Category ranking
Best Agentic AI Models in October 2026
As of October 2026, Claude Opus 5 leads the Noometry agentic & tool use ranking with a score of 55.6, ahead of Claude Fable 5 at 54.0.
Last verified
Completing multi-step tasks with tools, terminals, browsers and computers, where the model plans and acts without step-by-step help.
- Claude Opus 5 55.6
- Claude Fable 5 54.0
- GPT-6 Astra 52.9
- Claude Opus 4.6 51.1
- Claude Fable 5.1 50.7
- GPT-5.5 50.7
- GPT-5.6 Sol 50.3
- Gemini 4 Argon 49.2
- GPT-5.3 Codex 48.0
- Claude Opus 4.7 47.9
Full ranking
154 models
| 1 | Anthropic Claude Opus 5 | Anthropic | Proprietary | 1M | 55.6 | $5 | $25 | — |
| 2 | Anthropic Claude Fable 5 | Anthropic | Proprietary | 1M | 54.0 | $10 | $50 | 25 |
| 3 | OpenAI GPT-6 Astra | OpenAI | Proprietary | 1.05M | 52.9 | $10 | $50 | — |
| 4 | Anthropic Claude Opus 4.6 | Anthropic | Proprietary | 1M | 51.1 | $5 | $25 | 19 |
| 5 | Anthropic Claude Fable 5.1 | Anthropic | Proprietary | 1M | 50.7 | $10 | $50 | — |
| 6 | OpenAI GPT-5.5 | OpenAI | Proprietary | 1.05M | 50.7 | $5 | $30 | 25 |
| 7 | OpenAI GPT-5.6 Sol | OpenAI | Proprietary | 1.05M | 50.3 | $4 | $20 | 10 |
| 8 |  Google Gemini 4 Argon | Proprietary | — | 49.2 | — | — | — | |
| 9 | OpenAI GPT-5.3 Codex | OpenAI | Proprietary | 400K | 48.0 | $1.75 | $14 | — |
| 10 | Anthropic Claude Opus 4.7 | Anthropic | Proprietary | 1M | 47.9 | $5 | $25 | 33 |
| 11 | Anthropic Claude Opus 4.8 | Anthropic | Proprietary | 1M | 47.6 | $5 | $25 | 34 |
| 12 | Anthropic Claude Opus 4.5 | Anthropic | Proprietary | 200K | 47.3 | $5 | $25 | 13 |
| 13 | OpenAI GPT-5.4 | OpenAI | Proprietary | 1.05M | 46.5 | $2.50 | $15 | 12 |
| 14 |  Alibaba (Qwen) Qwen3.8 Max | Alibaba (Qwen) | Proprietary | 1M | 45.4 | $2 | $6 | — |
| 15 | Anthropic Claude Opus 5.5 | Anthropic | Proprietary | 1M | 45.3 | $4 | $20 | — |
| 16 | Anthropic Claude Sonnet 5.5 | Anthropic | Proprietary | 1M | 45.0 | $2 | $10 | — |
| 17 | xAI Grok 4.5 | xAI | Proprietary | 500K | 44.4 | $2 | $6 | 4 |
| 18 | Anthropic Claude Sonnet 5 | Anthropic | Proprietary | 1M | 42.8 | $2 | $10 | — |
| 19 | Google Gemini 3.7 Flash | Proprietary | 1.05M | 42.1 | $0.75 | $3.75 | — | |
| 20 | Moonshot AI Kimi K3 | Moonshot AI | Open | 1.05M | 41.8 | $3 | $15 | — |
| 21 | Google Gemini 3.8 Flash | Proprietary | 1.05M | 41.8 | $0.75 | $3.75 | — | |
| 22 | OpenAI GPT-5.2 Codex | OpenAI | Proprietary | 400K | 41.0 | $1.75 | $14 | — |
| 23 | Google Gemini 3 Pro | Proprietary | — | 40.6 | — | — | 1 | |
| 24 | OpenAI GPT-5.2 | OpenAI | Proprietary | 400K | 40.2 | $1.75 | $14 | 15 |
| 25 | OpenAI GPT-5.6 Terra | OpenAI | Proprietary | 1.05M | 40.1 | $2 | $12 | 11 |
| 26 | OpenAI GPT-6.1 Sol | OpenAI | Proprietary | 1.05M | 39.6 | $2 | $10 | — |
| 27 | xAI Grok 4.6 | xAI | Proprietary | 500K | 39.4 | $2 | $6 | — |
