Category ranking
Best LLMs for Instruction Following in October 2026
As of October 2026, GPT-5.1 leads the Noometry instruction following ranking with a score of 83.9, ahead of Gemini 4 Argon at 80.1.
Last verified
Following explicit formatting, length and content constraints exactly.
- GPT-5.1 83.9
- Gemini 4 Argon 80.1
- Claude Opus 5.5 80.0
- Claude Opus 4.6 79.5
- Grok 4 79.2
- Claude Fable 5.1 79.2
- Claude Opus 5 79.2
- Claude Fable 5 78.6
- Grok-3 mini 78.5
- Claude Opus 4.7 78.4
Full ranking
305 models
| 1 | OpenAI GPT-5.1 | OpenAI | Proprietary | 400K | 83.9 | $1.25 | $10 | — |
| 2 |  Google Gemini 4 Argon | Proprietary | — | 80.1 | — | — | — | |
| 3 | Anthropic Claude Opus 5.5 | Anthropic | Proprietary | 1M | 80.0 | $4 | $20 | — |
| 4 | Anthropic Claude Opus 4.6 | Anthropic | Proprietary | 1M | 79.5 | $5 | $25 | 19 |
| 5 | xAI Grok 4 | xAI | Proprietary | — | 79.2 | — | — | 1 |
| 6 | Anthropic Claude Fable 5.1 | Anthropic | Proprietary | 1M | 79.2 | $10 | $50 | — |
| 7 | Anthropic Claude Opus 5 | Anthropic | Proprietary | 1M | 79.2 | $5 | $25 | — |
| 8 | Anthropic Claude Fable 5 | Anthropic | Proprietary | 1M | 78.6 | $10 | $50 | 25 |
| 9 | xAI Grok-3 mini | xAI | Proprietary | — | 78.5 | — | — | 10 |
| 10 | Anthropic Claude Opus 4.7 | Anthropic | Proprietary | 1M | 78.4 | $5 | $25 | 33 |
| 11 | Anthropic Claude Sonnet 5.5 | Anthropic | Proprietary | 1M | 78.3 | $2 | $10 | — |
| 12 | Xiaomi MiMo-V2.6-Pro | Xiaomi | Open | 1.05M | 78.2 | $0.43 | $0.87 | — |
| 13 | Google Gemini 3.8 Flash | Proprietary | 1.05M | 78.0 | $0.75 | $3.75 | — | |
| 14 | Moonshot AI Kimi K3 | Moonshot AI | Open | 1.05M | 77.7 | $3 | $15 | — |
| 15 | Google Gemini 3.7 Flash | Proprietary | 1.05M | 77.7 | $0.75 | $3.75 | — | |
| 16 | OpenAI GPT-5.6 Sol | OpenAI | Proprietary | 1.05M | 77.7 | $4 | $20 | 10 |
| 17 |  Alibaba (Qwen) Qwen3.8 Max | Alibaba (Qwen) | Proprietary | 1M | 77.6 | $2 | $6 | — |
| 18 | OpenAI GPT-5.5 | OpenAI | Proprietary | 1.05M | 77.5 | $5 | $30 | 25 |
| 19 | Anthropic Claude Opus 4.5 | Anthropic | Proprietary | 200K | 77.5 | $5 | $25 | 13 |
| 20 | Z.ai (Zhipu) GLM-5.3-Flash | Z.ai (Zhipu) | Open | 1M | 77.5 | $0.15 | $0.50 | — |
| 21 |  Meta Muse Spark 1.3 | Meta | Proprietary | 1.05M | 77.5 | $1.25 | $4.25 | — |
| 22 | Xiaomi MiMo-V2.5-Pro | Xiaomi | Open | 1.05M | 77.5 | $0.43 | $0.87 | — |
| 23 | Z.ai (Zhipu) GLM-5.3 | Z.ai (Zhipu) | Open | 1M | 77.5 | $1.40 | $4.40 | — |
| 24 | Anthropic Claude Opus 4.8 | Anthropic | Proprietary | 1M | 77.4 | $5 | $25 | 34 |
| 25 | Anthropic Claude Sonnet 4.6 | Anthropic | Proprietary | 1M | 77.4 | $3 | $15 | — |
| 26 |  DeepSeek DeepSeek V4.1 Flash | DeepSeek | Open | 1M | 77.3 | $0.15 | $0.60 | — |
| 27 | OpenAI GPT-5.4 | OpenAI | Proprietary | 1.05M | 77.1 | $2.50 | $15 | 12 |
| 28 | Anthropic Claude Opus 4 | Anthropic | Proprietary | 200K | 77.1 | $15 | $75 | 29 |
| 29 | OpenAI GPT-6.1 Sol | OpenAI | Proprietary | 1.05M | 77.0 | $2 | $10 | — |
| 30 | Google Gemini 3.5 Flash | Proprietary | 1.05M | 77.0 | $1.50 | $9 | — | |
| 31 | Alibaba (Qwen) Qwen3.5 Max Preview | Alibaba (Qwen) | Proprietary | — | 77.0 | — | — | — |
| 32 | Google Gemini 3.1 Pro Preview | Proprietary | 1.05M | 77.0 | $2 | $12 | — | |
| 33 | Google Gemini 3.6 Flash | Proprietary | 1.05M | 77.0 | $0.75 | $3.75 | — | |
| 34 | Z.ai (Zhipu) GLM-5.2 | Z.ai (Zhipu) | Open | 1M | 76.9 | $1.40 | $4.40 | 23 |
