模型排行
443 个模型 · 2 个榜单 · 2 个数据来源
智力王座
开源之光
性价比之王
国产之光
开源前三甲
DeepSeek R1 0528 (May '25)DeepSeek · 总第 7 名68.3
MiniMax M1 80kMiniMax · 总第 12 名63.0
Qwen3 235B A22B (Reasoning)Alibaba · 总第 14 名62.3
| 排名 | 变化 | 模型 | 智力 | 价格 $/M | 速度 tok/s | 首字延迟 |
|---|---|---|---|---|---|---|
| 1 | — | Grok 4闭源xAI | 73.2 | $6.0 | — | — |
| 2 | — | o3-pro闭源OpenAI | 71.0 | $35 | — | — |
| 3 | — | Gemini 2.5 Pro闭源Google | 70.5 | $3.4 | — | — |
| 4 | — | o3闭源OpenAI | 70.0 | $3.5 | — | — |
| 5 | — | o4-mini (high)闭源OpenAI | 69.8 | $1.9 | — | — |
| 6 | — | Gemini 2.5 Pro Preview (Mar' 25)闭源Google | 68.9 | $3.4 | — | — |
| 7 | — | Gemini 2.5 Pro Preview (May' 25)闭源Google | 67.9 | $3.4 | — | — |
| 8 | — | Grok 3 mini Reasoning (high)闭源xAI | 66.7 | $0.35 | — | — |
| 9 | — | o3-mini (high)闭源OpenAI | 65.5 | $1.9 | — | — |
| 10 | — | Gemini 2.5 Flash (Reasoning)闭源Google | 65.1 | $0.99 | — | — |
| 11 | — | Claude 4 Opus (Extended Thinking)闭源Anthropic | 64.4 | $30 | — | — |
| 12 | — | o3-mini闭源OpenAI | 62.9 | $1.9 | — | — |
| 13 | ▲ 2 | Claude 4 Sonnet (Extended Thinking)闭源Anthropic | 62.8 | $6.0 | — | — |
| 14 | ▼ 1 | o1闭源OpenAI | 61.9 | $26 | — | — |
| 15 | ▼ 1 | Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)开源NVIDIA | 60.8 | $0.90 | — | — |
| 16 | — | Gemini 2.5 Flash Preview (Reasoning)闭源Google | 60.5 | $0.99 | — | — |
| 17 | — | o1-preview闭源OpenAI | 59.6 | $26 | — | — |
| 18 | — | Claude 4 Opus闭源Anthropic | 57.7 | $30 | — | — |
| 19 | — | Claude 3.7 Sonnet (Extended Thinking)闭源Anthropic | 57.4 | $6.0 | — | — |
| 20 | — | Grok 3 Reasoning Beta闭源xAI | 56.1 | $0.000 | — | — |
| 20 | — | o1-pro闭源OpenAI | 56.1 | $263 | — | — |
| 22 | — | Gemini 2.5 Flash-Lite (Reasoning)闭源Google | 54.9 | $0.18 | — | — |
| 23 | — | o1-mini闭源OpenAI | 53.8 | $1.9 | — | — |
| 24 | — | Gemini 2.5 Flash闭源Google | 53.4 | $0.26 | — | — |
| 25 | — | Claude 4 Sonnet闭源Anthropic | 53.0 | $6.0 | — | — |
| 25 | — | GPT-4.5 (Preview)闭源OpenAI | 53.0 | $0.000 | — | — |
| 27 | — | GPT-4.1 mini闭源OpenAI | 52.9 | $0.70 | — | — |
| 28 | — | GPT-4.1闭源OpenAI | 52.6 | $3.5 | — | — |
| 29 | — | Gemini 2.0 Flash Thinking Experimental (Jan '25)闭源Google | 52.3 | $0.000 | — | — |
| 30 | — | Llama 3.3 Nemotron Super 49B v1 (Reasoning)开源NVIDIA | 51.2 | $0.000 | — | — |
| 31 | — | Grok 3闭源xAI | 50.6 | $6.0 | — | — |
| 32 | — | Llama 4 Maverick开源Meta | 50.5 | $0.38 | — | — |
| 33 | — | GPT-4o (March 2025, chatgpt-4o-latest)闭源OpenAI | 50.3 | $7.5 | — | — |
| 34 | — | Gemini 2.0 Pro Experimental (Feb '25)闭源Google | 49.2 | $0.000 | — | — |
| 35 | — | Sonar Reasoning闭源Perplexity | 48.8 | $2.0 | — | — |
| 36 | — | Gemini 2.5 Flash Preview闭源Google | 48.8 | $0.26 | — | — |
| 37 | — | Claude 3.7 Sonnet (Standard)闭源Anthropic | 48.2 | $6.0 | — | — |
| 38 | — | Gemini 2.0 Flash (Feb '25)闭源Google | 48.1 | $0.18 | — | — |
| 39 | — | Gemini 2.0 Flash (experimental)闭源Google | 46.4 | $0.000 | — | — |
| 40 | — | Gemini 2.5 Flash-Lite闭源Google | 45.6 | $0.18 | — | — |
| 41 | — | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)开源NVIDIA | 45.0 | $0.000 | — | — |
| 42 | — | Gemini 1.5 Pro (Sep '24)闭源Google | 44.6 | $2.2 | — | — |
| 43 | — | Claude 3.5 Sonnet (Oct '24)闭源Anthropic | 44.4 | $6.0 | — | — |
| 44 | — | Sonar闭源Perplexity | 43.4 | $1.0 | — | — |
| 45 | — | Llama 4 Scout开源Meta | 43.0 | $0.24 | — | — |
| 46 | — | Sonar Pro闭源Perplexity | 42.7 | $6.0 | — | — |
| 47 | — | Nova Premier闭源Amazon | 42.6 | $5.0 | — | — |
| 48 | — | GPT-4o (Nov '24)闭源OpenAI | 41.5 | $4.4 | — | — |
| 49 | — | Gemini 2.0 Flash-Lite (Feb '25)闭源Google | 41.4 | $0.13 | — | — |
| 50 | — | Llama 3.3 Instruct 70B开源Meta | 41.1 | $0.62 | — | — |
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