Category ranking
Best LLMs for Math in October 2026
As of October 2026, GPT-6.1 Sol leads the Noometry math ranking with a score of 93.7, ahead of GPT-6 Astra at 93.5. The two are close enough that new results could swap them.
Last verified
Competition and research mathematics, from AIME-style problems to unpublished research-level questions.
- GPT-6.1 Sol 93.7
- GPT-6 Astra 93.5
- Claude Opus 5.5 91.8
- Claude Fable 5.1 89.6
- Claude Fable 5 88.5
- Claude Sonnet 5.5 87.9
- GPT-6 Sol 87.2
- Claude Opus 5 86.2
- GPT-5.6 Sol 85.6
- GPT-5.5 Pro 84.0
Full ranking
327 models
| 1 | OpenAI GPT-6.1 Sol | OpenAI | Proprietary | 1.05M | 93.7 | $2 | $10 | — |
| 2 | OpenAI GPT-6 Astra | OpenAI | Proprietary | 1.05M | 93.5 | $10 | $50 | — |
| 3 | Anthropic Claude Opus 5.5 | Anthropic | Proprietary | 1M | 91.8 | $4 | $20 | — |
| 4 | Anthropic Claude Fable 5.1 | Anthropic | Proprietary | 1M | 89.6 | $10 | $50 | — |
| 5 | Anthropic Claude Fable 5 | Anthropic | Proprietary | 1M | 88.5 | $10 | $50 | 25 |
| 6 | Anthropic Claude Sonnet 5.5 | Anthropic | Proprietary | 1M | 87.9 | $2 | $10 | — |
| 7 | OpenAI GPT-6 Sol | OpenAI | Proprietary | 1.05M | 87.2 | $2 | $10 | — |
| 8 | Anthropic Claude Opus 5 | Anthropic | Proprietary | 1M | 86.2 | $5 | $25 | — |
| 9 | OpenAI GPT-5.6 Sol | OpenAI | Proprietary | 1.05M | 85.6 | $4 | $20 | 10 |
| 10 | OpenAI GPT-5.5 Pro | OpenAI | Proprietary | 1.05M | 84.0 | $30 | $180 | — |
| 11 | OpenAI GPT-5.5 | OpenAI | Proprietary | 1.05M | 81.7 | $5 | $30 | 25 |
| 12 | OpenAI GPT-5.6 Terra | OpenAI | Proprietary | 1.05M | 81.6 | $2 | $12 | 11 |
| 13 | Anthropic Claude Opus 4.8 | Anthropic | Proprietary | 1M | 78.4 | $5 | $25 | 34 |
| 14 | OpenAI GPT-5.6 Luna | OpenAI | Proprietary | 1.05M | 77.7 | $0.20 | $1.20 | 12 |
| 15 | OpenAI GPT-6 Luna | OpenAI | Proprietary | 1.05M | 76.1 | $0.10 | $0.50 | — |
| 16 | Moonshot AI Kimi K3 | Moonshot AI | Open | 1.05M | 74.2 | $3 | $15 | — |
| 17 |  Google Gemini 4 Argon | Proprietary | — | 73.9 | — | — | — | |
| 18 | Anthropic Claude Haiku 5.5 | Anthropic | Proprietary | 1M | 73.6 | $0.10 | $0.50 | — |
| 19 | OpenAI GPT-5.4 | OpenAI | Proprietary | 1.05M | 73.5 | $2.50 | $15 | 12 |
| 20 |  Alibaba (Qwen) Qwen3.8 Max | Alibaba (Qwen) | Proprietary | 1M | 73.2 | $2 | $6 | — |
| 21 |  Meta Muse Spark 1.3 | Meta | Proprietary | 1.05M | 73.1 | $1.25 | $4.25 | — |
| 22 | OpenAI GPT-5.4 Pro | OpenAI | Proprietary | 1.05M | 72.4 | $30 | $180 | — |
| 23 | Google Gemini 3.7 Flash | Proprietary | 1.05M | 69.6 | $0.75 | $3.75 | — | |
| 24 | xAI Grok 4.6 | xAI | Proprietary | 500K | 67.0 | $2 | $6 | — |
| 25 |  DeepSeek DeepSeek V4.1 Flash | DeepSeek | Open | 1M | 66.7 | $0.15 | $0.60 | — |
| 26 | Anthropic Claude Opus 4.7 | Anthropic | Proprietary | 1M | 66.7 | $5 | $25 | 33 |
| 27 | Anthropic Claude Sonnet 5 | Anthropic | Proprietary | 1M | 66.2 | $2 | $10 | — |
| 28 | Google Gemini 3.8 Flash | Proprietary | 1.05M | 65.3 | $0.75 | $3.75 | — | |
| 29 | OpenAI GPT-5.2 Pro | OpenAI | Proprietary | 400K | 65.3 | $21 | $168 | — |
| 30 | DeepSeek DeepSeek V4 Pro | DeepSeek | Open | 1M | 64.8 | $0.66 | $1.98 | 16 |
| 31 | Anthropic Claude Opus 4.6 | Anthropic | Proprietary | 1M | 63.0 | $5 | $25 | 19 |
| 32 | Alibaba (Qwen) Qwen3.7 Max | Alibaba (Qwen) | Proprietary | 1M | 62.4 | $2.50 | $7.50 | — |
| 33 | Z.ai (Zhipu) GLM-5.3 | Z.ai (Zhipu) | Open | 1M | 62.3 | $1.40 | $4.40 | — |
| 34 | Google Gemini 3.1 Pro Preview | Proprietary | 1.05M | 62.1 | $2 | $12 | — | |
| 35 | xAI Grok 4.5 | xAI | Proprietary | 500K | 60.9 | $2 | $6 | 4 |
| 36 | Google Gemini 3.5 Flash | Proprietary | 1.05M | 60.7 | $1.50 | $9 | — | |