| 35 | Xiaomi MiMo-V2.6-Flash | Xiaomi | Open | 1.05M | 76.8 | $0.14 | $0.28 | — |
| 36 | Meta Muse Spark 1.2 | Meta | Proprietary | 1.05M | 76.7 | $1.25 | $4.25 | — |
| 37 |  Baidu ERNIE 5.1 | Baidu | Proprietary | — | 76.7 | — | — | — |
| 38 | Alibaba (Qwen) Qwen3.7 Max | Alibaba (Qwen) | Proprietary | 1M | 76.7 | $2.50 | $7.50 | — |
| 39 | Meta Muse Spark 1.1 | Meta | Proprietary | 1.05M | 76.5 | $1.25 | $4.25 | — |
| 40 | OpenAI GPT-5.6 Terra | OpenAI | Proprietary | 1.05M | 76.4 | $2 | $12 | 11 |
| 41 | Anthropic Claude Sonnet 5 | Anthropic | Proprietary | 1M | 76.3 | $2 | $10 | — |
| 42 | Z.ai (Zhipu) GLM-5.1 | Z.ai (Zhipu) | Open | 200K | 76.3 | $1.40 | $4.40 | — |
| 43 | Moonshot AI Kimi K2.6 | Moonshot AI | Open | 262K | 76.3 | $0.95 | $4 | — |
| 44 | OpenAI GPT-6 Astra | OpenAI | Proprietary | 1.05M | 76.3 | $10 | $50 | — |
| 45 | Google Gemini 3 Pro | Proprietary | — | 76.3 | — | — | 1 | |
| 46 | OpenAI GPT-5 Mini | OpenAI | Proprietary | 400K | 76.2 | $0.25 | $2 | 3 |
| 47 | DeepSeek DeepSeek V4 Pro | DeepSeek | Open | 1M | 76.1 | $0.66 | $1.98 | 16 |
| 48 | xAI Grok 4.5 | xAI | Proprietary | 500K | 76.0 | $2 | $6 | 4 |
| 49 | Xiaomi MiMo-V2-Pro | Xiaomi | Proprietary | 1.05M | 76.0 | $0.43 | $0.87 | — |
| 50 |  StepFun Step 5 Preview | StepFun | Proprietary | 1.02M | 76.0 | $1 | $2.70 | — |
| 51 | Meta Muse Spark | Meta | Proprietary | — | 75.9 | — | — | — |
| 52 | Alibaba (Qwen) Qwen3.7 Plus | Alibaba (Qwen) | Proprietary | 1M | 75.8 | $0.40 | $1.60 | — |
| 53 | Alibaba (Qwen) Qwen3.8 27B | Alibaba (Qwen) | Open | 262K | 75.8 | $0.99 | $1.49 | — |
| 54 | Google Gemini 2.5 Flash | Proprietary | 1.05M | 75.7 | $0.30 | $2.50 | 152 | |
| 55 | Alibaba (Qwen) Qwen3.6 Max Preview | Alibaba (Qwen) | Proprietary | 262K | 75.7 | $1.30 | $7.80 | — |
| 56 | Google Gemini 3 Flash Preview | Proprietary | 1.05M | 75.7 | $0.50 | $3 | — | |
| 57 | OpenAI GPT-5.6 Luna | OpenAI | Proprietary | 1.05M | 75.6 | $0.20 | $1.20 | 12 |
| 58 | Anthropic Claude Opus 4.1 | Anthropic | Proprietary | 200K | 75.6 | $15 | $75 | — |
| 59 | Xiaomi MiMo-V2.5 | Xiaomi | Open | 1.05M | 75.5 | $0.14 | $0.28 | — |
| 60 | Google Gemini 2.0 Pro | Proprietary | — | 75.5 | — | — | — | |
| 61 |  MiniMax MiniMax-M3 | MiniMax | Open | 1M | 75.5 | $0.30 | $1.20 | — |
| 62 | Google Gemma 4 31B IT | Open | 262K | 75.5 | $0.09 | $0.34 | 3 | |
| 63 | xAI Grok 4.6 | xAI | Proprietary | 500K | 75.4 | $2 | $6 | — |
| 64 | Moonshot AI Kimi K2.5 | Moonshot AI | Open | 262K | 75.3 | $0.45 | $2.25 | 66 |
| 65 | Moonshot AI Kimi K2.5 Instant | Moonshot AI | Open | — | 75.3 | — | — | — |
| 66 | Xiaomi MiMo-V2-Omni | Xiaomi | Proprietary | 262K | 75.2 | $0.14 | $0.28 | — |
| 67 | Z.ai (Zhipu) GLM-5 | Z.ai (Zhipu) | Open | 205K | 75.2 | $1 | $3.20 | 23 |
| 68 | OpenAI o4-mini | OpenAI | Proprietary | 200K | 75.2 | $1.10 | $4.40 | 6 |
| 69 | Amazon Amazon Nova Experimental Chat 26 02 10 | Amazon | Proprietary | — | 75.2 | — | — | — |
| 70 |  Tencent Hy3 | Tencent | Open | 262K | 75.1 | $0.0825 | $0.33 | — |
| 71 | Thinking Machines Lab Inkling | Thinking Machines Lab | Open | 66K | 75.1 | $1.87 | $4.68 | — |
| 72 | OpenAI o3-mini | OpenAI | Proprietary | 200K | 75.1 | $1.10 | $4.40 | — |
| 73 | Alibaba (Qwen) Qwen3.6 Plus | Alibaba (Qwen) | Proprietary | 1M | 75.0 | $0.50 | $3 | — |
| 74 | xAI Grok 3 | xAI | Proprietary | — | 75.0 | — | — | 42 |
