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
当前坐标 / CODING
编程能力指数
聚焦代码生成、问题解决与真实软件工程任务表现。
2026-09-27
- 01Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic · 2026-09-0181.6
- 02Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)Anthropic · 2026-09-0180.7
- 03Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)Anthropic · 2026-09-0179.1
- 04GPT-5.6 Sol (xhigh)OpenAI · 2026-07-0978.3
- 05Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic · 2026-07-2478.0
- 06GPT-5.6 Sol (max)OpenAI · 2026-07-0977.4
- 07GPT-5.6 Sol (high)OpenAI · 2026-07-0977.2
- 08Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)Anthropic · 2026-09-0177.1
- 09GPT-6 Astra (high)OpenAI · 2026-09-0377.1
- 10Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)Anthropic · 2026-07-2477.0
- 11GPT-6 Astra (max)OpenAI · 2026-09-0376.9
- 12Grok 4.6 (high)SpaceXAI · 2026-08-1276.8
- 13GPT-5.6 Terra (max)OpenAI · 2026-07-0976.7
- 14GPT-6 Astra (medium)OpenAI · 2026-09-0376.7
- 15Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic · 2026-06-0976.5
- 16Claude Opus 5 (Adaptive Reasoning, High Effort)Anthropic · 2026-07-2476.5
- 17Muse Spark 1.3 (xhigh)Meta · 2026-09-0276.5
- 18Gemini 3.8 Flash (high)Google · 2026-09-0276.3
- 19GPT-5.6 Sol (medium)OpenAI · 2026-07-0976.3
- 20Kimi K3 (max)Kimi · 2026-07-1676.2