模型排行
505 個模型 · 3 個榜單 · 2 個數據來源
智力王座
開源之光
價效比之王
國產之光
開源前三甲
Qwen3 235B A22B 2507 (Reasoning)Alibaba · 總第 8 名63.6
gpt-oss-120BOpenAI · 總第 9 名61.3
DeepSeek R1 0528 (May '25)DeepSeek · 總第 13 名58.7
這一期的變化
Mistral Medium 3.1智力榜 · 第 58新上榜
Gemma 3 4B Instruct智力榜 · 第 132上升 13 位
Gemini 2.5 Flash-Lite (Reasoning)智力榜 · 第 32上升 7 位
GPT-4.1 mini智力榜 · 第 38上升 7 位
GPT-4.1 nano智力榜 · 第 76上升 3 位
| 排名 | 變化 | 模型 | 智力 | 價格 $/M | 速度 tok/s | 首字延遲 |
|---|---|---|---|---|---|---|
| 1 | — | GPT-5 (high)閉源OpenAI | 69.0 | $3.4 | — | — |
| 2 | — | GPT-5 (medium)閉源OpenAI | 67.5 | $3.4 | — | — |
| 3 | — | Grok 4閉源xAI | 67.5 | $6.0 | — | — |
| 4 | — | o3-pro閉源OpenAI | 67.5 | $35 | — | — |
| 5 | — | o3閉源OpenAI | 67.1 | $3.5 | — | — |
| 6 | — | o4-mini (high)閉源OpenAI | 65.1 | $1.9 | — | — |
| 7 | — | Gemini 2.5 Pro閉源Google | 64.6 | $3.4 | — | — |
| 8 | — | GPT-5 mini閉源OpenAI | 63.7 | $0.69 | — | — |
| 9 | — | GPT-5 (low)閉源OpenAI | 63.4 | $3.4 | — | — |
| 10 | ▲ 1 | gpt-oss-120B開源OpenAI | 61.3 | $0.26 | — | — |
| 11 | ▼ 1 | Claude 4.1 Opus (Extended Thinking)閉源Anthropic | 61.0 | $30 | — | — |
| 12 | — | Gemini 2.5 Pro Preview (Mar' 25)閉源Google | 59.0 | $3.4 | — | — |
| 13 | — | Claude 4 Sonnet (Extended Thinking)閉源Anthropic | 58.8 | $6.0 | — | — |
| 14 | — | Gemini 2.5 Flash (Reasoning)閉源Google | 58.4 | $0.85 | — | — |
| 15 | — | Grok 3 mini Reasoning (high)閉源xAI | 58.0 | $0.35 | — | — |
| 16 | — | Gemini 2.5 Pro Preview (May' 25)閉源Google | 58.0 | $3.4 | — | — |
| 17 | — | o3-mini (high)閉源OpenAI | 55.5 | $1.9 | — | — |
| 18 | — | Claude 4 Opus (Extended Thinking)閉源Anthropic | 55.3 | $30 | — | — |
| 19 | — | GPT-5 nano閉源OpenAI | 53.8 | $0.14 | — | — |
| 20 | — | o3-mini閉源OpenAI | 52.7 | $1.9 | — | — |
| 21 | — | Llama Nemotron Super 49B v1.5 (Reasoning)開源NVIDIA | 52.4 | $0.000 | — | — |
| 22 | — | o1閉源OpenAI | 51.7 | $26 | — | — |
| 23 | — | Sonar Reasoning Pro閉源Perplexity | 50.7 | $0.000 | — | — |
| 24 | — | Gemini 2.5 Flash Preview (Reasoning)閉源Google | 50.2 | $0.99 | — | — |
| 25 | — | o1-preview閉源OpenAI | 49.3 | $29 | — | — |
| 26 | — | gpt-oss-20B開源OpenAI | 49.0 | $0.088 | — | — |
| 27 | — | Claude 4.1 Opus閉源Anthropic | 49.0 | $30 | — | — |
| 28 | — | Gemini 2.5 Flash閉源Google | 47.3 | $0.85 | — | — |
| 29 | ▲ 7 | Gemini 2.5 Flash-Lite (Reasoning)閉源Google | 47.3 | $0.18 | — | — |
| 30 | ▼ 1 | Claude 3.7 Sonnet (Extended Thinking)閉源Anthropic | 47.0 | $6.0 | — | — |
| 31 | ▼ 1 | GPT-4.1閉源OpenAI | 46.8 | $3.5 | — | — |
| 32 | ▼ 1 | Claude 4 Opus閉源Anthropic | 46.6 | $30 | — | — |
| 33 | ▼ 1 | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)開源NVIDIA | 46.4 | $0.90 | — | — |
| 34 | ▼ 1 | Claude 4 Sonnet閉源Anthropic | 45.7 | $6.0 | — | — |
| 35 | ▼ 1 | Grok 3 Reasoning Beta閉源xAI | 45.6 | $0.000 | — | — |
| 35 | ▼ 1 | o1-pro閉源OpenAI | 45.6 | $263 | — | — |
| 37 | ▲ 3 | GPT-4.1 mini閉源OpenAI | 45.6 | $0.70 | — | — |
| 38 | ▼ 1 | GPT-5 (minimal)閉源OpenAI | 43.8 | $3.4 | — | — |
| 39 | ▼ 1 | o1-mini閉源OpenAI | 43.3 | $1.9 | — | — |
| 40 | ▼ 1 | GPT-4.5 (Preview)閉源OpenAI | 42.4 | $0.000 | — | — |
| 41 | — | Llama 4 Maverick開源Meta | 41.7 | $0.39 | — | — |
| 42 | — | Gemini 2.0 Flash Thinking Experimental (Jan '25)閉源Google | 41.7 | $0.000 | — | — |
| 43 | — | Llama 3.3 Nemotron Super 49B v1 (Reasoning)開源NVIDIA | 40.5 | $0.000 | — | — |
| 44 | — | Grok 3閉源xAI | 39.9 | $6.0 | — | — |
| 45 | — | GPT-4o (March 2025, chatgpt-4o-latest)閉源OpenAI | 39.5 | $7.5 | — | — |
| 46 | — | Gemini 2.0 Pro Experimental (Feb '25)閉源Google | 38.4 | $0.000 | — | — |
| 47 | — | Sonar Reasoning閉源Perplexity | 38.0 | $2.0 | — | — |
| 48 | — | Gemini 2.5 Flash Preview閉源Google | 38.0 | $0.26 | — | — |
| 49 | — | Gemini 2.0 Flash (Feb '25)閉源Google | 37.8 | $0.18 | — | — |
| 50 | — | Claude 3.7 Sonnet (Standard)閉源Anthropic | 37.3 | $6.0 | — | — |
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