| 75 | Google Gemini 2.5 Pro | Proprietary | 1.05M | 75.0 | $1.25 | $10 | 5 | |
| 76 |  Mistral AI Mistral Large 4 | Mistral AI | Proprietary | 1.05M | 75.0 | $0.68 | $2.09 | — |
| 77 | Alibaba (Qwen) Qwen3.5 397B-A17B | Alibaba (Qwen) | Open | 262K | 75.0 | $0.60 | $3.60 | 9 |
| 78 | Anthropic Claude Sonnet 4.5 | Anthropic | Proprietary | 200K | 75.0 | $3 | $15 | 85 |
| 79 | OpenAI GPT-5 Nano | OpenAI | Proprietary | 400K | 75.0 | $0.05 | $0.40 | 4 |
| 80 | Z.ai (Zhipu) GLM-5V-Turbo | Z.ai (Zhipu) | Proprietary | 200K | 75.0 | $1.20 | $4 | — |
| 81 | DeepSeek DeepSeek V4 Flash | DeepSeek | Open | 1M | 74.9 | $0.15 | $0.60 | 6 |
| 82 | xAI Grok 4.20 (Non-Reasoning) | xAI | Proprietary | 1M | 74.8 | $1.25 | $2.50 | 61 |
| 83 | Google Gemma 4 26B A4B IT | Open | 262K | 74.8 | $0.0675 | $0.23 | — | |
| 84 | xAI Grok 4.20 Multi-Agent | xAI | Proprietary | 1M | 74.8 | $1.25 | $2.50 | — |
| 85 | Google Gemini 3.5 Flash Lite | Proprietary | 1.05M | 74.8 | $0.30 | $2.50 | — | |
| 86 | Alibaba (Qwen) Qwen3 Max | Alibaba (Qwen) | Proprietary | 262K | 74.8 | $1.20 | $6 | 48 |
| 87 | OpenAI o1 | OpenAI | Proprietary | 200K | 74.8 | $15 | $60 | — |
| 88 |  NVIDIA Nemotron 3 Ultra | NVIDIA | Open | 262K | 74.7 | $0.50 | $2.20 | — |
| 89 | OpenAI GPT-5.2 | OpenAI | Proprietary | 400K | 74.7 | $1.75 | $14 | 15 |
| 90 | Mistral AI Mistral Medium 3.5 | Mistral AI | Open | 262K | 74.6 | $1.50 | $7.50 | 50 |
| 91 |  ByteDance Seed Seed 2.0 Pro | ByteDance Seed | Proprietary | 256K | 74.5 | $0.50 | $3 | — |
| 92 | Baidu ERNIE 5.0 0110 | Baidu | Proprietary | — | 74.5 | — | — | — |
| 93 | DeepSeek DeepSeek-V3.2-Exp | DeepSeek | Open | 164K | 74.5 | $0.26 | $0.38 | 16 |
| 94 | OpenAI GPT-6 Sol | OpenAI | Proprietary | 1.05M | 74.5 | $2 | $10 | — |
| 95 | Z.ai (Zhipu) GLM-4.7 | Z.ai (Zhipu) | Open | 205K | 74.4 | $0.60 | $2.20 | — |
| 96 | Meituan Longcat Flash Chat | Meituan | Open | — | 74.4 | — | — | 69 |
| 97 | Google Gemini 2.0 Flash (Feb 2025) | Proprietary | — | 74.4 | — | — | 92 | |
| 98 | Z.ai (Zhipu) GLM-4.6 | Z.ai (Zhipu) | Open | 205K | 74.3 | $0.60 | $2.20 | 12 |
| 99 | OpenAI GPT-6 Luna | OpenAI | Proprietary | 1.05M | 74.3 | $0.10 | $0.50 | — |
| 100 | Alibaba (Qwen) Qwen3-VL 235B-A22B | Alibaba (Qwen) | Open | 131K | 74.2 | $0.70 | $2.80 | — |
| 101 | OpenAI GPT-5.5 Instant | OpenAI | Proprietary | — | 74.2 | — | — | — |
| 102 | OpenAI GPT-5.4 mini | OpenAI | Proprietary | 400K | 74.1 | $0.75 | $4.50 | 10 |
| 103 | MiniMax MiniMax-M2.7 | MiniMax | Open | 205K | 74.1 | $0.30 | $1.20 | — |
| 104 | xAI Grok 4.7 | xAI | Proprietary | 500K | 74.1 | $2 | $6 | — |
| 105 | Z.ai (Zhipu) GLM-4.5 | Z.ai (Zhipu) | Open | 131K | 74.1 | $0.60 | $2.20 | 32 |
| 106 | DeepSeek DeepSeek-V3.1-Terminus | DeepSeek | Open | 164K | 74.0 | $0.27 | $1 | 30 |
| 107 | OpenAI Chatgpt 4o Latest 20250326 | OpenAI | Proprietary | — | 74.0 | — | — | 21 |
| 108 | Mistral AI Mistral Large 3 | Mistral AI | Open | 262K | 74.0 | $0.25 | $0.75 | 7 |
| 109 | Moonshot AI Kimi K2 Thinking Turbo | Moonshot AI | Open | — | 74.0 | — | — | — |
| 110 | DeepSeek DeepSeek-V3.1 | DeepSeek | Open | 164K | 73.9 | $0.25 | $0.95 | 328 |
| 111 | xAI Grok 4.1 | xAI | Proprietary | — | 73.8 | — | — | — |
| 112 | MiniMax MiniMax-M2.1 | MiniMax | Open | 205K | 73.8 | $0.30 | $1.20 | — |
| 113 | OpenAI GPT-5 | OpenAI | Proprietary | 400K | 73.8 | $1.25 | $10 | 2 |
