | |
Claude Fable 5.1 (xhigh with fallback) | 1M | Anthropic | 50 | $10.85 | 63 | 81.27 | 89.19 | |
Claude Sonnet 5.5 (xhigh with fallback) | 1M | Anthropic | 50 | $4.09 | 107 | 36.85 | 41.51 | |
Claude Fable 5.1 (max with fallback) | 1M | Anthropic | 49 | $12.99 | 70 | 253.12 | 260.31 | |
Claude Opus 5.5 (medium with fallback) | 1M | Anthropic | 48 | $2.45 | 81 | 22.61 | 28.82 | |
Claude Fable 5.1 (high with fallback) | 1M | Anthropic | 47 | $7.54 | 57 | 19.50 | 28.20 | |
GPT-6.1 Sol (medium) | 1M | OpenAI | 46 | $0.36 | 63 | 9.35 | 17.34 | |
Kimi K3.1 Pro | 1M |  Kimi | 46 | $3.68 | 31 | 3.43 | 83.43 | |
GPT-6.1 Terra (xhigh) | 1M | OpenAI | 45 | $0.40 | 100 | 69.43 | 74.42 | |
Muse Wonder (max) | 1.05M | Meta | 43 | $6.95 | 200 | 27.74 | 40.22 | |
GPT-6 Astra (low) | 1M | OpenAI | 43 | $1.42 | 54 | 2.76 | 11.97 | |
Claude Fable 5.1 (medium with fallback) | 1M | Anthropic | 43 | $5.56 | 58 | 15.84 | 24.52 | |
GPT-6.1 Terra (high) | 1M | OpenAI | 42 | $0.26 | 93 | 20.82 | 26.18 | |
Claude Sonnet 5.5 (high with fallback) | 1M | Anthropic | 41 | $1.64 | 108 | 15.00 | 19.64 | |
Claude Fable 5.1 (low with fallback) | 1M | Anthropic | 38 | $4.47 | 56 | 3.07 | 11.93 | |
GPT-6.1 Terra (medium) | 1M | OpenAI | 38 | $0.17 | 91 | 4.84 | 10.34 | |
Claude Haiku 5.5 (max) | 1M | Anthropic | 36 | $0.41 | 235 | 364.23 | 366.36 | |
Grok 4.7 (xhigh) | 500k |  SpaceXAI | 35 | $7.77 | 86 | 111.58 | 117.41 | |
Grok 4.7 (high) | 500k | SpaceXAI | 35 | $6.18 | 76 | 73.01 | 79.63 | |
GPT-6.1 Sol (low) | 1M | OpenAI | 35 | $0.16 | 62 | 2.52 | 10.55 | |
Claude Opus 5.5 (low with fallback) | 1M | Anthropic | 35 | $0.98 | 79 | 11.35 | 17.68 | |
Claude Haiku 5.5 (xhigh) | 1M | Anthropic | 34 | $0.25 | 194 | 65.94 | 68.53 | |
Qwen3.8 Max (0902) | 984k | Alibaba | 34 | $10.02 | 38 | 2.94 | 68.67 | |
DeepSeek V4.1 Flash 1017 (max) | 1M |  DeepSeek | 32 | $0.60 | 174 | 1.23 | 15.61 | |
GLM-5.3 (max) | 1M |  Z AI | 32 | $5.01 | 89 | 1.43 | 29.53 | |
Grok 4.7 (low) | 500k | SpaceXAI | 31 | $2.92 | 68 | 6.57 | 13.95 | |
Gemini 3.8 Flash (high) | 1M | Google | 31 | $7.77 | 137 | 26.19 | 29.85 | |
GPT-6.1 Terra (non-reasoning) | 1M | OpenAI | 30 | $0.23 | 91 | 0.94 | 6.44 | |
Claude Sonnet 5.5 (medium with fallback) | 1M | Anthropic | 30 | $0.78 | 101 | 1.23 | 6.16 | |
Gemini 3.8 Flash (medium) | 1M | Google | 30 | $6.26 | -- | -- | -- | |
MiMo-V2.6-Pro | 1M |  Xiaomi | 30 | $0.26 | 44 | 3.22 | 60.64 | |
Claude Haiku 5.5 (high) | 1M | Anthropic | 30 | $0.16 | 184 | 33.23 | 35.95 | |