| 37 | DeepSeek DeepSeek V4 Flash | DeepSeek | Open | 1M | 60.3 | $0.15 | $0.60 | 6 |
| 38 | OpenAI GPT-5.2 | OpenAI | Proprietary | 400K | 60.0 | $1.75 | $14 | 15 |
| 39 | xAI Grok 4.7 | xAI | Proprietary | 500K | 57.8 | $2 | $6 | — |
| 40 | Google Gemini 3.6 Flash | Proprietary | 1.05M | 57.3 | $0.75 | $3.75 | — | |
| 41 | Moonshot AI Kimi K2.6 | Moonshot AI | Open | 262K | 57.0 | $0.95 | $4 | — |
| 42 |  Tencent Hy4 preview | Tencent | Open | 1.05M | 55.7 | $0.75 | $2.25 | — |
| 43 | Z.ai (Zhipu) GLM-5.2 | Z.ai (Zhipu) | Open | 1M | 55.7 | $1.40 | $4.40 | 23 |
| 44 | OpenAI GPT-5 | OpenAI | Proprietary | 400K | 55.0 | $1.25 | $10 | 2 |
| 45 | Xiaomi MiMo-V2.6-Pro | Xiaomi | Open | 1.05M | 54.5 | $0.43 | $0.87 | — |
| 46 | Alibaba (Qwen) Qwen3.6 Max Preview | Alibaba (Qwen) | Proprietary | 262K | 54.1 | $1.30 | $7.80 | — |
| 47 | Z.ai (Zhipu) GLM-5.3-Flash | Z.ai (Zhipu) | Open | 1M | 53.3 | $0.15 | $0.50 | — |
| 48 | Moonshot AI Kimi K2.7 Code | Moonshot AI | Open | 262K | 52.9 | $0.95 | $4 | — |
| 49 | Anthropic Claude Sonnet 4.6 | Anthropic | Proprietary | 1M | 52.9 | $3 | $15 | — |
| 50 | OpenAI gpt-oss-120b | OpenAI | Open | 131K | 52.5 | $0.037 | $0.17 | 55 |
| 51 | OpenAI GPT-5.1 | OpenAI | Proprietary | 400K | 52.2 | $1.25 | $10 | — |
| 52 | Xiaomi MiMo-V2.6-Flash | Xiaomi | Open | 1.05M | 51.9 | $0.14 | $0.28 | — |
| 53 | Moonshot AI Kimi K2.5 | Moonshot AI | Open | 262K | 51.8 | $0.45 | $2.25 | 66 |
| 54 | Alibaba (Qwen) Qwen3.6 Plus | Alibaba (Qwen) | Proprietary | 1M | 51.8 | $0.50 | $3 | — |
| 55 | Google Gemini 3 Flash Preview | Proprietary | 1.05M | 51.7 | $0.50 | $3 | — | |
| 56 | Alibaba (Qwen) Qwen3.7 Plus | Alibaba (Qwen) | Proprietary | 1M | 50.5 | $0.40 | $1.60 | — |
| 57 | Alibaba (Qwen) Qwen3 235B-A22B | Alibaba (Qwen) | Open | 131K | 50.4 | $0.70 | $2.80 | 85 |
| 58 | OpenAI o3 | OpenAI | Proprietary | 200K | 50.2 | $2 | $8 | 3 |
| 59 | Google Gemini 3 Pro | Proprietary | — | 49.9 | — | — | 1 | |
| 60 | Z.ai (Zhipu) GLM-5.1 | Z.ai (Zhipu) | Open | 200K | 49.7 | $1.40 | $4.40 | — |
| 61 | Alibaba (Qwen) Qwen3.5 Plus | Alibaba (Qwen) | Proprietary | 1M | 49.6 | $0.40 | $2.40 | — |
| 62 | Alibaba (Qwen) Qwen3.6 27B | Alibaba (Qwen) | Open | 262K | 48.5 | $0.60 | $3.60 | — |
| 63 | OpenAI GPT-5 Pro | OpenAI | Proprietary | 400K | 48.5 | $15 | $120 | 5 |
| 64 | xAI Grok 4 | xAI | Proprietary | — | 48.4 | — | — | 1 |
| 65 | xAI Grok 4.20 (Non-Reasoning) | xAI | Proprietary | 1M | 48.2 | $1.25 | $2.50 | 61 |
| 66 | Meta Muse Spark | Meta | Proprietary | — | 47.8 | — | — | — |
| 67 | Google Gemma 4 26B A4B IT | Open | 262K | 47.6 | $0.0675 | $0.23 | — | |
| 68 | Moonshot AI Kimi K2 Thinking Turbo | Moonshot AI | Open | — | 47.4 | — | — | — |
| 69 | OpenAI GPT-5 Mini | OpenAI | Proprietary | 400K | 46.7 | $0.25 | $2 | 3 |
| 70 | Meta Muse Spark 1.2 | Meta | Proprietary | 1.05M | 46.4 | $1.25 | $4.25 | — |
| 71 | Z.ai (Zhipu) GLM-5 | Z.ai (Zhipu) | Open | 205K | 46.4 | $1 | $3.20 | 23 |
| 72 |  StepFun Step 5 Preview | StepFun | Proprietary | 1.02M | 46.1 | $1 | $2.70 | — |
| 73 | Alibaba (Qwen) Qwen3.5 397B-A17B | Alibaba (Qwen) | Open | 262K | 46.1 | $0.60 | $3.60 | 9 |
| 74 | xAI Grok 4.3 | xAI | Proprietary | 1M | 46.0 | $1.25 | $2.50 | — |
| 75 | OpenAI GPT-5.4 mini | OpenAI | Proprietary | 400K | 45.5 | $0.75 | $4.50 | 10 |
| 76 | Meta Muse Spark 1.1 | Meta | Proprietary | 1.05M | 45.5 | $1.25 | $4.25 | — |
| 77 | Thinking Machines Lab Inkling-Small | Thinking Machines Lab | Open | 524K | 45.1 | $0.45 | $1.20 | — |
| 78 | Anthropic Claude Haiku 4.5 | Anthropic | Proprietary | 200K | 44.9 | $1 | $5 | — |