| 114 | Thinking Machines Lab Inkling-Small | Thinking Machines Lab | Open | 524K | 73.8 | $0.45 | $1.20 | — |
| 115 | Alibaba (Qwen) Qwen3.5 122B-A10B | Alibaba (Qwen) | Open | 262K | 73.8 | $0.40 | $3.20 | — |
| 116 | Mistral AI Mistral Medium | Mistral AI | Open | 262K | 73.7 | $1.50 | $7.50 | 68 |
| 117 | Tencent Hunyuan Vision 1.5 | Tencent | Proprietary | — | 73.7 | — | — | — |
| 118 | OpenAI GPT-4.1 mini | OpenAI | Proprietary | 1.05M | 73.7 | $0.40 | $1.60 | 86 |
| 119 | Alibaba (Qwen) Qwen3.5 27B | Alibaba (Qwen) | Open | 262K | 73.5 | $0.30 | $2.40 | — |
| 120 | Xiaomi MiMo-V2-Flash | Xiaomi | Open | 262K | 73.5 | $0.14 | $0.28 | — |
| 121 | xAI Grok 4 Fast | xAI | Proprietary | — | 73.2 | — | — | 577 |
| 122 | Amazon Amazon Nova Experimental Chat 11 10 | Amazon | Proprietary | — | 73.2 | — | — | — |
| 123 | Amazon Amazon Nova Experimental Chat 12 10 | Amazon | Proprietary | — | 73.2 | — | — | — |
| 124 | StepFun Step 3.5 Flash | StepFun | Open | 256K | 73.1 | $0.10 | $0.30 | — |
| 125 | Anthropic Claude 3.7 Sonnet | Anthropic | Proprietary | — | 72.9 | — | — | — |
| 126 | Amazon Amazon Nova Experimental Chat 26 01 10 | Amazon | Proprietary | — | 72.9 | — | — | — |
| 127 | OpenAI o3 | OpenAI | Proprietary | 200K | 72.8 | $2 | $8 | 3 |
| 128 | Alibaba (Qwen) Qwen3.5 35B-A3B | Alibaba (Qwen) | Open | 262K | 72.8 | $0.25 | $2 | — |
| 129 | OpenAI GPT-5.3 Chat | OpenAI | Proprietary | 128K | 72.8 | $1.75 | $14 | — |
| 130 | DeepSeek DeepSeek-V3 | DeepSeek | Open | 164K | 72.8 | $0.24 | $0.90 | 73 |
| 131 | Google Gemini 3.1 Flash Lite | Proprietary | 1.05M | 72.7 | $0.25 | $1.50 | 10 | |
| 132 |  Upstage Solar Pro4 | Upstage | Proprietary | 524K | 72.7 | $0.30 | $1.20 | — |
| 133 | xAI Grok 4.1 Fast | xAI | Proprietary | 128K | 72.7 | $0.20 | $0.50 | — |
| 134 | OpenAI GPT-4.5 | OpenAI | Proprietary | — | 72.6 | — | — | — |
| 135 | Meta Muse Glimmer | Meta | Open | — | 72.6 | — | — | — |
| 136 | Alibaba (Qwen) Qwen3 235B-A22B | Alibaba (Qwen) | Open | 131K | 72.6 | $0.70 | $2.80 | 85 |
| 137 | Alibaba (Qwen) QwQ-32B | Alibaba (Qwen) | Open | — | 72.6 | — | — | — |
| 138 | Alibaba (Qwen) Qwen3.5-Flash | Alibaba (Qwen) | Proprietary | 1M | 72.6 | $0.10 | $0.40 | — |
| 139 | Tencent Hunyuan T1 20250711 | Tencent | Proprietary | — | 72.6 | — | — | — |
| 140 | xAI Grok 4.3 | xAI | Proprietary | 1M | 72.1 | $1.25 | $2.50 | — |
| 141 | Amazon Amazon Nova Experimental Chat 10 20 | Amazon | Proprietary | — | 72.1 | — | — | — |
| 142 | Alibaba (Qwen) Qwen3-30B-A3B | Alibaba (Qwen) | Open | 41K | 72.0 | $0.12 | $0.50 | 42 |
| 143 | DeepSeek DeepSeek-R1 | DeepSeek | Proprietary | 164K | 72.0 | $0.50 | $2.15 | 10 |
| 144 | OpenAI GPT-5.4 nano | OpenAI | Proprietary | 400K | 71.9 | $0.20 | $1.25 | 19 |
| 145 | Anthropic Claude Sonnet 4 | Anthropic | Proprietary | 200K | 71.7 | $3 | $15 | 31 |
| 146 | Meta Llama 4 Maverick | Meta | Open | 128K | 71.7 | $0.19 | $0.65 | 456 |
| 147 | Alibaba (Qwen) Qwen3-Coder 480B-A35B Instruct | Alibaba (Qwen) | Open | 262K | 71.6 | $1.50 | $7.50 | 67 |
| 148 | MiniMax MiniMax-M2.5 | MiniMax | Open | 205K | 71.5 | $0.30 | $1.20 | 49 |
| 149 | Anthropic Claude Haiku 4.5 | Anthropic | Proprietary | 200K | 71.4 | $1 | $5 | — |
| 150 |  Perplexity Sonar | Perplexity | Proprietary | 128K | 71.4 | $1 | $1 | — |
| 151 | Z.ai (Zhipu) GLM-4.6V | Z.ai (Zhipu) | Open | 128K | 71.4 | $0.30 | $0.90 | — |