Ling 3.1 Flash 1019 | 1.05M | InclusionAI | 29 | $3.19 | -- | -- | -- | |
GPT-6.1 Terra (low) | 1M | OpenAI | 29 | $0.07 | 91 | 1.57 | 7.07 | |
MiniMax-M3.1-Flash | 1M |  MiniMax | 29 | $0.49 | 124 | 0.88 | 21.11 | |
DeepSeek V4.1 Flash 1017 (high) | 1M | DeepSeek | 29 | -- | 203 | 0.95 | 13.25 | |
Step 5 Preview | 1M |  StepFun | 29 | $2.35 | 143 | 0.92 | 18.40 | |
GPT-6 Luna (max) | 1M | OpenAI | 28 | $0.15 | 117 | 121.69 | 125.96 | |
GLM-5.3-Flash | 1M | Z AI | 28 | $0.58 | 74 | 1.55 | 35.14 | |
MiMo-V2.6-Flash | 1M | Xiaomi | 27 | $0.13 | 36 | 2.63 | 71.77 | |
Mistral Large 4 (high) | 1M | Mistral | 26 | $2.06 | -- | -- | -- | |
Claude Sonnet 5.5 (low with fallback) | 1M | Anthropic | 25 | $0.51 | 106 | 1.20 | 5.93 | |
Muse Spark Open (xhigh) | 1.05M | Meta | 25 | $2.02 | 193 | 0.74 | 13.73 | |
Claude Haiku 5.5 (medium) | 1M | Anthropic | 25 | $0.09 | 176 | 14.14 | 16.98 | |
GPT-6 Luna (xhigh) | 1M | OpenAI | 23 | $0.10 | 127 | 39.36 | 43.29 | |
Mistral Large 4 (medium) | 1M | Mistral | 23 | $1.41 | -- | -- | -- | |
DeepSeek V4 Pro 0813 (max) | 1M | DeepSeek | 23 | $1.77 | 87 | 1.79 | 30.45 | |
GLM-5.3 (low) | 1M | Z AI | 23 | $1.57 | 88 | 1.64 | 30.20 | |
Gemini 3.8 Flash (low) | 1M | Google | 22 | -- | -- | -- | -- | |
GPT-6 Luna (high) | 1M | OpenAI | 21 | $0.07 | 121 | 29.08 | 33.21 | |
Nanbeige4.3-33B | 524k |  Nanbeige | 20 | -- | -- | -- | -- | |
Qwen3.8 27B (xhigh) | 256k | Alibaba | 20 | $3.53 | 40 | 4.02 | 65.98 | |
MiniMax-M3 | 1M | MiniMax | 19 | $1.29 | 116 | 0.73 | 22.25 | |
Claude Haiku 5.5 (low) | 1M | Anthropic | 19 | $0.04 | 167 | 8.96 | 11.96 | |
DeepSeek V4.1 Flash 1017 (non-reasoning) | 1M | DeepSeek | 19 | $0.43 | 185 | 1.40 | 4.11 | |
GPT-6 Luna (medium) | 1M | OpenAI | 18 | $0.04 | -- | -- | -- | |
K2 Horizon 375B A23B | 524k | Institute of Foundation Models | 18 | $0.00 | 665 | 2.36 | 6.12 | |
Beam 1.0 | 1.05M |  Reflection | 18 | $0.28 | 369 | 0.63 | 7.40 | |
Qwen3.8 27B (medium) | 256k | Alibaba | 17 | $2.16 | 48 | 4.02 | 56.34 | |
Qwen3.8 27B (low) | 256k | Alibaba | 16 | $1.91 | 48 | 4.11 | 55.95 | |
Nemotron 3.5 Super VL | 1M | NVIDIA | 14 | $0.54 | 468 | 0.72 | 6.06 | |
Inkling Small | 1M |  Thinking Machines | 13 | $0.20 | 232 | 1.59 | 12.34 | |
Inkling (xhigh) | 1M | Thinking Machines | 12 | $1.35 | 215 | 1.71 | 13.32 | |
Nemotron 3 Ultra | 262k | NVIDIA | 12 | $2.23 | 161 | 1.21 | 18.41 | |
Gemini 3.5 Flash-Lite | 1M | Google | 12 | $0.69 | 442 | 6.64 | 7.77 | |