| 28 | Anthropic Claude Sonnet 4.6 | Anthropic | Proprietary | 1M | 39.1 | $3 | $15 | — |
| 29 | Google Gemini 3 Flash Preview | Proprietary | 1.05M | 38.7 | $0.50 | $3 | — | |
| 30 |  Meta Muse Spark 1.3 | Meta | Proprietary | 1.05M | 38.6 | $1.25 | $4.25 | — |
| 31 | Anthropic Claude Sonnet 4 | Anthropic | Proprietary | 200K | 38.5 | $3 | $15 | 31 |
| 32 | Anthropic Claude Sonnet 4.5 | Anthropic | Proprietary | 200K | 38.3 | $3 | $15 | 85 |
| 33 | OpenAI GPT-5.1-Codex | OpenAI | Proprietary | 400K | 38.0 | $1.25 | $10 | — |
| 34 | Google Gemini 3.1 Pro Preview | Proprietary | 1.05M | 37.7 | $2 | $12 | — | |
| 35 | Xiaomi MiMo-V2.6-Pro | Xiaomi | Open | 1.05M | 37.5 | $0.43 | $0.87 | — |
| 36 | OpenAI GPT-6 Sol | OpenAI | Proprietary | 1.05M | 37.2 | $2 | $10 | — |
| 37 | xAI Grok 4.7 | xAI | Proprietary | 500K | 36.7 | $2 | $6 | — |
| 38 | Z.ai (Zhipu) GLM-5.3 | Z.ai (Zhipu) | Open | 1M | 36.4 | $1.40 | $4.40 | — |
| 39 | xAI Grok 4.1 Fast | xAI | Proprietary | 128K | 36.3 | $0.20 | $0.50 | — |
| 40 |  Cohere Command A | Cohere | Open | 256K | 35.9 | $2.50 | $10 | 28 |
| 41 | Anthropic Claude Opus 4.1 | Anthropic | Proprietary | 200K | 35.0 | $15 | $75 | — |
| 42 | Anthropic Claude Opus 4 | Anthropic | Proprietary | 200K | 34.8 | $15 | $75 | 29 |
| 43 | OpenAI GPT-4.1 | OpenAI | Proprietary | 1.05M | 34.7 | $2 | $8 | 116 |
| 44 | OpenAI o3 | OpenAI | Proprietary | 200K | 34.5 | $2 | $8 | 3 |
| 45 | OpenAI GPT-5.6 Luna | OpenAI | Proprietary | 1.05M | 34.4 | $0.20 | $1.20 | 12 |
| 46 | xAI Grok 4.20 (Non-Reasoning) | xAI | Proprietary | 1M | 34.4 | $1.25 | $2.50 | 61 |
| 47 | Z.ai (Zhipu) GLM-5.3-Flash | Z.ai (Zhipu) | Open | 1M | 34.2 | $0.15 | $0.50 | — |
| 48 | Moonshot AI Kimi K2.5 | Moonshot AI | Open | 262K | 34.2 | $0.45 | $2.25 | 66 |
| 49 | xAI Grok 4.1 | xAI | Proprietary | — | 34.1 | — | — | — |
| 50 | Anthropic Claude 3.7 Sonnet | Anthropic | Proprietary | — | 34.1 | — | — | — |
| 51 | Alibaba (Qwen) Qwen3 235B-A22B | Alibaba (Qwen) | Open | 131K | 33.9 | $0.70 | $2.80 | 85 |
| 52 | Anthropic Claude Haiku 4.5 | Anthropic | Proprietary | 200K | 33.6 | $1 | $5 | — |
| 53 | Alibaba (Qwen) Qwen3.5 397B-A17B | Alibaba (Qwen) | Open | 262K | 33.3 | $0.60 | $3.60 | 9 |
| 54 | OpenAI GPT-6 Luna | OpenAI | Proprietary | 1.05M | 33.3 | $0.10 | $0.50 | — |
| 55 | OpenAI GPT-4.1 mini | OpenAI | Proprietary | 1.05M | 33.3 | $0.40 | $1.60 | 86 |
| 56 | OpenAI GPT-5 | OpenAI | Proprietary | 400K | 33.1 | $1.25 | $10 | 2 |
| 57 | Alibaba (Qwen) Qwen3.8 27B | Alibaba (Qwen) | Open | 262K | 32.9 | $0.99 | $1.49 | — |
| 58 |  DeepSeek DeepSeek V4 Pro | DeepSeek | Open | 1M | 32.8 | $0.66 | $1.98 | 16 |
| 59 | DeepSeek DeepSeek-V3.2-Exp | DeepSeek | Open | 164K | 32.7 | $0.26 | $0.38 | 16 |
| 60 | OpenAI GPT-5.1 | OpenAI | Proprietary | 400K | 32.7 | $1.25 | $10 | — |
