模型排行
315 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
得分前三甲
o3-2025-04-16OpenAI1,380
chatgpt-4o-latest-20250326OpenAI1,361
gpt-4.5-preview-2025-02-27OpenAI1,357
開源前三甲
deepseek-v3-0324DeepSeek · 總第 6 名1,323
deepseek-r1DeepSeek · 總第 9 名1,316
gemma-3-27b-itGoogle · 總第 18 名1,282
這一期的變化
o4-mini (high)智力榜 · 第 1新上榜
o3智力榜 · 第 3新上榜
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)智力榜 · 第 7新上榜
Gemini 2.5 Flash Preview (Reasoning)智力榜 · 第 8新上榜
| 排名 | 變化 | 模型 | 得分 | 置信區間 | 投票 | 價格 $/M |
|---|---|---|---|---|---|---|
| 1 | — | deepseek-v3-0324開源DeepSeek · 另有 1 個檔位 | 1,323 | ±9 | 6,792 | — |
| 2 | — | deepseek-r1開源DeepSeek | 1,316 | ±4 | 16,857 | — |
| 3 | — | gemma-3-27b-it開源Google | 1,282 | ±6 | 10,735 | — |
| 4 | — | command-a-03-2025開源Cohere | 1,264 | ±5 | 8,521 | — |
| 5 | — | qwq-32b開源Alibaba · 另有 1 個檔位 | 1,257 | ±6 | 8,563 | — |
| 6 | — | llama-3.1-405b-instruct-bf16開源Meta | 1,254 | ±2 | 43,785 | — |
| 7 | — | llama-3.1-405b-instruct-fp8開源Meta | 1,253 | ±2 | 63,056 | — |
| 8 | — | llama-4-maverick-17b-128e-instruct開源Meta | 1,250 | ±7 | 5,772 | — |
| 9 | — | llama-3.3-nemotron-49b-super-v1開源NVIDIA | 1,247 | ±11 | 2,368 | — |
| 10 | — | deepseek-v2.5-1210開源DeepSeek · 另有 1 個檔位 | 1,240 | ±6 | 7,239 | — |
| 11 | — | llama-3.3-70b-instruct開源Meta | 1,235 | ±2 | 38,099 | — |
| 12 | — | mistral-large-2407開源Mistral · 另有 1 個檔位 | 1,232 | ±2 | 48,214 | — |
| 13 | — | qwen-max-0919開源Alibaba | 1,231 | ±4 | 17,438 | — |
| 14 | — | athene-v2-chat開源NexusFlow | 1,231 | ±3 | 26,086 | — |
| 15 | — | athene-70b-0725開源NexusFlow | 1,223 | ±4 | 20,580 | — |
| 16 | — | qwen2.5-72b-instruct開源Alibaba | 1,222 | ±2 | 41,532 | — |
| 17 | — | llama-3.1-nemotron-70b-instruct開源NVIDIA | 1,217 | ±6 | 7,576 | — |
| 18 | — | llama-3.1-70b-instruct開源Meta | 1,214 | ±2 | 58,650 | — |
| 19 | — | llama-3.1-tulu-3-70b開源Ai2 | 1,209 | ±9 | 3,011 | — |
| 20 | — | gemma-2-27b-it開源Google | 1,207 | ±2 | 79,532 | — |
| 21 | — | jamba-1.5-large開源AI21 Labs | 1,206 | ±5 | 9,122 | — |
| 22 | — | llama-3.1-nemotron-51b-instruct開源NVIDIA | 1,204 | ±8 | 3,889 | — |
| 23 | — | gemma-2-9b-it-simpo開源Princeton | 1,200 | ±5 | 10,548 | — |
| 24 | — | command-r-plus-08-2024開源Cohere | 1,197 | ±6 | 10,534 | — |
| 25 | — | nemotron-4-340b-instruct開源NVIDIA | 1,196 | ±4 | 20,614 | — |
| 26 | — | llama-3-70b-instruct開源Meta | 1,195 | ±2 | 163,662 | — |
| 27 | ▲ 1 | mistral-small-24b-instruct-2501開源Mistral | 1,192 | ±4 | 15,089 | — |
| 28 | ▲ 1 | qwen2.5-coder-32b-instruct開源Alibaba | 1,190 | ±6 | 5,731 | — |
| 29 | ▲ 1 | c4ai-aya-expanse-32b開源Cohere | 1,185 | ±3 | 28,752 | — |
| 30 | ▲ 1 | command-r-plus開源Cohere | 1,183 | ±2 | 80,848 | — |
| 31 | ▲ 1 | deepseek-coder-v2開源DeepSeek | 1,182 | ±3 | 15,757 | — |
| 32 | ▲ 1 | qwen2-72b-instruct開源Alibaba | 1,181 | ±3 | 38,886 | — |
| 33 | ▲ 1 | gemma-2-9b-it開源Google | 1,180 | ±2 | 57,206 | — |
| 34 | ▲ 1 | phi-4開源Microsoft | 1,177 | ±3 | 25,228 | — |
| 35 | ▲ 1 | command-r-08-2024開源Cohere | 1,176 | ±5 | 10,843 | — |
| 36 | ▲ 2 | jamba-1.5-mini開源AI21 Labs | 1,160 | ±5 | 9,273 | — |
| 37 | — | ministral-8b-2410開源Mistral | 1,160 | ±6 | 5,108 | — |
| 38 | ▲ 1 | qwen1.5-110b-chat開源Alibaba | 1,155 | ±3 | 27,438 | — |
| 39 | ▲ 1 | c4ai-aya-expanse-8b開源Cohere | 1,151 | ±5 | 10,397 | — |
| 40 | ▲ 1 | mixtral-8x22b-instruct-v0.1開源Mistral | 1,149 | ±3 | 53,758 | — |
| 41 | ▲ 1 | qwen1.5-72b-chat開源Alibaba | 1,148 | ±3 | 40,670 | — |
| 42 | ▲ 1 | command-r開源Cohere | 1,148 | ±2 | 56,381 | — |
| 43 | ▲ 1 | llama-3.1-tulu-3-8b開源Ai2 | 1,147 | ±9 | 3,076 | — |
| 44 | ▲ 1 | llama-3-8b-instruct開源Meta | 1,143 | ±2 | 109,091 | — |
| 45 | ▲ 1 | granite-3.1-8b-instruct開源IBM | 1,135 | ±8 | 3,293 | — |
| 46 | ▲ 1 | yi-1.5-34b-chat開源01 AI | 1,134 | ±4 | 25,131 | — |
| 47 | ▲ 1 | llama-3.1-8b-instruct開源Meta | 1,133 | ±3 | 52,586 | — |
| 48 | ▲ 1 | zephyr-orpo-141b-A35b-v0.1開源HuggingFace | 1,130 | ±6 | 4,860 | — |
| 49 | ▲ 1 | qwen1.5-32b-chat開源Alibaba | 1,126 | ±4 | 22,757 | — |
| 50 | ▲ 1 | phi-3-medium-4k-instruct開源Microsoft | 1,118 | ±4 | 26,109 | — |
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