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 Opus 5 (Adaptive Reasoning, Max Effort) · 智能 63.1
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 Opus 5 (Adaptive Reasoning, Max Effort) claude-opus-5 | Anthropic | 63.1 | 78 | — | $10 | 53.8 | 34.57 |
2 | Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) claude-opus-5-xhigh | Anthropic | 62.5 | 77 | — | $10 | 54.3 | 18.21 |
3 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) claude-fable-5 | Anthropic | 62.1 | 76.5 | — | $20 | 62.4 | 54.13 |
4 | Claude Opus 5 (Adaptive Reasoning, High Effort) claude-opus-5-high | Anthropic | 61.5 | 76.5 | — | $10 | 53 | 11.33 |
5 | GPT-5.6 Sol (max) gpt-5-6-sol | OpenAI | 60.9 | 77.4 | — | $8 | 84.2 | 50.56 |
6 | Grok 4.6 (high) grok-4-6 | SpaceXAI | 60.9 | 76.8 | — | $3 | 57.6 | 36.59 |
7 | Grok 4.6 (xhigh) grok-4-6-xhigh | SpaceXAI | 60 | 75.9 | — | $3 | 60.4 | 38.68 |
8 | Kimi K3 (max) kimi-k3 | Kimi | 59.7 | 76.2 | — | $6 | 36.4 | 3.56 |
9 | GLM-5.3 (max) glm-5-3 | Z AI | 59.5 | 74.8 | — | $2.15 | 75.2 | 1.61 |
10 | GPT-5.6 Sol (xhigh) gpt-5-6-sol-xhigh | OpenAI | 59 | 78.3 | — | $8 | 81.7 | 23.49 |
11 | Grok 4.6 (medium) grok-4-6-medium | SpaceXAI | 59 | 74.4 | — | $3 | 56.8 | 31.7 |
12 | Claude Opus 5 (Adaptive Reasoning, Medium Effort) claude-opus-5-medium | Anthropic | 58.6 | 74.3 | — | $10 | 51 | 8.65 |
13 | Qwen3.8 Max qwen3-8-max | Alibaba | 58.1 | 71.8 | — | $3 | 29.9 | 1.76 |
14 | Qwen3.8 2.4T A95B qwen3-8-2-4t-a95b | Alibaba | 57.7 | 71.9 | — | $3 | 31.4 | 1.91 |
15新 | GLM-5.3-Flash glm-5-3-flash | Z AI | 57.5 | 71.5 | — | $0.237 | 50.1 | 1.11 |
16 | GPT-5.6 Sol (high) gpt-5-6-sol-high | OpenAI | 57.3 | 77.2 | — | $8 | 77.6 | 14.11 |
17 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) claude-opus-4-8 | Anthropic | 57.3 | 74.3 | — | $10 | 0 | 0 |
18 | Muse Spark 1.2 (xhigh) muse-spark-1-2 | Meta | 56.8 | 72.2 | — | $2 | 0 | 0 |
19 | GPT-5.6 Terra (max) gpt-5-6-terra | OpenAI | 56.6 | 76.7 | — | $4.5 | 110 | 119.68 |
20 | GPT-5.5 (xhigh) gpt-5-5 | OpenAI | 56.3 | 74.9 | — | $11.25 | 0 | 0 |
21 | Gemini 3.7 Flash (high) gemini-3-7-flash | 56 | 76.1 | — | $1.5 | 345.2 | 7.57 | |
22新 | Qwen3.8-Flash-Next qwen3-8-flash-next | Alibaba | 55.8 | 73.1 | — | $0.23 | 82.9 | 1.22 |
23 | Grok 4.5 (high) grok-4-5 | SpaceXAI | 55.8 | 72.4 | — | $3 | 53.8 | 13.12 |
24 | GPT-5.6 Sol (medium) gpt-5-6-sol-medium | OpenAI | 55.6 | 76.3 | — | $8 | 78.2 | 5.35 |
25 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) claude-sonnet-5 | Anthropic | 55.3 | 71.5 | — | $4 | 91.4 | 121.77 |
按Artificial Analysis 智能指数排序。
显示 25 个模型。