第 1 名
Claude Opus 5 (Adaptive Reasoning, Max Effort)
Anthropic
能力得分
60.7
54 tok/s
输出速度
全部天梯10 / 50 48 个模型
当前数据AIUtil 能力天梯
模型综合智能天梯
衡量复杂推理、专业知识与真实任务中的综合表现。
本次数据
收录 50 个模型
当前第一
Claude Opus 5 (Adaptive Reasoning, Max Effort)
最高分
60.7
入榜数量
50
最近发布
2026/08/05
前三名
领先梯队
分数越高，排名越靠前
第 2 名
Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
Anthropic
能力得分
60.1
55 tok/s
输出速度
第 3 名
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)
Anthropic
能力得分
59.9
72 tok/s
输出速度
分数对比
前十名能力差距
- 01Claude Opus 5 (Adaptive Reasoning, Max Effort)60.7
- 02Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)60.1
- 03Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)59.9
- 04Claude Opus 5 (Adaptive Reasoning, High Effort)58.9
- 05GPT-5.6 Sol (max)58.9
- 06GPT-5.6 Sol (xhigh)57.7
- 07Kimi K3 (max)57.1
- 08Claude Opus 5 (Adaptive Reasoning, Medium Effort)56.3
- 09GPT-5.6 Sol (high)55.9
- 10Claude Opus 4.8 (Adaptive Reasoning, Max Effort)55.7
020406080Artificial Analysis Intelligence Index
价格对比
能力与输出价格
越靠近左上角，代表更高能力与更低输出价格。
每百万输出 Token 价格（美元，对数轴）Artificial Analysis Intelligence Index
62.957.251.545.740.0$0.28$1.02$3.74$14$50
Claude Opus 5 (Adaptive Reasoning, Max Effort)
Anthropic
能力分60.7输出价格$25 / 1M
54 tok/s全部结果
完整排名
Artificial Analysis Intelligence Index
| 排名 | 模型 | 厂商 | Artificial Analysis Intelligence Index | 输出速度 | 发布日期 |
|---|---|---|---|---|---|
| #01 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic | 60.7 | 54 tok/s | |
| #02 | Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | Anthropic | 60.1 | 55 tok/s | |
| #03 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Anthropic | 59.9 | 72 tok/s | |
| #04 | Claude Opus 5 (Adaptive Reasoning, High Effort) | Anthropic | 58.9 | 53 tok/s | |
| #05 | GPT-5.6 Sol (max) | OpenAI | 58.9 | 64 tok/s | |
| #06 | GPT-5.6 Sol (xhigh) | OpenAI | 57.7 | 63 tok/s | |
| #07 | Kimi K3 (max) | Kimi | 57.1 | 38 tok/s | |
| #08 | Claude Opus 5 (Adaptive Reasoning, Medium Effort) | Anthropic | 56.3 | 54 tok/s | |
| #09 | GPT-5.6 Sol (high) | OpenAI | 55.9 | 61 tok/s | |
| #10 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | Anthropic | 55.7 | 58 tok/s | |
| #11 | GPT-5.6 Terra (max) | OpenAI | 55.0 | 125 tok/s | |
| #12 | GPT-5.5 (xhigh) | OpenAI | 54.8 | 76 tok/s | |
| #13 | Muse Spark 1.2 (xhigh) | Meta | 54.1 | 0 tok/s | |
| #14 | Grok 4.5 (high) | SpaceXAI | 53.8 | 59 tok/s | |
| #15 | GPT-5.6 Sol (medium) | OpenAI | 53.6 | 58 tok/s | |
| #16 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | Anthropic | 53.5 | 51 tok/s | |
| #17 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | Anthropic | 53.4 | 70 tok/s | |
| #18 | GPT-5.5 (high) | OpenAI | 53.1 | 72 tok/s | |
| #19 | GPT-5.6 Terra (xhigh) | OpenAI | 51.6 | 116 tok/s | |
| #20 | GPT-5.4 (xhigh) | OpenAI | 51.4 | 125 tok/s | |
| #21 | GPT-5.6 Luna (max) | OpenAI | 51.2 | 178 tok/s | |
| #22 | GLM-5.2 (max) | Z AI | 51.1 | 150 tok/s | |
| #23 | Claude Opus 5 (Adaptive Reasoning, Low Effort) | Anthropic | 50.6 | 52 tok/s | |
| #24 | Muse Spark 1.1 (xhigh) | Meta | 50.6 | 213 tok/s | |
| #25 | GPT-5.5 (medium) | OpenAI | 50.4 | 69 tok/s | |
| #26 | Gemini 3.5 Flash (high) | 50.2 | 168 tok/s | ||
| #27 | Gemini 3.6 Flash (high) | 50.1 | 188 tok/s | ||
| #28 | DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | DeepSeek | 49.9 | 103 tok/s | |
| #29 | GPT-5.6 Sol (low) | OpenAI | 49.4 | 61 tok/s | |
| #30 | GPT-5.6 Luna (xhigh) | OpenAI | 49.1 | 164 tok/s | |
| #31 | GPT-5.6 Terra (high) | OpenAI | 49.0 | 109 tok/s | |
| #32 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 47.2 | 58 tok/s | |
| #33 | Kimi K3 (low) | Kimi | 46.6 | 38 tok/s | |
| #34 | Gemini 3.1 Pro Preview | 46.5 | 126 tok/s | ||
| #35 | GPT-5.6 Luna (high) | OpenAI | 46.1 | 163 tok/s | |
| #36 | Qwen3.7 Max | Alibaba | 46.0 | 202 tok/s | |
| #37 | GPT-5.6 Terra (medium) | OpenAI | 45.6 | 112 tok/s | |
| #38 | Gemini 3.5 Flash (medium) | 45.4 | 177 tok/s | ||
| #39 | MiniMax-M3 | MiniMax | 44.4 | 82 tok/s | |
| #40 | DeepSeek V4 Pro (Reasoning, Max Effort) | DeepSeek | 44.3 | 63 tok/s | |
| #41 | GPT-5.3 Codex (xhigh) | OpenAI | 44.3 | 117 tok/s | |
| #42 | Kimi K2.6 | Kimi | 44.2 | 39 tok/s | |
| #43 | Motif 3 (Beta) | Motif Technologies | 44.1 | 0 tok/s | |
| #44 | Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | Anthropic | 43.7 | 44 tok/s | |
| #45 | GPT-5.5 (low) | OpenAI | 43.5 | 69 tok/s | |
| #46 | DeepSeek V4 Pro (Reasoning, High Effort) | DeepSeek | 43.1 | 64 tok/s | |
| #47 | Muse Spark | Meta | 43.1 | 0 tok/s | |
| #48 | Claude Opus 4.7 (Non-reasoning, High Effort) | Anthropic | 42.7 | 46 tok/s | |
| #49 | GPT-5.2 (xhigh) | OpenAI | 42.2 | 75 tok/s | |
| #50 | MiMo-V2.5-Pro | Xiaomi | 42.2 | 68 tok/s |