| 152 | Alibaba (Qwen) Qwen2.5-Max | Alibaba (Qwen) | Proprietary | — | 71.3 | — | — | — |
| 153 | OpenAI GPT-4.1 | OpenAI | Proprietary | 1.05M | 71.3 | $2 | $8 | 116 |
| 154 | NVIDIA Nemotron 3 Super | NVIDIA | Open | 262K | 71.2 | $0.08 | $0.45 | — |
| 155 | IBM Granite 4.2 30b | IBM | Open | — | 71.2 | — | — | — |
| 156 | Moonshot AI Kimi K2 (Jul 2025) | Moonshot AI | Open | 262K | 71.1 | $0.57 | $2.30 | 201 |
| 157 | Meta Llama-3.3-70B-Instruct | Meta | Open | 128K | 71.1 | $0.10 | $0.32 | — |
| 158 | Tencent Hunyuan Turbos 20250226 | Tencent | Proprietary | — | 71.0 | — | — | — |
| 159 | Alibaba (Qwen) Qwen3-Next 80B-A3B Instruct | Alibaba (Qwen) | Open | 131K | 70.8 | $0.50 | $2 | 111 |
| 160 | Google Gemma 3 27B | Open | 131K | 70.6 | $0.08 | $0.16 | 62 | |
| 161 | Amazon Nova 2 Lite | Amazon | Proprietary | 1M | 70.5 | $0.30 | $2.50 | — |
| 162 |  Arcee AI Trinity Large Thinking | Arcee AI | Open | 262K | 70.5 | $0.25 | $0.80 | — |
| 163 | StepFun Step 3 | StepFun | Open | — | 70.4 | — | — | 7 |
| 164 | Google Gemini 2.0 Flash-Lite | Proprietary | — | 70.4 | — | — | — | |
| 165 | Inception Mercury 2 | Inception | Proprietary | 128K | 70.2 | $0.25 | $0.75 | — |
| 166 | MiniMax MiniMax-M2 | MiniMax | Open | 205K | 70.2 | $0.30 | $1.20 | 17 |
| 167 | Z.ai (Zhipu) GLM-4.7-Flash | Z.ai (Zhipu) | Open | 200K | 70.1 | $0.06 | $0.40 | — |
| 168 | Google Gemini 2.5 Flash-Lite | Proprietary | 1.05M | 70.0 | $0.10 | $0.40 | 172 | |
| 169 | IBM Granite 4.0 Micro | IBM | Open | 131K | 69.9 | $0.017 | $0.11 | — |
| 170 | NVIDIA Nemotron 3.5 Lightning | NVIDIA | Open | 262K | 69.6 | $0.05 | $0.20 | — |
| 171 | Z.ai (Zhipu) GLM-4.5-Air | Z.ai (Zhipu) | Open | 131K | 69.6 | $0.20 | $1.10 | 160 |
| 172 | Amazon Amazon Nova Experimental Chat 10 09 | Amazon | Proprietary | — | 69.4 | — | — | — |
| 173 | OpenAI gpt-oss-120b | OpenAI | Open | 131K | 69.3 | $0.037 | $0.17 | 55 |
| 174 | MiniMax MiniMax M1 | MiniMax | Open | 1M | 69.3 | $0.55 | $2.20 | — |
| 175 | Z.ai (Zhipu) GLM-4.5V | Z.ai (Zhipu) | Open | 64K | 69.2 | $0.60 | $1.80 | 34 |
| 176 | StepFun Step 1o Turbo 202506 | StepFun | Proprietary | — | 69.2 | — | — | — |
| 177 |  Cohere Command A | Cohere | Open | 256K | 69.1 | $2.50 | $10 | 28 |
| 178 | NVIDIA Llama 3.1 Nemotron Ultra 253b v1 | NVIDIA | Open | — | 69.0 | — | — | — |
| 179 | Alibaba (Qwen) Qwen3 32B | Alibaba (Qwen) | Open | 131K | 68.9 | $0.70 | $2.80 | 86 |
| 180 | NVIDIA Nemotron 3 Nano 30B A3B | NVIDIA | Open | 262K | 68.8 | $0.05 | $0.20 | — |
| 181 | Alibaba (Qwen) Qwen Plus | Alibaba (Qwen) | Proprietary | 1M | 68.8 | $0.40 | $1.20 | 37 |
| 182 | Anthropic Claude 3.5 Sonnet | Anthropic | Proprietary | — | 68.8 | — | — | — |
| 183 | IBM Granite 4.0 H Small | IBM | Open | — | 68.7 | — | — | — |
| 184 | IBM Granite 4.2 8B | IBM | Open | 131K | 68.7 | $0.06 | $0.25 | — |
| 185 | Google Gemini 1.5 Pro (May 2024) | Proprietary | — | 68.6 | — | — | — | |
| 186 | Google Gemma 3 12B | Open | 131K | 68.6 | $0.05 | $0.15 | — | |
| 187 |  Allen Institute for AI (Ai2) Olmo 3.1 32b Instruct | Allen Institute for AI (Ai2) | Open | — | 68.6 | — | — | — |
| 188 | NVIDIA Nvidia Llama 3.3 Nemotron Super 49b v1.5 | NVIDIA | Open | 131K | 68.6 | $0.40 | $0.40 | — |
| 189 | NVIDIA Llama 3.3 Nemotron 49b Super v1 | NVIDIA | Open | — | 68.3 | — | — | — |
| 190 | DeepSeek DeepSeek-R1-Distill-Llama-70B | DeepSeek | Open | — | 68.2 | — | — | 18 |
