模型排行
262 个模型 · 2 个榜单 · 2 个数据来源
开源前三甲
DeepSeek R1DeepSeek · 总第 3 名60.2
DeepSeek R1 Distill Qwen 32BDeepSeek · 总第 6 名51.0
DeepSeek R1 Distill Qwen 14BDeepSeek · 总第 8 名49.0
这一期的变化
Claude 3.7 Sonnet (Extended Thinking)智力榜 · 第 4新上榜
Qwen2 Instruct 72B智力榜 · 第 39新上榜
Claude 3 Sonnet智力榜 · 第 45新上榜
Qwen2.5 Coder Instruct 7B智力榜 · 第 51新上榜
Claude 2.1智力榜 · 第 53新上榜
| 排名 | 变化 | 模型 | 智力 | 价格 $/M | 速度 tok/s | 首字延迟 |
|---|---|---|---|---|---|---|
| 1 | 新 | o3-mini (high)闭源OpenAI | 65.5 | — | — | — |
| 2 | ▼ 1 | o3-mini闭源OpenAI | 62.9 | — | — | — |
| 3 | ▼ 1 | o1闭源OpenAI | 61.9 | — | — | — |
| 4 | ▼ 1 | DeepSeek R1开源DeepSeek | 60.2 | — | — | — |
| 5 | 新 | Claude 3.7 Sonnet (Extended Thinking)闭源Anthropic | 57.4 | — | — | — |
| 6 | ▼ 2 | o1-mini闭源OpenAI | 53.8 | — | — | — |
| 7 | ▲ 3 | DeepSeek R1 Distill Qwen 32B开源DeepSeek | 51.0 | — | — | — |
| 8 | ▼ 2 | Gemini 2.0 Pro Experimental (Feb '25)闭源Google | 49.2 | — | — | — |
| 9 | ▼ 4 | DeepSeek R1 Distill Qwen 14B开源DeepSeek | 49.0 | — | — | — |
| 10 | ▲ 3 | DeepSeek R1 Distill Llama 70B开源DeepSeek | 48.2 | — | — | — |
| 11 | 新 | Claude 3.7 Sonnet (Standard)闭源Anthropic | 48.2 | — | — | — |
| 12 | ▼ 5 | Gemini 2.0 Flash (Feb '25)闭源Google | 48.1 | — | — | — |
| 13 | ▼ 5 | DeepSeek V3开源DeepSeek | 45.7 | — | — | — |
| 14 | ▼ 5 | Qwen2.5 Max闭源Alibaba | 45.3 | — | — | — |
| 15 | ▼ 4 | Gemini 1.5 Pro (Sep '24)闭源Google | 44.6 | — | — | — |
| 16 | ▼ 4 | Claude 3.5 Sonnet (Oct '24)闭源Anthropic | 44.3 | — | — | — |
| 17 | ▼ 3 | QwQ 32B-Preview开源Alibaba | 42.6 | — | — | — |
| 18 | ▼ 3 | Gemini 2.0 Flash-Lite (Preview)闭源Google | 41.9 | — | — | — |
| 19 | ▼ 3 | GPT-4o (Nov '24)闭源OpenAI | 41.5 | — | — | — |
| 20 | ▼ 3 | Llama 3.3 Instruct 70B开源Meta | 41.1 | — | — | — |
| 21 | ▼ 3 | GPT-4o (ChatGPT)闭源OpenAI | 41.1 | — | — | — |
| 22 | ▼ 3 | GPT-4o (Aug '24)闭源OpenAI | 40.9 | — | — | — |
| 23 | ▼ 3 | GPT-4o (May '24)闭源OpenAI | 40.9 | — | — | — |
| 24 | ▼ 3 | Llama 3.1 Instruct 405B开源Meta | 40.5 | — | — | — |
| 25 | ▼ 3 | Qwen2.5 Instruct 72B开源Alibaba | 40.3 | — | — | — |
| 26 | ▼ 3 | Phi-4开源Microsoft Azure | 40.2 | — | — | — |
| 27 | ▼ 3 | Llama 3.1 Tulu3 405B开源Allen Institute for AI | 39.9 | — | — | — |
| 28 | ▼ 3 | MiniMax-Text-01开源MiniMax | 39.9 | — | — | — |
| 29 | ▼ 3 | Mistral Large 2 (Nov '24)开源Mistral | 38.3 | — | — | — |
| 30 | ▼ 3 | Grok Beta闭源xAI | 37.5 | — | — | — |
| 31 | ▼ 3 | Pixtral Large开源Mistral | 37.4 | — | — | — |
| 32 | ▼ 3 | Qwen2.5 Instruct 32B开源Alibaba | 37.4 | — | — | — |
| 33 | ▼ 3 | Llama 3.1 Nemotron Instruct 70B开源NVIDIA | 37.3 | — | — | — |
| 34 | ▼ 3 | Nova Pro闭源Amazon | 37.1 | — | — | — |
| 35 | ▼ 3 | Mistral Large 2 (Jul '24)开源Mistral | 36.6 | — | — | — |
| 36 | ▼ 3 | Qwen2.5 Coder Instruct 32B开源Alibaba | 36.3 | — | — | — |
| 37 | ▼ 3 | GPT-4o mini闭源OpenAI | 35.7 | — | — | — |
| 38 | ▼ 2 | Llama 3.1 Instruct 70B开源Meta | 35.4 | — | — | — |
| 39 | ▼ 2 | Mistral Small 3开源Mistral | 35.3 | — | — | — |
| 40 | ▼ 2 | Claude 3 Opus闭源Anthropic | 35.1 | — | — | — |
| 41 | ▼ 2 | Claude 3.5 Haiku闭源Anthropic | 34.6 | — | — | — |
| 42 | ▼ 7 | DeepSeek R1 Distill Llama 8B开源DeepSeek | 34.0 | — | — | — |
| 43 | ▼ 3 | Gemini 1.5 Pro (May '24)闭源Google | 33.7 | — | — | — |
| 44 | ▼ 3 | Qwen Turbo闭源Alibaba | 33.6 | — | — | — |
| 45 | ▼ 3 | Llama 3.2 Instruct 90B (Vision)开源Meta | 33.4 | — | — | — |
| 46 | 新 | Qwen2 Instruct 72B开源Alibaba | 32.6 | — | — | — |
| 47 | ▼ 4 | Mistral Saba闭源Mistral | 32.2 | — | — | — |
| 48 | ▼ 4 | Jamba 1.5 Large开源AI21 Labs | 29.3 | — | — | — |
| 49 | ▼ 4 | Gemini 1.5 Flash (May '24)闭源Google | 28.4 | — | — | — |
| 50 | ▼ 4 | Nova Micro闭源Amazon | 28.3 | — | — | — |
智力进步
涨得最多 · Anthropic +57.2目前最高 · Anthropic 64.6最高与最低相差 18.1 分时间范围 2025年11月 – 2026年11月
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi