能力坐标

模型不靠声量，
靠坐标说话。

每日读取官方评测，把模型能力拆成综合智能、编程与智能体三条清晰坐标。

更新频率: 每日 00:00
榜单规模: 3 × TOP 20
数据时间: 9月27日 00:15

01综合智能INTELLIGENCE 02编程能力CODING 03智能体能力AGENTIC

当前坐标 / INTELLIGENCE

综合智能指数

综合衡量模型在推理、知识与多项核心任务中的整体能力。

INDEX 4.32026-09-27

名次 / 模型综合智能指数 · HIGHER IS BETTER

01Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic · 2026-09-22
57.6
02Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback)Anthropic · 2026-09-22
56.0
03Claude Opus 5.5 (Adaptive Reasoning, High Effort, Default Fallback)Anthropic · 2026-09-22
53.6
04Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic · 2026-09-01
53.4
05Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)Anthropic · 2026-09-01
53.2
06GPT-6 Astra (max)OpenAI · 2026-09-03
52.7
07GPT-6 Astra (xhigh)OpenAI · 2026-09-03
52.4
08Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)Anthropic · 2026-09-01
51.2
09Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback)Anthropic · 2026-09-22
51.2
10GPT-6 Astra (high)OpenAI · 2026-09-03
50.9
11Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic · 2026-07-24
50.8
12Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)Anthropic · 2026-07-24
49.7
13Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic · 2026-06-09
49.6
14GPT-6 Astra (medium)OpenAI · 2026-09-03
49.6
15Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)Anthropic · 2026-09-01
48.9
16Claude Opus 5 (Adaptive Reasoning, High Effort)Anthropic · 2026-07-24
48.1
17Muse Spark 1.3 (max)Meta · 2026-09-02
48.1
18GPT-6 Sol (max)OpenAI · 2026-09-22
47.5
19GPT-5.6 Sol (max)OpenAI · 2026-07-09
47.0
20Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)Anthropic · 2026-09-01
46.8