| 61 | OpenAI o4-mini | OpenAI | Proprietary | 200K | 32.6 | $1.10 | $4.40 | 6 |
| 62 | Alibaba (Qwen) Qwen3 32B | Alibaba (Qwen) | Open | 131K | 32.6 | $0.70 | $2.80 | 86 |
| 63 | Z.ai (Zhipu) GLM-5.2 | Z.ai (Zhipu) | Open | 1M | 32.4 | $1.40 | $4.40 | 23 |
| 64 | Moonshot AI Kimi K2 (Jul 2025) | Moonshot AI | Open | 262K | 32.4 | $0.57 | $2.30 | 201 |
| 65 | Google Gemini 3.6 Flash | Proprietary | 1.05M | 32.3 | $0.75 | $3.75 | — | |
| 66 | Z.ai (Zhipu) GLM-4.6 | Z.ai (Zhipu) | Open | 205K | 32.3 | $0.60 | $2.20 | 12 |
| 67 | Anthropic Claude 3.5 Sonnet | Anthropic | Proprietary | — | 32.3 | — | — | — |
| 68 | xAI Grok 4 | xAI | Proprietary | — | 32.3 | — | — | 1 |
| 69 | DeepSeek DeepSeek V4.1 Flash | DeepSeek | Open | 1M | 31.2 | $0.15 | $0.60 | — |
| 70 | OpenAI GPT-5 Mini | OpenAI | Proprietary | 400K | 31.1 | $0.25 | $2 | 3 |
| 71 | Z.ai (Zhipu) GLM-5 | Z.ai (Zhipu) | Open | 205K | 31.1 | $1 | $3.20 | 23 |
| 72 | OpenAI GPT-5-Codex | OpenAI | Proprietary | 400K | 31.0 | $1.25 | $10 | 95 |
| 73 | Meta Muse Spark 1.1 | Meta | Proprietary | 1.05M | 30.8 | $1.25 | $4.25 | — |
| 74 | Google Gemini 2.5 Flash | Proprietary | 1.05M | 30.8 | $0.30 | $2.50 | 152 | |
| 75 | DeepSeek DeepSeek-R1 | DeepSeek | Proprietary | 164K | 30.7 | $0.50 | $2.15 | 10 |
| 76 | xAI Grok 3 | xAI | Proprietary | — | 30.5 | — | — | 42 |
| 77 |  MiniMax MiniMax-M2.5 | MiniMax | Open | 205K | 30.4 | $0.30 | $1.20 | 49 |
| 78 | Alibaba (Qwen) Qwen3 8B | Alibaba (Qwen) | Open | 131K | 30.2 | $0.18 | $0.70 | — |
| 79 | Google Gemini 3.1 Flash Lite | Proprietary | 1.05M | 30.2 | $0.25 | $1.50 | 10 | |
| 80 | Meta Llama 3.2 90B | Meta | Open | — | 30.0 | — | — | — |
| 81 | OpenAI GPT-5.4 mini | OpenAI | Proprietary | 400K | 29.9 | $0.75 | $4.50 | 10 |
| 82 | Alibaba (Qwen) Qwen3-30B-A3B | Alibaba (Qwen) | Open | 41K | 29.8 | $0.12 | $0.50 | 42 |
| 83 | Alibaba (Qwen) Qwen3 14B | Alibaba (Qwen) | Open | 131K | 29.6 | $0.35 | $1.40 | 79 |
| 84 | OpenAI o3-mini | OpenAI | Proprietary | 200K | 29.6 | $1.10 | $4.40 | — |
| 85 | Thinking Machines Lab Inkling | Thinking Machines Lab | Open | 66K | 29.6 | $1.87 | $4.68 | — |
| 86 | xAI Grok 4 Fast | xAI | Proprietary | — | 29.5 | — | — | 577 |
| 87 | Meta Muse Spark 1.2 | Meta | Proprietary | 1.05M | 29.4 | $1.25 | $4.25 | — |
| 88 | Google Gemini 2.5 Pro | Proprietary | 1.05M | 29.2 | $1.25 | $10 | 5 | |
| 89 |  Mistral AI Mistral Large | Mistral AI | Open | 131K | 28.6 | $2 | $6 | — |
| 90 | Mistral AI Mistral Medium | Mistral AI | Open | 262K | 28.3 | $1.50 | $7.50 | 68 |
| 91 | Meta Llama 4 Maverick | Meta | Open | 128K | 28.2 | $0.19 | $0.65 | 456 |
| 92 | Google Gemini 2.0 Flash (Feb 2025) | Proprietary | — | 28.1 | — | — | 92 | |
| 93 | Mistral AI Mistral Small | Mistral AI | Open | 262K | 28.1 | $0.15 | $0.60 | 120 |