| 79 | DeepSeek DeepSeek-R1 | DeepSeek | Proprietary | 164K | 43.8 | $0.50 | $2.15 | 10 |
| 80 | Anthropic Claude Sonnet 4 | Anthropic | Proprietary | 200K | 43.3 | $3 | $15 | 31 |
| 81 | Google Gemma 4 31B IT | Open | 262K | 43.2 | $0.09 | $0.34 | 3 | |
| 82 | StepFun Step 3.7 Flash | StepFun | Open | 256K | 42.9 | $0.18 | $1.11 | — |
| 83 | Moonshot AI Kimi K2 (Jul 2025) | Moonshot AI | Open | 262K | 42.7 | $0.57 | $2.30 | 201 |
| 84 | StepFun Step 3.5 Flash | StepFun | Open | 256K | 42.6 | $0.10 | $0.30 | — |
| 85 | xAI Grok-3 mini | xAI | Proprietary | — | 42.1 | — | — | 10 |
| 86 | Anthropic Claude Opus 4 | Anthropic | Proprietary | 200K | 42.0 | $15 | $75 | 29 |
| 87 | DeepSeek DeepSeek-V3.2-Exp | DeepSeek | Open | 164K | 41.7 | $0.26 | $0.38 | 16 |
| 88 | OpenAI GPT-5.4 nano | OpenAI | Proprietary | 400K | 40.9 | $0.20 | $1.25 | 19 |
| 89 | OpenAI o4-mini | OpenAI | Proprietary | 200K | 40.8 | $1.10 | $4.40 | 6 |
| 90 | Google Gemini 3.1 Flash Lite | Proprietary | 1.05M | 40.7 | $0.25 | $1.50 | 10 | |
| 91 |  Mistral AI Mistral Large 4 | Mistral AI | Proprietary | 1.05M | 40.4 | $0.68 | $2.09 | — |
| 92 |  Baidu ERNIE 5.1 | Baidu | Proprietary | — | 40.3 | — | — | — |
| 93 | Tencent Hy3 | Tencent | Open | 262K | 40.1 | $0.0825 | $0.33 | — |
| 94 | Alibaba (Qwen) Qwen3.5 Max Preview | Alibaba (Qwen) | Proprietary | — | 40.1 | — | — | — |
| 95 |  MiniMax MiniMax-M3 | MiniMax | Open | 1M | 40.0 | $0.30 | $1.20 | — |
| 96 | Xiaomi MiMo-V2.5-Pro | Xiaomi | Open | 1.05M | 40.0 | $0.43 | $0.87 | — |
| 97 | Alibaba (Qwen) Qwen3.5 35B-A3B | Alibaba (Qwen) | Open | 262K | 39.9 | $0.25 | $2 | — |
| 98 | Google Gemini 2.5 Flash | Proprietary | 1.05M | 39.9 | $0.30 | $2.50 | 152 | |
| 99 | Alibaba (Qwen) Qwen3 32B | Alibaba (Qwen) | Open | 131K | 39.7 | $0.70 | $2.80 | 86 |
| 100 | Google Gemini 2.0 Pro | Proprietary | — | 39.7 | — | — | — | |
| 101 |  NVIDIA Nemotron 3 Super | NVIDIA | Open | 262K | 39.6 | $0.08 | $0.45 | — |
| 102 | Xiaomi MiMo-V2-Pro | Xiaomi | Proprietary | 1.05M | 39.5 | $0.43 | $0.87 | — |
| 103 | OpenAI gpt-oss-20b | OpenAI | Open | 131K | 39.4 | $0.018 | $0.09 | 96 |
| 104 | xAI Grok 4.20 Multi-Agent | xAI | Proprietary | 1M | 39.4 | $1.25 | $2.50 | — |
| 105 | Moonshot AI Kimi K2.5 Instant | Moonshot AI | Open | — | 39.4 | — | — | — |
| 106 | Z.ai (Zhipu) GLM-5V-Turbo | Z.ai (Zhipu) | Proprietary | 200K | 39.4 | $1.20 | $4 | — |
| 107 | Meituan Longcat Flash Chat | Meituan | Open | — | 39.4 | — | — | 69 |
| 108 |  ByteDance Seed Seed 2.0 Pro | ByteDance Seed | Proprietary | 256K | 39.3 | $0.50 | $3 | — |
| 109 | Amazon Amazon Nova Experimental Chat 26 02 10 | Amazon | Proprietary | — | 39.3 | — | — | — |
| 110 | Baidu ERNIE 5.0 0110 | Baidu | Proprietary | — | 39.3 | — | — | — |
| 111 | Alibaba (Qwen) Qwen3.5 122B-A10B | Alibaba (Qwen) | Open | 262K | 39.1 | $0.40 | $3.20 | — |
| 112 | Z.ai (Zhipu) GLM-4.6 | Z.ai (Zhipu) | Open | 205K | 39.1 | $0.60 | $2.20 | 12 |
| 113 | Mistral AI Mistral Medium 3.5 | Mistral AI | Open | 262K | 39.1 | $1.50 | $7.50 | 50 |
| 114 | Amazon Amazon Nova Experimental Chat 11 10 | Amazon | Proprietary | — | 39.1 | — | — | — |
| 115 | Xiaomi MiMo-V2-Omni | Xiaomi | Proprietary | 262K | 39.1 | $0.14 | $0.28 | — |
| 116 | Z.ai (Zhipu) GLM-4.5 | Z.ai (Zhipu) | Open | 131K | 39.0 | $0.60 | $2.20 | 32 |
| 117 | Alibaba (Qwen) Qwen3.6 Flash | Alibaba (Qwen) | Proprietary | 1M | 39.0 | $0.19 | $1.13 | — |
| 118 | Alibaba (Qwen) Qwen3-VL 235B-A22B | Alibaba (Qwen) | Open | 131K | 39.0 | $0.70 | $2.80 | — |
| 119 | Amazon Amazon Nova Experimental Chat 10 20 | Amazon | Proprietary | — | 39.0 | — | — | — |
| 120 | xAI Grok 4.1 | xAI | Proprietary | — | 38.9 | — | — | — |
| 121 | Alibaba (Qwen) Qwen3.6 35B-A3B | Alibaba (Qwen) | Open | 262K | 38.9 | $0.25 | $1.49 | — |
| 122 | DeepSeek DeepSeek-V3.1 | DeepSeek | Open | 164K | 38.9 | $0.25 | $0.95 | 328 |
| 123 | xAI Grok 4 Fast | xAI | Proprietary | — | 38.9 | — | — | 577 |
| 124 | Amazon Amazon Nova Experimental Chat 12 10 | Amazon | Proprietary | — | 38.9 | — | — | — |
| 125 | Meta Muse Glimmer | Meta | Open | — | 38.8 | — | — | — |
| 126 | Alibaba (Qwen) Qwen3-Next 80B-A3B Instruct | Alibaba (Qwen) | Open | 131K | 38.8 | $0.50 | $2 | 111 |
| 127 | Alibaba (Qwen) Qwen3.5 27B | Alibaba (Qwen) | Open | 262K | 38.8 | $0.30 | $2.40 | — |
| 128 |  Upstage Solar Pro4 | Upstage | Proprietary | 524K | 38.8 | $0.30 | $1.20 | — |
| 129 | Mistral AI Mistral Large 3 | Mistral AI | Open | 262K | 38.7 | $0.25 | $0.75 | 7 |
| 130 | Alibaba (Qwen) Qwen3 Max | Alibaba (Qwen) | Proprietary | 262K | 38.7 | $1.20 | $6 | 48 |
| 131 | Tencent Hunyuan T1 20250711 | Tencent | Proprietary | — | 38.7 | — | — | — |
| 132 | Anthropic Claude Opus 4.5 | Anthropic | Proprietary | 200K | 38.6 | $5 | $25 | 13 |
| 133 | Alibaba (Qwen) Qwen3 14B | Alibaba (Qwen) | Open | 131K | 38.6 | $0.35 | $1.40 | 79 |
| 134 | OpenAI Chatgpt 4o Latest 20250326 | OpenAI | Proprietary | — | 38.6 | — | — | 21 |
| 135 | Z.ai (Zhipu) GLM-4.7 | Z.ai (Zhipu) | Open | 205K | 38.6 | $0.60 | $2.20 | — |
| 136 | Amazon Amazon Nova Experimental Chat 26 01 10 | Amazon | Proprietary | — | 38.5 | — | — | — |
| 137 | DeepSeek DeepSeek-V3.1-Terminus | DeepSeek | Open | 164K | 38.5 | $0.27 | $1 | 30 |
| 138 | MiniMax MiniMax-M2.1 | MiniMax | Open | 205K | 38.3 | $0.30 | $1.20 | — |
| 139 | Xiaomi MiMo-V2-Flash | Xiaomi | Open | 262K | 38.3 | $0.14 | $0.28 | — |
| 140 | Alibaba (Qwen) Qwen3.7 Flash | Alibaba (Qwen) | Proprietary | 1M | 38.3 | $0.03 | $0.13 | — |
| 141 | NVIDIA Nvidia Llama 3.3 Nemotron Super 49b v1.5 | NVIDIA | Open | 131K | 38.2 | $0.40 | $0.40 | — |
| 142 | OpenAI GPT-5.3 Chat | OpenAI | Proprietary | 128K | 38.2 | $1.75 | $14 | — |
| 143 | Alibaba (Qwen) QwQ-32B | Alibaba (Qwen) | Open | — | 38.0 | — | — | — |
| 144 | xAI Grok 3 | xAI | Proprietary | — | 38.0 | — | — | 42 |
| 145 | Google Gemini 2.5 Flash-Lite | Proprietary | 1.05M | 38.0 | $0.10 | $0.40 | 172 | |
| 146 | Google Gemini 2.0 Flash (Feb 2025) | Proprietary | — | 37.9 | — | — | 92 | |
| 147 | NVIDIA Nemotron 3 Nano 30B A3B | NVIDIA | Open | 262K | 37.8 | $0.05 | $0.20 | — |
| 148 | StepFun Step 3 | StepFun | Open | — | 37.6 | — | — | 7 |
| 149 |  Arcee AI Trinity Large Thinking | Arcee AI | Open | 262K | 37.6 | $0.25 | $0.80 | — |
| 150 | Alibaba (Qwen) Qwen3-Coder 480B-A35B Instruct | Alibaba (Qwen) | Open | 262K | 37.6 | $1.50 | $7.50 | 67 |
| 151 | MiniMax MiniMax M1 | MiniMax | Open | 1M | 37.5 | $0.55 | $2.20 | — |
| 152 | NVIDIA Llama 3.1 Nemotron Ultra 253b v1 | NVIDIA | Open | — | 37.5 | — | — | — |
| 153 | Tencent Hunyuan Turbos 20250226 | Tencent | Proprietary | — | 37.5 | — | — | — |
| 154 | NVIDIA Nemotron 3.5 Lightning | NVIDIA | Open | 262K | 37.5 | $0.05 | $0.20 | — |
| 155 | Amazon Nova 2 Lite | Amazon | Proprietary | 1M | 37.5 | $0.30 | $2.50 | — |
| 156 | Anthropic Claude 3.7 Sonnet | Anthropic | Proprietary | — | 37.5 | — | — | — |
| 157 | Alibaba (Qwen) Qwen3-30B-A3B | Alibaba (Qwen) | Open | 41K | 37.4 | $0.12 | $0.50 | 42 |
| 158 | Alibaba (Qwen) Qwen3.5-Flash | Alibaba (Qwen) | Proprietary | 1M | 37.4 | $0.10 | $0.40 | — |
| 159 | Z.ai (Zhipu) GLM-4.5V | Z.ai (Zhipu) | Open | 64K | 37.4 | $0.60 | $1.80 | 34 |
| 160 | MiniMax MiniMax-M2 | MiniMax | Open | 205K | 37.3 | $0.30 | $1.20 | 17 |
| 161 | Alibaba (Qwen) Qwen3.8 27B | Alibaba (Qwen) | Open | 262K | 37.1 | $0.99 | $1.49 | — |
| 162 | Alibaba (Qwen) Qwen2.5-Max | Alibaba (Qwen) | Proprietary | — | 36.9 | — | — | — |
| 163 | Xiaomi MiMo-V2.5 | Xiaomi | Open | 1.05M | 36.8 | $0.14 | $0.28 | — |
| 164 | StepFun Step 1o Turbo 202506 | StepFun | Proprietary | — | 36.6 | — | — | — |
| 165 |  Allen Institute for AI (Ai2) Olmo 3 32b Think | Allen Institute for AI (Ai2) | Open | — | 36.5 | — | — | — |
| 166 | IBM Granite 4.1 8b | IBM | Open | — | 36.4 | — | — | — |
| 167 | Allen Institute for AI (Ai2) Olmo 3.1 32b Instruct | Allen Institute for AI (Ai2) | Open | — | 36.3 | — | — | — |
| 168 | StepFun Step 2 16k Exp 202412 | StepFun | Proprietary | — | 36.3 | — | — | — |
| 169 | Allen Institute for AI (Ai2) Olmo 3.1 32b Think | Allen Institute for AI (Ai2) | Open | — | 36.3 | — | — | — |
| 170 | Z.ai (Zhipu) GLM-4.5-Air | Z.ai (Zhipu) | Open | 131K | 36.2 | $0.20 | $1.10 | 160 |
| 171 |  Cohere Command A | Cohere | Open | 256K | 36.2 | $2.50 | $10 | 28 |
| 172 | 01.AI Yi-Lightning | 01.AI | Proprietary | — | 36.2 | — | — | — |
| 173 | Z.ai (Zhipu) GLM-4.7-Flash | Z.ai (Zhipu) | Open | 200K | 36.1 | $0.06 | $0.40 | — |
| 174 | Alibaba (Qwen) Qwen2.5 Plus 1127 | Alibaba (Qwen) | Proprietary | — | 36.1 | — | — | — |
| 175 | OpenAI o1 | OpenAI | Proprietary | 200K | 36.1 | $15 | $60 | — |
| 176 | DeepSeek DeepSeek-R1-Distill-Llama-70B | DeepSeek | Open | — | 36.0 | — | — | 18 |
| 177 | DeepSeek DeepSeek-V2.5 (Sep 2024) | DeepSeek | Open | — | 35.9 | — | — | — |
| 178 | Tencent Hunyuan Large 2025 02 10 | Tencent | Proprietary | — | 35.8 | — | — | — |
| 179 | Tencent Hunyuan Standard 2025 02 10 | Tencent | Proprietary | — | 35.6 | — | — | — |
| 180 | Tencent Hunyuan Turbo 0110 | Tencent | Proprietary | — | 35.6 | — | — | — |
| 181 | Google Gemini Advanced 0514 | Proprietary | — | 35.5 | — | — | — | |
| 182 | NVIDIA Llama 3.1 Nemotron 70b Instruct | NVIDIA | Open | — | 35.5 | — | — | — |
| 183 | Tencent Hunyuan Large Vision | Tencent | Proprietary | — | 35.5 | — | — | — |
| 184 | DeepSeek DeepSeek-R1-Distill-Qwen-14B | DeepSeek | Open | — | 35.5 | — | — | — |
| 185 | xAI Grok 2 Mini 2024 08 13 | xAI | Proprietary | — | 35.4 | — | — | — |
| 186 | OpenAI o1-mini | OpenAI | Proprietary | — | 35.4 | — | — | — |
| 187 | NVIDIA Nemotron 3 Ultra | NVIDIA | Open | 262K | 35.3 | $0.50 | $2.20 | — |
| 188 | Google Gemma 3n E4b IT | Open | — | 35.1 | — | — | 13 | |
| 189 | Mistral AI Magistral Medium | Mistral AI | Open | 262K | 35.1 | $2 | $5 | 0 |
| 190 | DeepSeek Deepseek Coder v2 | DeepSeek | Open | — | 34.9 | — | — | — |
| 191 | Alibaba (Qwen) Qwen3 8B | Alibaba (Qwen) | Open | 131K | 34.9 | $0.18 | $0.70 | — |
| 192 | Alibaba (Qwen) Qwen3.5-9B | Alibaba (Qwen) | Open | 262K | 34.8 | $0.10 | $0.15 | — |
| 193 | NVIDIA Llama 3.1 Nemotron 51b Instruct | NVIDIA | Open | — | 34.6 | — | — | — |
| 194 | DeepSeek DeepSeek-R1-Distill-Qwen-32B | DeepSeek | Open | — | 34.5 | — | — | — |
| 195 | NVIDIA Nemotron 4 340b Instruct | NVIDIA | Open | — | 34.3 | — | — | — |
| 196 | Google Gemini 2.0 Flash-Lite | Proprietary | — | 34.1 | — | — | — | |
| 197 | Cohere C4ai Aya Expanse 32b | Cohere | Open | 128K | 34.0 | — | — | — |
| 198 | Allen Institute for AI (Ai2) Llama 3.1 Tulu 3 8b | Allen Institute for AI (Ai2) | Open | — | 33.9 | — | — | — |
| 199 | Amazon Nova Premier 1.0 | Amazon | Proprietary | 1M | 33.8 | $2.50 | $12.50 | 9 |
| 200 |  Perplexity Sonar | Perplexity | Proprietary | 128K | 33.7 | $1 | $1 | — |