Qwen3.8 27B (non-reasoning) | 256k | Alibaba | 10 | $3.77 | 46 | 4.05 | 15.02 | |
GPT-6 Luna (low) | 1M | OpenAI | 10 | $0.01 | 115 | 2.91 | 7.26 | |
GPT-6 Luna (non-reasoning) | 1M | OpenAI | 9 | $0.07 | 109 | 0.81 | 5.39 | |
Muse Glimmer (high) | 131k | Meta | 6 | $0.16 | 126 | 1.19 | 21.01 | |
Command A+ | 192k | Cohere | 6 | $0.00 | 176 | 0.46 | 14.64 | |
Nemotron 3.5 Lightning | 1M | NVIDIA | 6 | $0.29 | 293 | 0.57 | 9.11 | |
Granite 4.2 8B | 131k |  IBM | 5 | $0.04 | 61 | 0.92 | 41.82 | |
Granite 4.2 3B | 131k | IBM | 5 | -- | -- | -- | -- | |
Mistral Small 4 | 256k | Mistral | 4 | $0.04 | 170 | 0.80 | 15.52 | |
Nemotron 3 Nano 4B | 262k | NVIDIA | 2 | -- | -- | -- | -- | |
JT-35B-Flash | 256k |  China Mobile | -- | -- | -- | -- | -- | |
Qwen3.5 Omni Plus | 256k | Alibaba | -- | -- | 131 | 2.08 | 5.90 | |
Nova 2.0 Omni (medium) | 1M |  Amazon | -- | -- | -- | -- | -- | |
Qwen3.5 122B A10B (non-reasoning) | 262k | Alibaba | -- | -- | 141 | 2.32 | 5.87 | |
Gemma 4 12B (non-reasoning) | 262k | Google | -- | -- | 115 | 2.21 | 6.54 | |
Gemma 3 270M | 32k | Google | -- | -- | -- | -- | -- | |
Apodex 1.1 | 256k |  Apodex | -- | -- | -- | -- | -- | |
Qwen3.5 2B (non-reasoning) | 262k | Alibaba | -- | -- | -- | -- | -- | |
Qwen3 Omni 30B A3B | 65.5k | Alibaba | -- | -- | 95 | 1.85 | 7.13 | |
Nova 2.0 Pro Preview (medium) | 256k | Amazon | -- | -- | 127 | 12.73 | 32.44 | |
Qwen3.5 397B A17B | 262k | Alibaba | -- | -- | 57 | 2.23 | 66.84 | |
Granite 4.2 30B | 131k | IBM | -- | -- | -- | -- | -- | |
K2 Horizon 7B | 524k | Institute of Foundation Models | -- | -- | -- | -- | -- | |
Mistral Small 4 (non-reasoning) | 256k | Mistral | -- | -- | 163 | 0.85 | 3.91 | |
Solar Pro 4 | 512k |  Upstage | -- | -- | 100 | 1.95 | 27.07 | |
gpt-oss-20b (low) | 131k | OpenAI | -- | -- | 253 | 0.76 | 10.66 | |
o3 | 200k | OpenAI | -- | -- | 163 | 6.80 | 9.86 | |
K-EXAONE 2.0 | 262k |  LG AI Research | -- | -- | -- | -- | -- | |
North Mini Code | 256k | Cohere | -- | -- | 87 | 0.43 | 29.04 | |
Nova 2.0 Omni (non-reasoning) | 1M | Amazon | -- | -- | -- | -- | -- | |
Granite 4.0 Micro | 128k | IBM | -- | -- | -- | -- | -- | |
Qwen3.5 9B (non-reasoning) | 262k | Alibaba | -- | -- | 92 | 0.52 | 5.94 | |
Qwen3.5 122B A10B | 262k | Alibaba | -- | -- | 130 | 2.31 | 21.60 | |
Hermes 4 70B (non-reasoning) | 128k |  Nous Research | -- | -- | -- | -- | -- | |
Nemotron 3 Nano (non-reasoning) | 1M | NVIDIA | -- | -- | 270 | 0.54 | 2.39 | |
