比较和追踪最新 AI 模型性能排名
AI 排行榜
构建时从 Artificial Analysis 获取的模型评估和定价快照。
#1 Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) · 智能 59.9
来源：artificialanalysis.ai
| 排名 | 模型 | 创建者 | 智能 | 编程 | 数学 | 混合 $/1M | Tok/s | TTFT (秒) |
|---|---|---|---|---|---|---|---|---|
1最佳 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) claude-fable-5 | Anthropic | 59.9 | 76.5 | — | $20 | 62.5 | 66.11 |
2 | GPT-5.6 Sol (max) gpt-5-6-sol | OpenAI | 58.9 | 77.4 | — | $11.25 | 65.7 | 87.54 |
3 | GPT-5.6 Sol (xhigh) gpt-5-6-sol-xhigh | OpenAI | 57.7 | 78.3 | — | $11.25 | 59.3 | 30.82 |
4新 | Kimi K3 kimi-k3 | Kimi | 57.1 | 76.2 | — | $6 | 58.5 | 1.35 |
5 | GPT-5.6 Sol (high) gpt-5-6-sol-high | OpenAI | 55.9 | 77.2 | — | $11.25 | 53.3 | 9.93 |
6 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) claude-opus-4-8 | Anthropic | 55.7 | 74.3 | — | $10 | 55 | 23.67 |
7 | GPT-5.6 Terra (max) gpt-5-6-terra | OpenAI | 55 | 76.7 | — | $5.625 | 137.9 | 154.48 |
8 | GPT-5.5 (xhigh) gpt-5-5 | OpenAI | 54.8 | 74.9 | — | $11.25 | 70.1 | 27.3 |
9 | Grok 4.5 (high) grok-4-5 | SpaceXAI | 53.8 | 72.4 | — | $3 | 119.1 | 12.24 |
10 | GPT-5.6 Sol (medium) gpt-5-6-sol-medium | OpenAI | 53.6 | 76.3 | — | $11.25 | 54.4 | 3.95 |
11 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort) claude-opus-4-7 | Anthropic | 53.5 | 73.6 | — | $10 | 49.4 | 22.95 |
12 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) claude-sonnet-5 | Anthropic | 53.4 | 71.5 | — | $4 | 78.2 | 126.94 |
13 | GPT-5.5 (high) gpt-5-5-high | OpenAI | 53.1 | 71.6 | — | $11.25 | 64.4 | 13.08 |
14 | GPT-5.6 Terra (xhigh) gpt-5-6-terra-xhigh | OpenAI | 51.6 | 70.6 | — | $5.625 | 123.8 | 6.87 |
15 | GPT-5.4 (xhigh) gpt-5-4 | OpenAI | 51.4 | 71.1 | — | $5.625 | 151.7 | 120.83 |
16 | GPT-5.6 Luna (max) gpt-5-6-luna | OpenAI | 51.2 | 71.4 | — | $2.25 | 180.3 | 72.48 |
17 | GLM-5.2 (max) glm-5-2 | Z AI | 51.1 | 68.8 | — | $2.15 | 164.5 | 0.94 |
18 | Muse Spark 1.1 (xhigh) muse-spark-1-1 | Meta | 50.6 | 71.3 | — | $2 | 112.8 | 0.85 |
19 | GPT-5.5 (medium) gpt-5-5-medium | OpenAI | 50.4 | 71.5 | — | $11.25 | 62.8 | 5.15 |
20 | Gemini 3.5 Flash (high) gemini-3-5-flash | 50.2 | 70.1 | — | $3.375 | 236.9 | 12.15 | |
21 | GPT-5.6 Sol (low) gpt-5-6-sol-low | OpenAI | 49.4 | 69.7 | — | $11.25 | 56.8 | 3.8 |
22 | GPT-5.6 Luna (xhigh) gpt-5-6-luna-xhigh | OpenAI | 49.1 | 68.6 | — | $2.25 | 174.3 | 22.83 |
23 | GPT-5.6 Terra (high) gpt-5-6-terra-high | OpenAI | 49 | 67.1 | — | $5.625 | 111.3 | 2.62 |
24 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) claude-sonnet-4-6-adaptive | Anthropic | 47.2 | 63 | — | $6 | 64 | 59.34 |
25 | Gemini 3.1 Pro Preview gemini-3-1-pro-preview | 46.5 | 68.8 | — | $4.5 | 128.6 | 22.54 |
按Artificial Analysis 智能指数排序。
显示 25 个模型。