| 201 | Alibaba (Qwen) Qwen1.5-110B | Alibaba (Qwen) | Open | — | 33.7 | — | — | — |
| 202 |  Microsoft Phi 3 Medium 4k Instruct | Microsoft | Open | — | 33.4 | — | — | — |
| 203 | Cohere C4ai Aya Expanse 8b | Cohere | Open | — | 33.3 | — | — | — |
| 204 | Alibaba (Qwen) Qwen2.5-Coder-32B | Alibaba (Qwen) | Open | 33K | 33.3 | $0.66 | $1 | — |
| 205 | Alibaba (Qwen) Qwen1.5-72B | Alibaba (Qwen) | Open | — | 33.2 | — | — | — |
| 206 | IBM Granite 3.1 2b Instruct | IBM | Open | — | 33.1 | — | — | — |
| 207 | Alibaba (Qwen) Qwen1.5-32B | Alibaba (Qwen) | Open | — | 33.0 | — | — | — |
| 208 | Microsoft Phi 3 Mini 4k Instruct June 2024 | Microsoft | Open | — | 33.0 | — | — | — |
| 209 | IBM Granite 3.1 8b Instruct | IBM | Open | — | 33.0 | — | — | — |
| 210 | IBM Granite 3.0 8b Instruct | IBM | Open | — | 32.8 | — | — | — |
| 211 | OpenAI GPT-4.5 | OpenAI | Proprietary | — | 32.6 | — | — | — |
| 212 | Google Gemma 2 2b IT | Open | — | 32.6 | — | — | — | |
| 213 | Google Gemini 2.5 Pro | Proprietary | 1.05M | 32.5 | $1.25 | $10 | 5 | |
| 214 | Meta Llama 3.2 3B | Meta | Open | 131K | 32.4 | $0.05 | $0.33 | — |
| 215 | Alibaba (Qwen) Qwen1.5-14B | Alibaba (Qwen) | Open | — | 32.4 | — | — | — |
| 216 | Anthropic Claude Sonnet 4.5 | Anthropic | Proprietary | 200K | 32.3 | $3 | $15 | 85 |
| 217 | IBM Granite 3.0 2b Instruct | IBM | Open | — | 32.2 | — | — | — |
| 218 | Microsoft Wizardlm 70b | Microsoft | Open | — | 32.2 | — | — | — |
| 219 | DeepSeek DeepSeek-V3 | DeepSeek | Open | 164K | 32.1 | $0.24 | $0.90 | 73 |
| 220 | Google Gemma 1.1 7b IT | Open | — | 32.0 | — | — | — | |
| 221 | xAI Grok 4.1 Fast | xAI | Proprietary | 128K | 31.9 | $0.20 | $0.50 | — |
| 222 | Microsoft Phi 3 Mini 128k Instruct | Microsoft | Open | — | 31.6 | — | — | — |
| 223 | IBM Granite 4.0 H Small | IBM | Open | — | 31.4 | — | — | — |
| 224 | Alibaba (Qwen) Qwen1.5-7B | Alibaba (Qwen) | Open | — | 31.4 | — | — | — |
| 225 | Thinking Machines Lab Inkling | Thinking Machines Lab | Open | 66K | 31.3 | $1.87 | $4.68 | — |
| 226 | NVIDIA Llama2 70b Steerlm Chat | NVIDIA | Open | — | 31.3 | — | — | — |
| 227 | Alibaba (Qwen) Qwen-14B | Alibaba (Qwen) | Open | — | 31.2 | — | — | — |
| 228 | Google Gemma 7B | Open | — | 31.2 | — | — | — | |
| 229 | Meta Llama 2-13B | Meta | Open | — | 31.1 | — | — | — |
| 230 | Meta Codellama 34b Instruct | Meta | Open | — | 31.0 | — | — | — |
| 231 | Google Palm 2 | Proprietary | — | 30.8 | — | — | — | |
| 232 | Google Gemma 1.1 2b IT | Open | — | 30.8 | — | — | — | |
| 233 | Meta Llama 2-7B | Meta | Open | — | 30.7 | — | — | — |
| 234 | Alibaba (Qwen) Qwen1.5 4b Chat | Alibaba (Qwen) | Open | — | 30.4 | — | — | — |
| 235 | OpenAI GPT-5.1-Codex | OpenAI | Proprietary | 400K | 30.3 | $1.25 | $10 | — |
| 236 | Alibaba (Qwen) Qwen2-72B | Alibaba (Qwen) | Open | — | 30.2 | — | — | — |
| 237 | Allen Institute for AI (Ai2) Olmo 7b Instruct | Allen Institute for AI (Ai2) | Open | — | 30.2 | — | — | — |
| 238 | Microsoft Wizardlm 13b | Microsoft | Open | — | 30.2 | — | — | — |
| 239 | Google Gemma 2B | Open | — | 30.0 | — | — | — | |
| 240 | Alibaba (Qwen) Qwen3-4B | Alibaba (Qwen) | Open | — | 29.7 | — | — | — |
| 241 | OpenAI GPT-5 Nano | OpenAI | Proprietary | 400K | 29.4 | $0.05 | $0.40 | 4 |
| 242 | Cohere Command R+ | Cohere | Open | 128K | 28.9 | $2.50 | $10 | — |
| 243 | Amazon Amazon Nova Pro | Amazon | Proprietary | 300K | 28.5 | $0.80 | $3.20 | — |
| 244 | OpenAI o3-mini | OpenAI | Proprietary | 200K | 28.1 | $1.10 | $4.40 | — |
| 245 | Mistral AI Mistral Medium | Mistral AI | Open | 262K | 28.1 | $1.50 | $7.50 | 68 |