| 191 | Mistral AI Mistral Large | Mistral AI | Open | 131K | 67.9 | $2 | $6 | — |
| 192 | StepFun Step 2 16k Exp 202412 | StepFun | Proprietary | — | 67.9 | — | — | — |
| 193 | OpenAI GPT-4.1 nano | OpenAI | Proprietary | 1.05M | 67.8 | $0.10 | $0.40 | 135 |
| 194 | DeepSeek DeepSeek-V2.5 (Sep 2024) | DeepSeek | Open | — | 67.5 | — | — | — |
| 195 | Tencent Hunyuan Turbo 0110 | Tencent | Proprietary | — | 67.4 | — | — | — |
| 196 | 01.AI Yi-Lightning | 01.AI | Proprietary | — | 67.4 | — | — | — |
| 197 | Tencent Hunyuan Large 2025 02 10 | Tencent | Proprietary | — | 67.3 | — | — | — |
| 198 | Allen Institute for AI (Ai2) Olmo 3 32b Think | Allen Institute for AI (Ai2) | Open | — | 67.2 | — | — | — |
| 199 | Alibaba (Qwen) Qwen2.5 Plus 1127 | Alibaba (Qwen) | Proprietary | — | 67.2 | — | — | — |
| 200 | IBM Granite 4.2 3b | IBM | Open | — | 67.1 | — | — | — |
| 201 | Allen Institute for AI (Ai2) Molmo 2 8b | Allen Institute for AI (Ai2) | Open | — | 67.0 | — | — | — |
| 202 | xAI Grok-2 (Dec 2024) | xAI | Proprietary | — | 66.9 | — | — | — |
| 203 | IBM Granite 4.1 8b | IBM | Open | — | 66.9 | — | — | — |
| 204 | Amazon Nova Premier 1.0 | Amazon | Proprietary | 1M | 66.8 | $2.50 | $12.50 | 9 |
| 205 | Google Gemini 1.5 Flash (May 2024) | Proprietary | — | 66.8 | — | — | — | |
| 206 | OpenAI o1-mini | OpenAI | Proprietary | — | 66.7 | — | — | — |
| 207 | OpenAI GPT-4o | OpenAI | Proprietary | 128K | 66.6 | $2.50 | $10 | — |
| 208 | Alibaba (Qwen) Qwen Max | Alibaba (Qwen) | Proprietary | 33K | 66.5 | $1.60 | $6.40 | — |
| 209 | Mistral AI Mistral Small | Mistral AI | Open | 262K | 66.4 | $0.15 | $0.60 | 120 |
| 210 | Google Gemma 3n E4b IT | Open | — | 66.1 | — | — | 13 | |
| 211 | Mistral AI Magistral Medium | Mistral AI | Open | 262K | 66.0 | $2 | $5 | 0 |
| 212 | Google Gemini Advanced 0514 | Proprietary | — | 66.0 | — | — | — | |
| 213 | NVIDIA Llama 3.1 Nemotron 70b Instruct | NVIDIA | Open | — | 65.9 | — | — | — |
| 214 | Meta Llama 3.1-405B | Meta | Open | — | 65.9 | — | — | 78 |
| 215 | Tencent Hunyuan Large Vision | Tencent | Proprietary | — | 65.8 | — | — | — |
| 216 | OpenAI GPT-4 Turbo | OpenAI | Proprietary | 128K | 65.8 | $10 | $30 | — |
| 217 | Meta Llama 4 Scout | Meta | Open | 128K | 65.8 | $0.10 | $0.30 | 272 |
| 218 | Allen Institute for AI (Ai2) Olmo 3.1 32b Think | Allen Institute for AI (Ai2) | Open | — | 65.6 | — | — | — |
| 219 | Tencent Hunyuan Standard 2025 02 10 | Tencent | Proprietary | — | 65.5 | — | — | — |
| 220 | xAI Grok 2 Mini 2024 08 13 | xAI | Proprietary | — | 65.5 | — | — | — |
| 221 | Alibaba (Qwen) Qwen2.5 72B Instruct | Alibaba (Qwen) | Open | 131K | 65.5 | $1.40 | $5.60 | — |
| 222 | OpenAI GPT-4 | OpenAI | Proprietary | 8K | 65.3 | $30 | $60 | — |
| 223 | Meta Llama 3.1-70B | Meta | Open | 128K | 65.3 | $0.40 | $0.40 | — |
| 224 | Inception Mercury | Inception | Proprietary | — | 65.2 | — | — | 35 |
| 225 | Google Gemma 3 4B | Open | 131K | 65.2 | $0.04 | $0.08 | 72 | |
| 226 | Amazon Amazon Nova Pro | Amazon | Proprietary | 300K | 64.9 | $0.80 | $3.20 | — |
| 227 | Allen Institute for AI (Ai2) Tulu 3 (Tülu 3) 70B | Allen Institute for AI (Ai2) | Open | — | 64.8 | — | — | — |
| 228 | Anthropic Claude 3 Opus | Anthropic | Proprietary | — | 64.1 | — | — | — |
| 229 | Mistral AI Mistral Small 3 | Mistral AI | Open | 33K | 63.7 | $0.05 | $0.08 | — |