Qwen3 Next 80B A3B | 262k | Alibaba | -- | -- | 183 | 0.89 | 3.61 | |
Phi-4 Multimodal | 128k |  Microsoft | -- | -- | -- | -- | -- | |
Qwen3.5 9B | 262k | Alibaba | -- | -- | 62 | 1.60 | 41.79 | |
NVIDIA Nemotron Nano 9B V2 (non-reasoning) | 131k | NVIDIA | -- | -- | 169 | 1.01 | 3.96 | |
EXAONE 4.0 32B (non-reasoning) | 131k | LG AI Research | -- | -- | -- | -- | -- | |
G9v3-3B | 131k |  AI9Stars | -- | -- | -- | -- | -- | |
Qwen3.5 4B (non-reasoning) | 262k | Alibaba | -- | -- | 22 | 0.85 | 23.88 | |
Qwen3.5 397B A17B (non-reasoning) | 262k | Alibaba | -- | -- | 59 | 2.22 | 10.72 | |
K2 Horizon 3.7B | 524k | Institute of Foundation Models | -- | -- | -- | -- | -- | |
Olmo 3 7B Think | 65.5k |  Allen Institute for AI | -- | -- | -- | -- | -- | |
HyperCLOVA X SEED Think (32B) | 128k |  Naver | -- | -- | -- | -- | -- | |
HyperNova 60B 2605 (high) | 131k |  Multiverse Computing | -- | -- | -- | -- | -- | |
Nova Micro | 130k | Amazon | -- | -- | 277 | 0.78 | 2.58 | |
EXAONE 4.5 33B (non-reasoning) | 262k | LG AI Research | -- | -- | -- | -- | -- | |
INTELLECT-3 | 131k |  Prime Intellect | -- | -- | -- | -- | -- | |
gpt-oss-20b (high) | 131k | OpenAI | -- | -- | 171 | 0.71 | 15.32 | |
Olmo 3.1 32B Think | 65.5k | Allen Institute for AI | -- | -- | -- | -- | -- | |
Nex-N2-Pro | 262k |  Nex AGI | -- | -- | -- | -- | -- | |
Command A | 256k | Cohere | -- | -- | 14 | 2.30 | 36.85 | |
LFM2.5-VL-1.6B | 32k |  Liquid AI | -- | -- | -- | -- | -- | |
JT-MINI | 128k | China Mobile | -- | -- | -- | -- | -- | |
Molmo2-8B | 36.9k | Allen Institute for AI | -- | -- | -- | -- | -- | |
Qwen3.5 0.8B (non-reasoning) | 262k | Alibaba | -- | -- | -- | -- | -- | |
Ling-3.0-flash-VL | 262k | InclusionAI | -- | -- | -- | -- | -- | |
MiniCPM-V 4.6 1.3B | 262k |  OpenBMB | -- | -- | -- | -- | -- | |
EXAONE 4.0 32B | 131k | LG AI Research | -- | -- | -- | -- | -- | |
Sarvam 105B (high) | 128k |  Sarvam | -- | -- | 136 | 1.64 | 20.03 | |
Llama 3.1 405B | 128k | Meta | -- | -- | -- | -- | -- | |
JT-4.1 Flash 236B A21B | 262k | China Mobile | -- | -- | -- | -- | -- | |
Ring-flash-2.0 | 128k | InclusionAI | -- | -- | -- | -- | -- | |
LFM2.5-1.2B-Instruct | 32k | Liquid AI | -- | -- | -- | -- | -- | |
Apertus 70B Instruct | 65.5k |  Swiss AI Initiative | -- | -- | -- | -- | -- | |
Doubao Seed Code | 256k |  ByteDance Seed | -- | -- | -- | -- | -- | |
EXAONE 4.5 33B | 262k | LG AI Research | -- | -- | -- | -- | -- | |
