模型排行
277 個模型 · 2 個榜單 · 2 個數據來源
人氣王座
開源之光
國產之光
最多人測
開源前三甲
deepseek-r1DeepSeek · 總第 4 名1,317
deepseek-v3DeepSeek · 總第 11 名1,276
gemma-3-27b-itGoogle · 總第 12 名1,276
這一期的變化
Sonar智力榜 · 第 15新上榜
Sonar Pro智力榜 · 第 16新上榜
Nova Lite智力榜 · 第 42新上榜
Jamba 1.6 Large智力榜 · 第 45新上榜
Phi-4 Multimodal Instruct智力榜 · 第 62新上榜
| 排名 | 變化 | 模型 | 得分 | 置信區間 | 投票 | 價格 $/M |
|---|---|---|---|---|---|---|
| 1 | — | deepseek-r1開源DeepSeek | 1,317 | ±6 | 11,355 | — |
| 2 | — | deepseek-v3開源DeepSeek | 1,276 | ±4 | 22,854 | — |
| 3 | 新 | gemma-3-27b-it開源Google | 1,276 | ±9 | 4,794 | — |
| 4 | ▲ 61 | qwq-32b開源Alibaba · 另有 1 個檔位 | 1,254 | ±11 | 2,691 | — |
| 5 | ▼ 2 | llama-3.1-405b-instruct-bf16開源Meta | 1,253 | ±4 | 37,887 | — |
| 6 | ▼ 2 | llama-3.1-405b-instruct-fp8開源Meta | 1,253 | ±3 | 63,074 | — |
| 7 | ▼ 2 | deepseek-v2.5-1210開源DeepSeek · 另有 1 個檔位 | 1,240 | ±6 | 7,251 | — |
| 8 | ▼ 2 | llama-3.3-70b-instruct開源Meta | 1,235 | ±4 | 32,176 | — |
| 9 | ▼ 2 | mistral-large-2407開源Mistral · 另有 1 個檔位 | 1,231 | ±4 | 48,215 | — |
| 10 | ▼ 2 | qwen-max-0919開源Alibaba | 1,231 | ±5 | 17,435 | — |
| 11 | ▼ 2 | athene-v2-chat開源NexusFlow | 1,230 | ±4 | 26,106 | — |
| 12 | ▼ 2 | athene-70b-0725開源NexusFlow | 1,223 | ±5 | 20,596 | — |
| 13 | ▼ 2 | qwen2.5-72b-instruct開源Alibaba | 1,222 | ±3 | 41,550 | — |
| 14 | ▼ 2 | llama-3.1-nemotron-70b-instruct開源NVIDIA | 1,216 | ±6 | 7,581 | — |
| 15 | ▼ 2 | llama-3.1-70b-instruct開源Meta | 1,214 | ±3 | 58,675 | — |
| 16 | ▼ 2 | llama-3.1-tulu-3-70b開源Ai2 | 1,208 | ±9 | 3,011 | — |
| 17 | ▼ 2 | gemma-2-27b-it開源Google | 1,207 | ±3 | 79,534 | — |
| 18 | ▼ 2 | jamba-1.5-large開源AI21 Labs | 1,205 | ±6 | 9,129 | — |
| 19 | ▼ 2 | llama-3.1-nemotron-51b-instruct開源NVIDIA | 1,204 | ±8 | 3,887 | — |
| 20 | ▼ 2 | gemma-2-9b-it-simpo開源Princeton | 1,200 | ±5 | 10,554 | — |
| 21 | ▼ 2 | command-r-plus-08-2024開源Cohere | 1,197 | ±5 | 10,542 | — |
| 22 | ▼ 2 | nemotron-4-340b-instruct開源NVIDIA | 1,196 | ±4 | 20,609 | — |
| 23 | ▼ 2 | llama-3-70b-instruct開源Meta | 1,195 | ±2 | 163,686 | — |
| 24 | ▼ 2 | qwen2.5-coder-32b-instruct開源Alibaba | 1,190 | ±7 | 5,731 | — |
| 25 | ▼ 2 | mistral-small-24b-instruct-2501開源Mistral | 1,187 | ±5 | 11,497 | — |
| 26 | ▼ 2 | c4ai-aya-expanse-32b開源Cohere | 1,185 | ±5 | 28,777 | — |
| 27 | ▼ 2 | command-r-plus開源Cohere | 1,183 | ±3 | 80,883 | — |
| 28 | ▼ 2 | deepseek-coder-v2開源DeepSeek | 1,182 | ±5 | 15,757 | — |
| 29 | ▼ 2 | qwen2-72b-instruct開源Alibaba | 1,181 | ±3 | 38,883 | — |
| 30 | ▼ 2 | gemma-2-9b-it開源Google | 1,180 | ±3 | 57,214 | — |
| 31 | ▼ 2 | command-r-08-2024開源Cohere | 1,176 | ±6 | 10,851 | — |
| 32 | ▼ 2 | phi-4開源Microsoft | 1,175 | ±4 | 19,667 | — |
| 33 | ▼ 2 | jamba-1.5-mini開源AI21 Labs | 1,160 | ±6 | 9,274 | — |
| 34 | ▼ 2 | ministral-8b-2410開源Mistral | 1,160 | ±8 | 5,115 | — |
| 35 | ▼ 2 | qwen1.5-110b-chat開源Alibaba | 1,155 | ±4 | 27,438 | — |
| 36 | ▼ 2 | c4ai-aya-expanse-8b開源Cohere | 1,151 | ±5 | 10,400 | — |
| 37 | ▼ 2 | mixtral-8x22b-instruct-v0.1開源Mistral | 1,149 | ±2 | 53,781 | — |
| 38 | ▼ 2 | qwen1.5-72b-chat開源Alibaba | 1,148 | ±3 | 40,664 | — |
| 39 | ▼ 2 | command-r開源Cohere | 1,148 | ±3 | 56,399 | — |
| 40 | ▼ 2 | llama-3.1-tulu-3-8b開源Ai2 | 1,147 | ±10 | 3,075 | — |
| 41 | ▼ 2 | llama-3-8b-instruct開源Meta | 1,142 | ±3 | 109,104 | — |
| 42 | ▼ 2 | granite-3.1-8b-instruct開源IBM | 1,135 | ±10 | 3,299 | — |
| 43 | ▼ 2 | yi-1.5-34b-chat開源01 AI | 1,133 | ±4 | 25,136 | — |
| 44 | ▼ 2 | llama-3.1-8b-instruct開源Meta | 1,133 | ±4 | 52,620 | — |
| 45 | ▼ 2 | zephyr-orpo-141b-A35b-v0.1開源HuggingFace | 1,130 | ±7 | 4,863 | — |
| 46 | ▼ 2 | qwen1.5-32b-chat開源Alibaba | 1,126 | ±4 | 22,772 | — |
| 47 | ▼ 2 | phi-3-medium-4k-instruct開源Microsoft | 1,118 | ±3 | 26,107 | — |
| 48 | ▼ 2 | gemma-2-2b-it開源Google | 1,118 | ±4 | 48,926 | — |
| 49 | ▼ 2 | internlm2_5-20b-chat開源InternLM | 1,116 | ±5 | 10,595 | — |
| 50 | ▼ 2 | mixtral-8x7b-instruct-v0.1開源Mistral | 1,114 | ±0 | 76,134 | — |
智力進步
漲得最多 · Anthropic +57.2目前最高 · Anthropic 64.6最高與最低相差 18.1 分時間範圍 2025年11月 – 2026年11月
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi