# 开源与闭源模型差距超乎基准测试显现

- 来源：Ethan Mollick (@emollick)
- 发布时间：2026-05-03 19:43
- AIHOT 分数：51
- AIHOT 链接：https://aihot.virxact.com/items/cmoppmbeo0yassll9riu8c7m6
- 原文链接：https://x.com/emollick/status/2050904152511848871

## AI 摘要

这是一个很好的解释，说明了为什么开源模型和闭源模型之间的差距比基准测试中显示的更大。我想补充一点，当前的开源模型也比闭源模型更脆弱：它们处理分布外问题的能力差得多，并且涌现能力较低。

## 正文

This is a good explanation of why the gap between open and closed models is larger than it appears in benchmarks. I would add in that current open models are also more fragile than closed： they handle out-of-distribution problems far less well &amp； have lower emergent capabilities.

### 引用推文

> Lisan al Gaib：http://x.com/i/article/2050605354501726209