Gemma 4 E4B (non-reasoning) | 128k | Google | -- | -- | 52 | 0.78 | 10.43 | |
K2 Horizon MoVA 36B A4B | 524k | Institute of Foundation Models | -- | -- | -- | -- | -- | |
Granite 4.0 350M | 32.8k | IBM | -- | -- | -- | -- | -- | |
Kimi Linear 48B A3B Instruct | 1M | Kimi | -- | -- | -- | -- | -- | |
Solar Open 100B | 128k | Upstage | -- | -- | -- | -- | -- | |
GPT-5.3 Codex (xhigh) | 400k | OpenAI | -- | -- | 114 | 68.87 | 73.27 | |
LFM2.5-1.2B-Thinking | 32k | Liquid AI | -- | -- | -- | -- | -- | |
K2 Think V2 | 262k | Institute of Foundation Models | -- | -- | -- | -- | -- | |
LongCat 2.0 | 1M |  LongCat | -- | -- | 76 | 2.73 | 35.73 | |
Qwen3.5 2B | 262k | Alibaba | -- | -- | -- | -- | -- | |
Tri-21B-Think | 32k |  Trillion Labs | -- | -- | -- | -- | -- | |
Granite 4.0 H Small | 128k | IBM | -- | -- | -- | -- | -- | |
Llama 3.2 11B (Vision) | 128k | Meta | -- | -- | 24 | 1.50 | 22.41 | |
LongCat Flash Lite | 256k | LongCat | -- | -- | -- | -- | -- | |
Nemotron 3.5 Bolt E4B 4GB | 131k | NVIDIA | -- | -- | -- | -- | -- | |
Nova 2.0 Lite (high) | 1M | Amazon | -- | -- | 178 | 18.01 | 32.04 | |
Solar Mini 4 | 1.05M | Upstage | -- | -- | 103 | 2.05 | 26.20 | |
MiniCPM5-2B | 131k | OpenBMB | -- | -- | -- | -- | -- | |
Qwen3.5 4B | 262k | Alibaba | -- | -- | 22 | 0.82 | 114.54 | |
Motif-2-12.7B | 128k |  Motif Technologies | -- | -- | -- | -- | -- | |
Qwen3.6 35B A3B (non-reasoning) | 262k | Alibaba | -- | -- | 147 | 2.08 | 5.48 | |
Ministral 3 3B | 256k | Mistral | -- | -- | 175 | 0.78 | 3.64 | |
Hermes 4 70B | 128k | Nous Research | -- | -- | -- | -- | -- | |
Ling-3.0-flash-Fin | 262k | InclusionAI | -- | -- | -- | -- | -- | |
Gemma 4 26B A4B | 256k | Google | -- | -- | 109 | 0.93 | 23.78 | |
NVIDIA Nemotron Nano 12B v2 VL | 128k | NVIDIA | -- | -- | -- | -- | -- | |
Qwen3.5 Omni Flash | 256k | Alibaba | -- | -- | 239 | 1.79 | 3.88 | |
Nova 2.0 Lite (low) | 1M | Amazon | -- | -- | 193 | 8.31 | 21.28 | |
Magistral Small 1.2 | 128k | Mistral | -- | -- | 74 | 1.50 | 35.40 | |
Gemma 4 26B A4B (non-reasoning) | 256k | Google | -- | -- | 125 | 0.92 | 4.90 | |
Ministral 3 14B | 256k | Mistral | -- | -- | 62 | 0.99 | 9.05 | |
Gemma 4 E2B (non-reasoning) | 128k | Google | -- | -- | -- | -- | -- | |
Sarvam 30B (high) | 65.5k | Sarvam | -- | -- | -- | -- | -- | |
Mercury 2.5 | 260k |  Inception | -- | -- | -- | -- | -- | |
Nova 2.0 Lite (non-reasoning) | 1M | Amazon | -- | -- | 177 | 1.02 | 3.85 | |
Nemotron 3 Nano | 1M | NVIDIA | -- | -- | 242 | 0.94 | 11.28 | |
