模型排行
127 個模型 · 1 個榜單 · 1 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
llama-3.1-405b-instruct-fp8Meta · 總第 7 名1,252
llama-3.1-405b-instruct-bf16Meta · 總第 8 名1,251
mistral-large-2407Mistral · 總第 19 名1,230
| 排名 | 變化 | 模型 | 得分 | 置信區間 | 投票 | 價格 $/M |
|---|---|---|---|---|---|---|
| 1 | ▲ 1 | llama-3.1-405b-instruct-fp8開源Meta | 1,252 | ±3 | 39,428 | — |
| 2 | ▼ 1 | llama-3.1-405b-instruct-bf16開源Meta | 1,251 | ±5 | 14,496 | — |
| 3 | — | mistral-large-2407開源Mistral | 1,230 | ±4 | 35,788 | — |
| 4 | 新 | qwen-max-0919開源Alibaba | 1,228 | ±5 | 12,205 | — |
| 5 | ▲ 1 | deepseek-v2.5開源DeepSeek | 1,222 | ±5 | 13,969 | — |
| 6 | ▼ 1 | qwen2.5-72b-instruct開源Alibaba | 1,221 | ±5 | 13,896 | — |
| 7 | ▼ 3 | athene-70b-0725開源NexusFlow | 1,220 | ±4 | 20,703 | — |
| 8 | ▼ 1 | llama-3.1-70b-instruct開源Meta | 1,210 | ±3 | 34,744 | — |
| 9 | ▼ 1 | gemma-2-27b-it開源Google | 1,205 | ±3 | 46,053 | — |
| 10 | ▼ 1 | jamba-1.5-large開源AI21 Labs | 1,202 | ±6 | 9,189 | — |
| 11 | ▼ 1 | gemma-2-9b-it-simpo開源Princeton | 1,198 | ±5 | 10,621 | — |
| 12 | ▼ 1 | nemotron-4-340b-instruct開源NVIDIA | 1,196 | ±4 | 20,656 | — |
| 13 | — | command-r-plus-08-2024開源Cohere | 1,196 | ±5 | 10,523 | — |
| 14 | ▼ 2 | llama-3-70b-instruct開源Meta | 1,194 | ±2 | 163,997 | — |
| 15 | ▼ 1 | command-r-plus開源Cohere | 1,183 | ±2 | 80,926 | — |
| 16 | — | qwen2-72b-instruct開源Alibaba | 1,181 | ±3 | 38,986 | — |
| 17 | ▼ 2 | deepseek-coder-v2開源DeepSeek | 1,180 | ±4 | 15,799 | — |
| 18 | ▼ 1 | gemma-2-9b-it開源Google | 1,175 | ±3 | 34,626 | — |
| 19 | ▼ 1 | command-r-08-2024開源Cohere | 1,175 | ±6 | 10,907 | — |
| 20 | ▼ 1 | jamba-1.5-mini開源AI21 Labs | 1,156 | ±6 | 9,300 | — |
| 21 | ▼ 1 | qwen1.5-110b-chat開源Alibaba | 1,155 | ±3 | 27,476 | — |
| 22 | ▼ 1 | mixtral-8x22b-instruct-v0.1開源Mistral | 1,150 | ±3 | 53,836 | — |
| 23 | — | qwen1.5-72b-chat開源Alibaba | 1,148 | ±3 | 40,642 | — |
| 24 | ▼ 2 | command-r開源Cohere | 1,148 | ±3 | 56,425 | — |
| 25 | ▼ 1 | llama-3-8b-instruct開源Meta | 1,142 | ±2 | 109,414 | — |
| 26 | ▼ 1 | yi-1.5-34b-chat開源01 AI | 1,133 | ±4 | 25,147 | — |
| 27 | ▼ 1 | zephyr-orpo-141b-A35b-v0.1開源HuggingFace | 1,131 | ±6 | 4,862 | — |
| 28 | ▼ 1 | qwen1.5-32b-chat開源Alibaba | 1,127 | ±3 | 22,763 | — |
| 29 | ▼ 1 | llama-3.1-8b-instruct開源Meta | 1,125 | ±3 | 32,937 | — |
| 30 | ▼ 1 | phi-3-medium-4k-instruct開源Microsoft | 1,119 | ±4 | 26,163 | — |
| 31 | — | mixtral-8x7b-instruct-v0.1開源Mistral | 1,114 | ±0 | 76,163 | — |
| 32 | — | dbrx-instruct-preview開源Databricks | 1,114 | ±3 | 33,735 | — |
| 33 | ▼ 3 | internlm2_5-20b-chat開源InternLM | 1,112 | ±5 | 9,176 | — |
| 34 | ▼ 1 | gemma-2-2b-it開源Google | 1,110 | ±4 | 26,098 | — |
| 35 | ▼ 1 | qwen1.5-14b-chat開源Alibaba | 1,107 | ±4 | 18,681 | — |
| 36 | ▼ 1 | wizardlm-70b開源Microsoft | 1,105 | ±6 | 8,385 | — |
| 37 | ▼ 1 | snowflake-arctic-instruct開源Snowflake | 1,103 | ±3 | 34,179 | — |
| 38 | ▼ 1 | openchat-3.5-0106開源OpenChat · 另有 1 個檔位 | 1,101 | ±4 | 12,977 | — |
| 39 | ▼ 1 | yi-34b-chat開源01 AI | 1,100 | ±4 | 15,930 | — |
| 40 | — | phi-3-small-8k-instruct開源Microsoft | 1,098 | ±4 | 18,492 | — |
| 41 | ▼ 2 | gemma-1.1-7b-it開源Google | 1,097 | ±4 | 25,097 | — |
| 42 | — | vicuna-33b開源LMSYS | 1,092 | ±5 | 22,950 | — |
| 43 | ▲ 2 | starling-lm-7b-beta開源Nexusflow | 1,091 | ±4 | 16,672 | — |
| 44 | ▼ 3 | tulu-2-dpo-70b開源AllenAI/UW | 1,091 | ±8 | 6,666 | — |
| 45 | ▲ 1 | llama-3.2-3b-instruct開源Meta | 1,090 | ±7 | 8,620 | — |
| 46 | ▼ 3 | deepseek-llm-67b-chat開源DeepSeek | 1,089 | ±7 | 4,982 | — |
| 47 | ▼ 3 | openhermes-2.5-mistral-7b開源NousResearch | 1,086 | ±9 | 5,093 | — |
| 48 | ▼ 1 | starling-lm-7b-alpha開源UC Berkeley | 1,083 | ±6 | 10,417 | — |
| 49 | ▼ 1 | llama-2-70b-chat開源Meta | 1,081 | ±3 | 39,641 | — |
| 50 | ▼ 1 | llama2-70b-steerlm-chat開源NVIDIA | 1,070 | ±9 | 3,638 | — |
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