| 246 | Cohere Command R | Cohere | Open | 128K | 28.0 | $0.15 | $0.60 | — |
| 247 | Amazon Amazon Nova Lite | Amazon | Proprietary | 300K | 27.8 | $0.06 | $0.24 | — |
| 248 | Microsoft Phi 3 Small 8k Instruct | Microsoft | Open | — | 27.6 | — | — | — |
| 249 | 01.AI Yi-1.5-34B | 01.AI | Open | — | 27.5 | — | — | — |
| 250 | Microsoft phi-3-medium 14B | Microsoft | Open | — | 27.3 | — | — | — |
| 251 |  Databricks Dolly 2.0-12b | Databricks | Open | — | 27.3 | — | — | — |
| 252 | OpenAI GPT-4.1 nano | OpenAI | Proprietary | 1.05M | 26.9 | $0.10 | $0.40 | 135 |
| 253 | MiniMax MiniMax-M2.5 | MiniMax | Open | 205K | 26.9 | $0.30 | $1.20 | 49 |
| 254 | Amazon Amazon Nova Micro | Amazon | Proprietary | 128K | 26.9 | $0.035 | $0.14 | — |
| 255 | Allen Institute for AI (Ai2) Olmo 2 0325 32b Instruct | Allen Institute for AI (Ai2) | Open | — | 26.8 | — | — | — |
| 256 | Meta Llama 13b | Meta | Open | — | 26.7 | — | — | — |
| 257 | Microsoft Phi 3 Mini 4k Instruct | Microsoft | Open | — | 26.6 | — | — | — |
| 258 | Mistral AI Ministral 3B | Mistral AI | Open | 131K | 26.6 | $0.10 | $0.10 | — |
| 259 | OpenAI GPT-5.5 Instant | OpenAI | Proprietary | — | 26.5 | — | — | — |
| 260 | Mistral AI Mistral Small 3.2 | Mistral AI | Open | 256K | 26.3 | $0.0938 | $0.25 | 68 |
| 261 | Mistral AI Magistral Small | Mistral AI | Open | 128K | 26.2 | $0.50 | $1.50 | 0 |
| 262 | Meta Llama 4 Maverick | Meta | Open | 128K | 26.0 | $0.19 | $0.65 | 456 |
| 263 | MiniMax MiniMax-M2.7 | MiniMax | Open | 205K | 25.9 | $0.30 | $1.20 | — |
| 264 | Google Gemini 3.5 Flash Lite | Proprietary | 1.05M | 25.9 | $0.30 | $2.50 | — | |
| 265 | Google Gemma 3 27B | Open | 131K | 25.9 | $0.08 | $0.16 | 62 | |
| 266 | Google Gemini 1.5 Pro (May 2024) | Proprietary | — | 25.8 | — | — | — | |
| 267 | Mistral AI Ministral 8B | Mistral AI | Open | 262K | 25.7 | $0.15 | $0.15 | — |
| 268 | Mistral AI Mistral Nemo | Mistral AI | Open | 128K | 25.5 | $0.15 | $0.15 | — |
| 269 | Databricks DBRX | Databricks | Open | — | 24.3 | — | — | — |
| 270 | OpenAI GPT-4.1 mini | OpenAI | Proprietary | 1.05M | 24.1 | $0.40 | $1.60 | 86 |
| 271 | Alibaba (Qwen) Qwen Plus | Alibaba (Qwen) | Proprietary | 1M | 23.3 | $0.40 | $1.20 | 37 |
| 272 | Inception Mercury 2.5 | Inception | Proprietary | 260K | 23.3 | $0.04 | $0.15 | — |
| 273 | Allen Institute for AI (Ai2) OLMo 2 Furious 13B | Allen Institute for AI (Ai2) | Open | — | 23.1 | — | — | — |
| 274 | DeepSeek DeepSeek-R1-Distill-Qwen-1.5B | DeepSeek | Open | — | 23.0 | — | — | — |
| 275 | Mistral AI Mixtral 8x22B | Mistral AI | Open | 64K | 22.9 | $2 | $6 | — |
| 276 | Alibaba (Qwen) Qwen Max | Alibaba (Qwen) | Proprietary | 33K | 22.3 | $1.60 | $6.40 | — |
| 277 | Anthropic Claude Opus 4.1 | Anthropic | Proprietary | 200K | 22.3 | $15 | $75 | — |
| 278 | Mistral AI Mistral | Mistral AI | Proprietary | — | 22.3 | — | — | — |
| 279 | Google Gemma 3 12B | Open | 131K | 22.3 | $0.05 | $0.15 | — | |
| 280 | OpenAI GPT-4.1 | OpenAI | Proprietary | 1.05M | 22.3 | $2 | $8 | 116 |
| 281 | Google Gemini 1.5 Flash (May 2024) | Proprietary | — | 22.1 | — | — | — | |
| 282 | 01.AI Yi-34B | 01.AI | Open | — | 21.6 | — | — | — |
| 283 |  Poolside Laguna M.1 | Poolside | Open | 262K | 21.1 | — | — | — |
| 284 | xAI Grok-2 (Dec 2024) | xAI | Proprietary | — | 20.8 | — | — | — |
| 285 | Microsoft Phi-4 | Microsoft | Open | 128K | 20.8 | $0.07 | $0.14 | — |
| 286 | Meta Llama 4 Scout | Meta | Open | 128K | 19.6 | $0.10 | $0.30 | 272 |
| 287 | Alibaba (Qwen) Qwen2.5 72B Instruct | Alibaba (Qwen) | Open | 131K | 19.3 | $1.40 | $5.60 | — |