DeepSeek V4 Flash Vision (max) | 1M | DeepSeek | -- | -- | 159 | 1.61 | 17.34 | |
MiniCPM5-1B | 128k | OpenBMB | -- | -- | -- | -- | -- | |
Jamba 1.7 Large | 256k |  AI21 Labs | -- | -- | -- | -- | -- | |
Nemotron 3.5 Bolt 74B-A9B | 262k | NVIDIA | -- | -- | -- | -- | -- | |
Nanbeige4.1-3B | 256k | Nanbeige | -- | -- | -- | -- | -- | |
Solar Open2 250B | 1.05M | Upstage | -- | -- | -- | -- | -- | |
Ling 3.0 Tiny | 262k | InclusionAI | -- | -- | 58 | 2.59 | 45.99 | |
Celeris-1 | 131k | Celeris | -- | -- | 1,638 | 0.55 | 0.86 | |
Tiny Aya Global | 8.19k | Cohere | -- | -- | -- | -- | -- | |
A.X-K2 | 262k |  SK Telecom | -- | -- | -- | -- | -- | |
Exaone 4.0 1.2B (non-reasoning) | 64k | LG AI Research | -- | -- | -- | -- | -- | |
Hermes 4 405B | 128k | Nous Research | -- | -- | 41 | 2.33 | 63.01 | |
Magistral Medium 1.2 | 128k | Mistral | -- | -- | -- | -- | -- | |
Qwen3.6 35B A3B | 262k | Alibaba | -- | -- | 134 | 2.04 | 46.08 | |
Apertus 8B Instruct | 65.5k | Swiss AI Initiative | -- | -- | -- | -- | -- | |
Nemotron 3 Nano Omni 30B A3B | 256k | NVIDIA | -- | -- | 230 | 0.84 | 11.72 | |
Kimi K2.7 Code | 256k | Kimi | -- | -- | 46 | 2.84 | 62.55 | |
Qwen3.8 2.4T A95B | 262k | Alibaba | -- | -- | 38 | 3.04 | 68.15 | |
Olmo 3 7B | 65.5k | Allen Institute for AI | -- | -- | -- | -- | -- | |
JT-4.1 Flash 236B A21B (non-reasoning) | 262k | China Mobile | -- | -- | -- | -- | -- | |
Llama 4 Maverick | 1M | Meta | -- | -- | 63 | 0.97 | 8.94 | |
GPT-6 Sol (Daybreak Blue, max) | 1.05M | OpenAI | -- | -- | -- | -- | -- | |
Olmo 3.1 32B Instruct | 65.5k | Allen Institute for AI | -- | -- | -- | -- | -- | |
Ministral 3 8B | 256k | Mistral | -- | -- | 108 | 0.97 | 5.58 | |
Llama 3.3 70B | 128k | Meta | -- | -- | 92 | 1.81 | 7.25 | |
Nemotron Cascade 2 30B A3B | 1M | NVIDIA | -- | -- | -- | -- | -- | |
R1 1776 | 128k |  Perplexity | -- | -- | -- | -- | -- | |
Qwen3.8-Flash-Next | 256k | Alibaba | -- | -- | 52 | 2.30 | 50.07 | |
Llama 3.2 90B (Vision) | 128k | Meta | -- | -- | -- | -- | -- | |
K2 Horizon 0.9B | 131k | Institute of Foundation Models | -- | -- | -- | -- | -- | |
Phi-4 Mini | 128k | Microsoft | -- | -- | 45 | 0.84 | 12.01 | |
Nova 2.0 Pro Preview (non-reasoning) | 256k | Amazon | -- | -- | 126 | 1.12 | 5.10 | |
K2-V2 (high) | 512k | Institute of Foundation Models | -- | -- | -- | -- | -- | |
Gemini 3 Deep Think | 128k | Google | -- | -- | -- | -- | -- | |
ERNIE 5.0 Thinking Preview | 128k |  Baidu | -- | -- | -- | -- | -- | |