| 94 | DeepSeek DeepSeek-R1-Distill-Qwen-32B | DeepSeek | Open | — | 28.1 | — | — | — |
| 95 | Anthropic Claude 3.5 Haiku | Anthropic | Proprietary | — | 28.0 | — | — | — |
| 96 | Google Gemini 2.5 Flash-Lite | Proprietary | 1.05M | 28.0 | $0.10 | $0.40 | 172 | |
| 97 | OpenAI GPT-4.5 | OpenAI | Proprietary | — | 27.9 | — | — | — |
| 98 | MiniMax MiniMax-M2.1 | MiniMax | Open | 205K | 27.9 | $0.30 | $1.20 | — |
| 99 | xAI Grok 4.3 | xAI | Proprietary | 1M | 27.7 | $1.25 | $2.50 | — |
| 100 | Alibaba (Qwen) Qwen3-4B | Alibaba (Qwen) | Open | — | 27.6 | — | — | — |
| 101 | OpenAI GPT-4o mini | OpenAI | Proprietary | 128K | 27.5 | $0.15 | $0.60 | 120 |
| 102 | Google Gemini 1.5 Flash (May 2024) | Proprietary | — | 26.6 | — | — | — | |
| 103 | Z.ai (Zhipu) GLM-4.7 | Z.ai (Zhipu) | Open | 205K | 26.5 | $0.60 | $2.20 | — |
| 104 | OpenAI GPT-4.1 nano | OpenAI | Proprietary | 1.05M | 26.5 | $0.10 | $0.40 | 135 |
| 105 | Meta Llama-3.3-70B-Instruct | Meta | Open | 128K | 25.8 | $0.10 | $0.32 | — |
| 106 | OpenAI GPT-5 Nano | OpenAI | Proprietary | 400K | 25.8 | $0.05 | $0.40 | 4 |
| 107 | Google Gemini 3.5 Flash Lite | Proprietary | 1.05M | 25.7 | $0.30 | $2.50 | — | |
| 108 | Google Gemma 3 12B | Open | 131K | 25.5 | $0.05 | $0.15 | — | |
| 109 | MiniMax MiniMax-M2 | MiniMax | Open | 205K | 25.1 | $0.30 | $1.20 | 17 |
| 110 | Google Gemma 3 27B | Open | 131K | 25.1 | $0.08 | $0.16 | 62 | |
| 111 | MiniMax MiniMax-M2.7 | MiniMax | Open | 205K | 25.1 | $0.30 | $1.20 | — |
| 112 | Meta Llama 3.1-70B | Meta | Open | 128K | 25.1 | $0.40 | $0.40 | — |
| 113 | Z.ai (Zhipu) GLM-5.1 | Z.ai (Zhipu) | Open | 200K | 24.9 | $1.40 | $4.40 | — |
| 114 | Google Gemini 3.5 Flash | Proprietary | 1.05M | 24.7 | $1.50 | $9 | — | |
| 115 | Alibaba (Qwen) Qwen3-1.7B | Alibaba (Qwen) | Open | — | 24.7 | — | — | — |
| 116 | OpenAI o1 | OpenAI | Proprietary | 200K | 24.6 | $15 | $60 | — |
| 117 | OpenAI o1-mini | OpenAI | Proprietary | — | 24.6 | — | — | — |
| 118 | Anthropic Claude 3 Opus | Anthropic | Proprietary | — | 24.6 | — | — | — |
| 119 | Meta Llama 4 Scout | Meta | Open | 128K | 24.6 | $0.10 | $0.30 | 272 |
| 120 | Amazon Nova 2 Lite | Amazon | Proprietary | 1M | 24.1 | $0.30 | $2.50 | — |
| 121 | IBM Granite 3.1 8b Instruct | IBM | Open | — | 24.1 | — | — | — |
| 122 | Moonshot AI Kimi K2.7 Code | Moonshot AI | Open | 262K | 24.0 | $0.95 | $4 | — |
| 123 | Alibaba (Qwen) Qwen3-Coder 480B-A35B Instruct | Alibaba (Qwen) | Open | 262K | 23.9 | $1.50 | $7.50 | 67 |
| 124 | Alibaba (Qwen) Qwen2.5 7B Instruct | Alibaba (Qwen) | Open | 131K | 23.8 | $0.17 | $0.70 | — |
| 125 | Mistral AI Mistral Nemo | Mistral AI | Open | 128K | 23.5 | $0.15 | $0.15 | — |
| 126 |  NVIDIA Nemotron 3 Ultra | NVIDIA | Open | 262K | 23.4 | $0.50 | $2.20 | — |