| 230 | Mistral AI Mistral Small 3.1 | Mistral AI | Open | 128K | 63.6 | $0.35 | $0.56 | — |
| 231 | Alibaba (Qwen) Qwen2.5 7B Instruct | Alibaba (Qwen) | Open | 131K | 63.2 | $0.17 | $0.70 | — |
| 232 | NVIDIA Nemotron 4 340b Instruct | NVIDIA | Open | — | 63.1 | — | — | — |
| 233 | NVIDIA Llama 3.1 Nemotron 51b Instruct | NVIDIA | Open | — | 62.9 | — | — | — |
| 234 | Anthropic Claude 3.5 Haiku | Anthropic | Proprietary | — | 62.9 | — | — | — |
| 235 | Anthropic Claude 3 Sonnet | Anthropic | Proprietary | — | 62.8 | — | — | — |
| 236 | Google Gemini 1.5 Flash 8B | Proprietary | — | 62.8 | — | — | — | |
| 237 | Cohere C4ai Aya Expanse 32b | Cohere | Open | 128K | 62.6 | — | — | — |
| 238 | Meta Llama 3-70B | Meta | Open | — | 62.5 | — | — | 104 |
| 239 | OpenAI GPT-4o mini | OpenAI | Proprietary | 128K | 61.9 | $0.15 | $0.60 | 120 |
| 240 | OpenAI gpt-oss-20b | OpenAI | Open | 131K | 61.8 | $0.018 | $0.09 | 96 |
| 241 | Alibaba (Qwen) Qwen2-72B | Alibaba (Qwen) | Open | — | 61.7 | — | — | — |
| 242 | DeepSeek Deepseek Coder v2 | DeepSeek | Open | — | 61.7 | — | — | — |
| 243 | DeepSeek DeepSeek-R1-Distill-Qwen-32B | DeepSeek | Open | — | 61.6 | — | — | — |
| 244 | Allen Institute for AI (Ai2) Olmo 2 0325 32b Instruct | Allen Institute for AI (Ai2) | Open | — | 61.5 | — | — | — |
| 245 | Alibaba (Qwen) Qwen2.5-Coder-32B | Alibaba (Qwen) | Open | 33K | 61.4 | $0.66 | $1 | — |
| 246 | Allen Institute for AI (Ai2) Llama 3.1 Tulu 3 8b | Allen Institute for AI (Ai2) | Open | — | 61.3 | — | — | — |
| 247 | Anthropic Claude 3 Haiku | Anthropic | Proprietary | — | 61.3 | — | — | 41 |
| 248 | Allen Institute for AI (Ai2) OLMo 2 Furious 13B | Allen Institute for AI (Ai2) | Open | — | 60.9 | — | — | — |
| 249 | Google Gemma 2 27B | Open | 8K | 60.5 | $0.65 | $0.65 | — | |
| 250 | Mistral AI Ministral 8B | Mistral AI | Open | 262K | 60.5 | $0.15 | $0.15 | — |
| 251 |  Microsoft Phi-4 | Microsoft | Open | 128K | 60.4 | $0.07 | $0.14 | — |
| 252 | Alibaba (Qwen) Qwen1.5-110B | Alibaba (Qwen) | Open | — | 60.3 | — | — | — |
| 253 | Cohere C4ai Aya Expanse 8b | Cohere | Open | — | 60.1 | — | — | — |
| 254 | Cohere Command R+ | Cohere | Open | 128K | 60.0 | $2.50 | $10 | — |
| 255 | Amazon Amazon Nova Lite | Amazon | Proprietary | 300K | 59.3 | $0.06 | $0.24 | — |
| 256 | Alibaba (Qwen) Qwen1.5-72B | Alibaba (Qwen) | Open | — | 59.3 | — | — | — |
| 257 | 01.AI Yi-1.5-34B | 01.AI | Open | — | 59.2 | — | — | — |
| 258 | Meta Llama 3.1-8B | Meta | Open | 128K | 58.9 | $0.05 | $0.08 | — |
| 259 | IBM Granite 3.1 8b Instruct | IBM | Open | — | 58.6 | — | — | — |
| 260 | Meta Llama 3-8B | Meta | Open | — | 58.4 | — | — | — |
| 261 | Cohere Command R | Cohere | Open | 128K | 58.1 | $0.15 | $0.60 | — |
| 262 | OpenAI GPT-3.5-turbo | OpenAI | Proprietary | 16K | 57.9 | $0.50 | $1.50 | — |
| 263 | Google Gemma 2 2b IT | Open | — | 57.8 | — | — | — | |
| 264 | IBM Granite 3.1 2b Instruct | IBM | Open | — | 57.7 | — | — | — |
| 265 | Alibaba (Qwen) Qwen1.5-32B | Alibaba (Qwen) | Open | — | 57.7 | — | — | — |
| 266 | Mistral AI Mixtral 8x22B | Mistral AI | Open | 64K | 57.7 | $2 | $6 | — |
| 267 | Google Gemini 1.0 Pro | Proprietary | — | 57.6 | — | — | — | |
| 268 | Microsoft Phi 3 Medium 4k Instruct | Microsoft | Open | — | 57.6 | — | — | — |
| 269 | Google Gemma 2 9B | Open | — | 57.6 | — | — | — | |
| 270 |  Databricks DBRX | Databricks | Open | — | 57.5 | — | — | — |