Ling 3.1 Flash | 1M | InclusionAI | -- | -- | 218 | 1.84 | 13.32 | |
Granite 4.0 H 350M | 32.8k | IBM | -- | -- | -- | -- | -- | |
Qwen3.5 0.8B | 262k | Alibaba | -- | -- | -- | -- | -- | |
Apriel-v1.6-15B-Thinker | 128k |  ServiceNow | -- | -- | -- | -- | -- | |
Qwen3.7 Plus | 1M | Alibaba | -- | -- | 57 | 2.40 | 46.00 | |
DeepHermes 3 - Mistral 24B (non-reasoning) | 32k | Nous Research | -- | -- | -- | -- | -- | |
NVIDIA Nemotron Nano 12B v2 VL (non-reasoning) | 128k | NVIDIA | -- | -- | 199 | 1.03 | 3.55 | |
Step3 VL 10B | 65.5k | StepFun | -- | -- | -- | -- | -- | |
Llama 4 Scout | 10M | Meta | -- | -- | 94 | 0.83 | 6.14 | |
ERNIE 4.5 300B A47B | 131k | Baidu | -- | -- | -- | -- | -- | |
Molmo 7B-D | 4.1k | Allen Institute for AI | -- | -- | -- | -- | -- | |
Motif 3 | 262k | Motif Technologies | -- | -- | -- | -- | -- | |
Gemma 4 E2B | 128k | Google | -- | -- | -- | -- | -- | |
Hy3 | 256k |  Tencent | -- | -- | 95 | 2.77 | 29.06 | |
Nova 2.0 Omni (low) | 1M | Amazon | -- | -- | -- | -- | -- | |
Jamba 1.7 Mini | 258k | AI21 Labs | -- | -- | -- | -- | -- | |
Trinity Large Thinking | 512k |  Arcee AI | -- | -- | -- | -- | -- | |
DeepHermes 3 - Llama-3.1 8B (non-reasoning) | 128k | Nous Research | -- | -- | -- | -- | -- | |
Qwen3 Omni 30B A3B | 65.5k | Alibaba | -- | -- | 98 | 1.87 | 27.39 | |
Gemini 3.1 Pro Preview | 1M | Google | -- | -- | 143 | 22.20 | 25.70 | |
G9v3-39A5B | 131k | AI9Stars | -- | -- | -- | -- | -- | |
DiffusionGemma 26B A4B | 256k | Google | -- | -- | -- | -- | -- | |
GPT-5.5 Instant (June 2026) | 400k | OpenAI | -- | -- | 158 | 0.88 | 16.72 | |
Falcon-H1R-7B | 256k |  TII UAE | -- | -- | -- | -- | -- | |
Qwen3 Next 80B A3B | 262k | Alibaba | -- | -- | -- | -- | -- | |
gpt-oss-120b (low) | 131k | OpenAI | -- | -- | 260 | 0.75 | 10.37 | |
Gemma 4 31B | 256k | Google | -- | -- | 35 | 1.07 | 64.69 | |
Llama Nemotron Ultra | 128k | NVIDIA | -- | -- | -- | -- | -- | |
Gemma 4 31B (non-reasoning) | 256k | Google | -- | -- | 60 | 1.86 | 10.21 | |
MiniCPM5-1B (non-reasoning) | 128k | OpenBMB | -- | -- | -- | -- | -- | |
Hermes 4 405B (non-reasoning) | 128k | Nous Research | -- | -- | 43 | 2.31 | 13.97 | |
DeepSeek V4 Pro 0813 (non-reasoning) | 1M | DeepSeek | -- | -- | 94 | 1.76 | 7.07 | |
Exaone 4.0 1.2B | 64k | LG AI Research | -- | -- | -- | -- | -- | |
Gemma 4 E4B | 128k | Google | -- | -- | 51 | 0.80 | 49.36 | |
K2-V2 (low) | 512k | Institute of Foundation Models | -- | -- | -- | -- | -- | |