| 288 | Anthropic Claude 3.5 Sonnet | Anthropic | Proprietary | — | 19.2 | — | — | — |
| 289 | Mistral AI Mixtral 8x7B | Mistral AI | Open | 32K | 18.8 | $0.70 | $0.70 | — |
| 290 | Meta Llama 3.1-405B | Meta | Open | — | 18.4 | — | — | 78 |
| 291 | Mistral AI Mistral Large | Mistral AI | Open | 131K | 18.2 | $2 | $6 | — |
| 292 | Google Gemma 3 4B | Open | 131K | 16.8 | $0.04 | $0.08 | 72 | |
| 293 | Mistral AI Mistral Small | Mistral AI | Open | 262K | 16.4 | $0.15 | $0.60 | 120 |
| 294 | Alibaba (Qwen) Qwen3-1.7B | Alibaba (Qwen) | Open | — | 16.3 | — | — | — |
| 295 | Mistral AI Mistral Small 3 | Mistral AI | Open | 33K | 16.3 | $0.05 | $0.08 | — |
| 296 | Alibaba (Qwen) Qwen2.5 32B Instruct | Alibaba (Qwen) | Open | 131K | 16.2 | $0.70 | $2.80 | — |
| 297 | Alibaba (Qwen) Qwen Turbo | Alibaba (Qwen) | Proprietary | 1M | 15.3 | $0.05 | $0.20 | — |
| 298 | Meta Llama-3.3-70B-Instruct | Meta | Open | 128K | 15.3 | $0.10 | $0.32 | — |
| 299 | Anthropic Claude 3 Opus | Anthropic | Proprietary | — | 14.8 | — | — | — |
| 300 | Mistral AI Mistral Small 3.1 | Mistral AI | Open | 128K | 14.7 | $0.35 | $0.56 | — |
| 301 | Anthropic Claude 3.5 Haiku | Anthropic | Proprietary | — | 14.7 | — | — | — |
| 302 | Google Gemini 1.5 Flash 8B | Proprietary | — | 14.2 | — | — | — | |
| 303 | Allen Institute for AI (Ai2) Tulu 3 (Tülu 3) 70B | Allen Institute for AI (Ai2) | Open | — | 14.2 | — | — | — |
| 304 | Meta Llama 3.1-70B | Meta | Open | 128K | 13.5 | $0.40 | $0.40 | — |
| 305 | Meta Llama 3-70B | Meta | Open | — | 12.8 | — | — | 104 |
| 306 | Alibaba (Qwen) Qwen2.5 7B Instruct | Alibaba (Qwen) | Open | 131K | 12.6 | $0.17 | $0.70 | — |
| 307 | IBM Granite 4.0 Micro | IBM | Open | 131K | 12.0 | $0.017 | $0.11 | — |
| 308 | Meta Llama 3.2 90B | Meta | Open | — | 11.1 | — | — | — |
| 309 | OpenAI GPT-4 | OpenAI | Proprietary | 8K | 10.8 | $30 | $60 | — |
| 310 | Anthropic Claude 3 Sonnet | Anthropic | Proprietary | — | 10.7 | — | — | — |
| 311 | Google Gemma 2 27B | Open | 8K | 10.7 | $0.65 | $0.65 | — | |
| 312 | OpenAI GPT-4o | OpenAI | Proprietary | 128K | 10.6 | $2.50 | $10 | — |
| 313 | Meta Llama 3.2 1B | Meta | Open | 60K | 10.4 | $0.027 | $0.20 | — |
| 314 | OpenAI GPT-4o mini | OpenAI | Proprietary | 128K | 10.4 | $0.15 | $0.60 | 120 |
| 315 | Anthropic Claude 2.1 | Anthropic | Proprietary | — | 10.2 | — | — | — |
| 316 | Google Gemma 3 1B | Open | — | 10.2 | — | — | — | |
| 317 | Meta Llama 3.1-8B | Meta | Open | 128K | 10.2 | $0.05 | $0.08 | — |
| 318 | Google Gemma 2 9B | Open | — | 9.9 | — | — | — | |
| 319 | Anthropic Claude 3 Haiku | Anthropic | Proprietary | — | 9.8 | — | — | 41 |
| 320 | Anthropic Claude 2 | Anthropic | Proprietary | — | 9.3 | — | — | — |
| 321 | Google Gemini 1.0 Pro | Proprietary | — | 9.3 | — | — | — | |
| 322 | OpenAI GPT-4 Turbo | OpenAI | Proprietary | 128K | 9.0 | $10 | $30 | — |
| 323 | Meta Llama 3-8B | Meta | Open | — | 8.8 | — | — | — |
| 324 | DeepSeek DeepSeek LLM 67B | DeepSeek | Open | — | 8.7 | — | — | — |
| 325 | Mistral AI Mistral 7B | Mistral AI | Open | 8K | 8.1 | $0.25 | $0.25 | — |
| 326 | Meta Llama 2-70B | Meta | Open | — | 8.1 | — | — | — |
| 327 | OpenAI GPT-3.5-turbo | OpenAI | Proprietary | 16K | 6.3 | $0.50 | $1.50 | — |
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 math?
As of October 2026, GPT-6.1 Sol leads the Noometry math ranking with a score of 93.7, ahead of GPT-6 Astra at 93.5. The two are close enough that new results could swap them.
What are the top 5 in this ranking?
GPT-6.1 Sol, GPT-6 Astra, Claude Opus 5.5, Claude Fable 5.1, Claude Fable 5, 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.