| 271 | Alibaba (Qwen) Qwen1.5-14B | Alibaba (Qwen) | Open | — | 56.8 | — | — | — |
| 272 | Amazon Amazon Nova Micro | Amazon | Proprietary | 128K | 56.3 | $0.035 | $0.14 | — |
| 273 | Microsoft Wizardlm 70b | Microsoft | Open | — | 56.3 | — | — | — |
| 274 | 01.AI Yi-34B | 01.AI | Open | — | 56.2 | — | — | — |
| 275 | Meta Llama 3.2 3B | Meta | Open | 131K | 56.0 | $0.05 | $0.33 | — |
| 276 | IBM Granite 3.0 8b Instruct | IBM | Open | — | 56.0 | — | — | — |
| 277 | DeepSeek DeepSeek LLM 67B | DeepSeek | Open | — | 55.4 | — | — | — |
| 278 | Meta Llama 2-70B | Meta | Open | — | 54.9 | — | — | — |
| 279 | NVIDIA Llama2 70b Steerlm Chat | NVIDIA | Open | — | 54.2 | — | — | — |
| 280 | Mistral AI Mistral 7B | Mistral AI | Open | 8K | 54.2 | $0.25 | $0.25 | — |
| 281 | Alibaba (Qwen) Qwen1.5-7B | Alibaba (Qwen) | Open | — | 54.1 | — | — | — |
| 282 | Microsoft Phi 3 Mini 4k Instruct June 2024 | Microsoft | Open | — | 54.1 | — | — | — |
| 283 | Google Gemma 1.1 7b IT | Open | — | 54.0 | — | — | — | |
| 284 | IBM Granite 3.0 2b Instruct | IBM | Open | — | 53.9 | — | — | — |
| 285 | Microsoft Wizardlm 13b | Microsoft | Open | — | 53.5 | — | — | — |
| 286 |  Technology Innovation Institute Falcon-180B | Technology Innovation Institute | Open | — | 53.4 | — | — | — |
| 287 | Meta Llama 2-13B | Meta | Open | — | 53.3 | — | — | — |
| 288 | Mistral AI Mistral | Mistral AI | Proprietary | — | 52.6 | — | — | — |
| 289 | Alibaba (Qwen) Qwen-14B | Alibaba (Qwen) | Open | — | 52.4 | — | — | — |
| 290 | Meta Llama 3.2 1B | Meta | Open | 60K | 52.4 | $0.027 | $0.20 | — |
| 291 | Meta Codellama 34b Instruct | Meta | Open | — | 52.2 | — | — | — |
| 292 | Microsoft Phi 3 Small 8k Instruct | Microsoft | Open | — | 51.9 | — | — | — |
| 293 | Meta Codellama 70b Instruct | Meta | Open | — | 51.9 | — | — | — |
| 294 | Microsoft Phi 3 Mini 128k Instruct | Microsoft | Open | — | 51.8 | — | — | — |
| 295 | Google Gemma 7B | Open | — | 51.5 | — | — | — | |
| 296 | Google Palm 2 | Proprietary | — | 51.0 | — | — | — | |
| 297 | Mistral AI Mixtral 8x7B | Mistral AI | Open | 32K | 51.0 | $0.70 | $0.70 | — |
| 298 | Meta Llama 2-7B | Meta | Open | — | 50.8 | — | — | — |
| 299 | Google Gemma 1.1 2b IT | Open | — | 49.9 | — | — | — | |
| 300 | Alibaba (Qwen) Qwen1.5 4b Chat | Alibaba (Qwen) | Open | — | 49.0 | — | — | — |
| 301 | Allen Institute for AI (Ai2) Olmo 7b Instruct | Allen Institute for AI (Ai2) | Open | — | 49.0 | — | — | — |
| 302 | Google Gemma 2B | Open | — | 48.5 | — | — | — | |
| 303 | Microsoft Phi 3 Mini 4k Instruct | Microsoft | Open | — | 47.7 | — | — | — |
| 304 | Databricks Dolly 2.0-12b | Databricks | Open | — | 38.7 | — | — | — |
| 305 | Meta Llama 13b | Meta | Open | — | 36.7 | — | — | — |
Sponsored placements are available on pages like this one. Advertise on Noometry
Compare the leaders
Frequently asked questions
Which AI model follows instructions best?
As of October 2026, GPT-5.1 leads the Noometry instruction following ranking with a score of 83.9, ahead of Gemini 4 Argon at 80.1.
What are the top 5 in this ranking?
GPT-5.1, Gemini 4 Argon, Claude Opus 5.5, Claude Opus 4.6, Grok 4, in that order, as of October 2026.
How is this list ranked?
By the category score, which is fitted from every public benchmark result and adjusted for how hard each benchmark is. Models need several independent results to be ranked.