Event ·Multi-source

1017 在复杂机械搭建任务中胜过 Opus 5.5

博主 teortaxesTex 发帖称，代号 1017 的模型在一项搭建复杂机械的任务中表现超过 Opus 5.5、Astra 和 Sol。他原本以为前几个模型已经做得不错，对比后认为它们缺乏品味和大胆度。他推测 1017 背后使用了某种蒸馏技术。该评价为个人观察，非基准测试数据。

Current read

一位博主拿 1017 和 Opus 5.5、Astra、Sol 同题对比，结果前者把后者都比下去了，还猜是蒸馏的功劳，可以看看他的具体任务截图。

6 sources33° AI heatLast updated 2026/10/23 14:01:49

Evidence

6 sources

Primary sourceTeortaxes

2026/10/23 14:01:49View source

Related source 1Artificial Analysis

2026/10/22 17:55:37View source

Related source 2Bindu Reddy

2026/10/21 20:30:03View source

Related source 3arXiv cs.AI

2026/10/21 17:11:52View source

Related source 4TestingCatalog

2026/10/21 18:57:16View source

Related source 5SiliconFlowAI

2026/10/23 13:42:34View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story