| 127 | Mistral AI Mixtral 8x22B | Mistral AI | Open | 64K | 23.1 | $2 | $6 | — |
| 128 |  Microsoft Phi-4 | Microsoft | Open | 128K | 22.8 | $0.07 | $0.14 | — |
| 129 | xAI Grok Build 0.1 | xAI | Proprietary | 256K | 22.7 | $1 | $2 | — |
| 130 | MiniMax MiniMax-M3 | MiniMax | Open | 1M | 22.6 | $0.30 | $1.20 | — |
| 131 | Meta Llama 3.1-8B | Meta | Open | 128K | 22.5 | $0.05 | $0.08 | — |
| 132 | Alibaba (Qwen) Qwen2.5 72B Instruct | Alibaba (Qwen) | Open | 131K | 22.1 | $1.40 | $5.60 | — |
| 133 | Amazon Amazon Nova Micro | Amazon | Proprietary | 128K | 22.1 | $0.035 | $0.14 | — |
| 134 | Alibaba (Qwen) Qwen3.7 Max | Alibaba (Qwen) | Proprietary | 1M | 22.1 | $2.50 | $7.50 | — |
| 135 | Alibaba (Qwen) Qwen3.6 35B-A3B | Alibaba (Qwen) | Open | 262K | 22.1 | $0.25 | $1.49 | — |
| 136 | Amazon Nova 2.0 Pro Preview | Amazon | Proprietary | — | 21.9 | — | — | — |
| 137 | Moonshot AI Kimi K2.6 | Moonshot AI | Open | 262K | 21.9 | $0.95 | $4 | — |
| 138 | Alibaba (Qwen) Qwen3.7 Plus | Alibaba (Qwen) | Proprietary | 1M | 21.4 | $0.40 | $1.60 | — |
| 139 | Meta Llama 3-70B | Meta | Open | — | 21.1 | — | — | 104 |
| 140 | Meta Llama 3.1-405B | Meta | Open | — | 21.0 | — | — | 78 |
| 141 | OpenAI GPT-4o | OpenAI | Proprietary | 128K | 21.0 | $2.50 | $10 | — |
| 142 | Google Gemma 3 4B | Open | 131K | 20.9 | $0.04 | $0.08 | 72 | |
| 143 | Meta Llama 3.2 3B | Meta | Open | 131K | 20.1 | $0.05 | $0.33 | — |
| 144 | Alibaba (Qwen) Qwen2.5-VL 72B Instruct | Alibaba (Qwen) | Open | 131K | 18.6 | $2.80 | $8.40 | 43 |
| 145 | Google Gemini 1.5 Pro (May 2024) | Proprietary | — | 17.9 | — | — | — | |
| 146 | Alibaba (Qwen) Qwen2-72B | Alibaba (Qwen) | Open | — | 17.0 | — | — | — |
| 147 | Amazon Amazon Nova Pro | Amazon | Proprietary | 300K | 16.7 | $0.80 | $3.20 | — |
| 148 | Mistral AI Ministral 8B | Mistral AI | Open | 262K | 16.4 | $0.15 | $0.15 | — |
| 149 | NVIDIA Llama 3.1 Nemotron Ultra 253b v1 | NVIDIA | Open | — | 15.7 | — | — | — |
| 150 | Meta Llama 3.2 1B | Meta | Open | 60K | 14.6 | $0.027 | $0.20 | — |
| 151 | Alibaba (Qwen) Qwen3.5-9B | Alibaba (Qwen) | Open | 262K | 14.5 | $0.10 | $0.15 | — |
| 152 | Google Gemma 3 1B | Open | — | 13.7 | — | — | — | |
| 153 | OpenAI gpt-oss-120b | OpenAI | Open | 131K | 12.2 | $0.037 | $0.17 | 55 |
| 154 | OpenAI gpt-oss-20b | OpenAI | Open | 131K | 9.3 | $0.018 | $0.09 | 96 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Compare the leaders
Frequently asked questions
What is the best AI model for agents and tool use?
As of October 2026, Claude Opus 5 leads the Noometry agentic & tool use ranking with a score of 55.6, ahead of Claude Fable 5 at 54.0.
What are the top 5 in this ranking?
Claude Opus 5, Claude Fable 5, GPT-6 Astra, Claude Opus 4.6, Claude Fable 5.1, 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.