Granite 4.0 H 1B | 128k | IBM | -- | -- | -- | -- | -- | |
Reka Flash 3 | 128k |  Reka AI | -- | -- | 90 | 1.39 | 29.25 | |
Mistral Medium 3.5 | 256k | Mistral | -- | -- | 179 | 2.45 | 16.42 | |
K2-V2 (medium) | 512k | Institute of Foundation Models | -- | -- | -- | -- | -- | |
Mi:dm K 2.5 Pro | 128k |  Korea Telecom | -- | -- | -- | -- | -- | |
LFM2.5-2.6B | 128k | Liquid AI | -- | -- | -- | -- | -- | |
LFM2.5-8B-A1B | 32.8k | Liquid AI | -- | -- | -- | -- | -- | |
GPT-5.5 Pro (xhigh) | 922k | OpenAI | -- | -- | -- | -- | -- | |
Nova Premier | 1M | Amazon | -- | -- | -- | -- | -- | |
Cogito v2.1 | 128k |  Deep Cogito | -- | -- | -- | -- | -- | |
Ring-2.6-1T | 262k | InclusionAI | -- | -- | 126 | 3.84 | 23.69 | |
Phi-4 | 16k | Microsoft | -- | -- | 42 | 2.41 | 14.39 | |
gpt-oss-120b (high) | 131k | OpenAI | -- | -- | 212 | 0.75 | 12.57 | |
NVIDIA Nemotron Nano 9B V2 | 131k | NVIDIA | -- | -- | 244 | 0.56 | 10.81 | |
Agnes 2.5 Pro Beta | 1M |  Sapiens AI | -- | -- | -- | -- | -- | |
Nova 2.0 Pro Preview (low) | 256k | Amazon | -- | -- | 133 | 10.39 | 29.16 | |
Jamba Reasoning 3B | 262k | AI21 Labs | -- | -- | -- | -- | -- | |
Quasar 438B (max) | 1M | Multiverse Computing | -- | -- | 173 | 1.31 | 15.73 | |
LFM2 24B A2B | 32.8k | Liquid AI | -- | -- | -- | -- | -- | |
Nova 2.0 Lite (medium) | 1M | Amazon | -- | -- | 192 | 18.71 | 31.72 | |
KAT-Coder-Pro V2 | 256k |  KwaiKAT | -- | -- | -- | -- | -- | |
Qwen3 Coder Next | 256k | Alibaba | -- | -- | 80 | 0.91 | 7.15 | |
Gemma 4 12B | 262k | Google | -- | -- | 118 | 2.25 | 23.45 | |
主要な定義
よくある質問
現在、Gemini 4 Carbon (High)がIntelligence Indexスコア59でArtificial Analysis LLM Leaderboardの1位です。順位付けの対象は91モデルです。
Intelligence Indexで上位のモデルは1位：Gemini 4 Carbon (High)（59）, 2位：Claude Opus 5.5 (Max, Default Fallback)（58）, 3位：Gemini 4 Carbon (Medium)（58）, 4位：Claude Opus 5.5 (Xhigh, Default Fallback)（57）, 5位：GPT-6 Astra (Max)（57）です。
Celeris-1が毎秒1,638.5トークンで最速で、K2 Horizon 375B A23B（664.6 t/s）、Nemotron 3.5 Super VL（467.8 t/s）が続きます。
K2 Horizon 375B A23BがIntelligence Indexのタスクあたり$0.00で最も低く、Command A+（$0.00）、GPT-6 Luna (Low)（$0.01）が続きます。
DeepSeek V4.1 Flash 1017 (Max)がIntelligence Indexスコア32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91モデル中、オープンウェイトモデルは34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：DeepSeek V4.1 Flash 1017 (Max)（32）, 2位：GLM-5.3 (Max)（32）, 3位：MiMo-V2.6-Pro（30）です。
Gemini 4 Carbon (High)がIntelligence Indexスコア59で、87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