Event ·Single source

Noam Brown 回顾：GSM8K 曾是两年半前实验室比拼的前沿基准

Noam Brown 在 X 上发帖回顾，2.5 年前 AI 实验室还会用小学数学基准 GSM8K 展示自家前沿 LLM 的成绩。如今 GSM8K 早已饱和，不再是衡量前沿能力的指标。他借此感叹两年半时间里模型能力的跃迁速度。

Current read

Noam Brown 发了条短推，说两年半前大家还在卷 GSM8K 小学数学基准，现在早就没人提了，可读一下感受下节奏。

2 sources33° AI heatLast updated 2026/10/27 01:06:15

Evidence

2 sources

Primary sourceNoam Brown (OpenAI 推理)

2026/10/27 01:06:15View source

Related source 1arXiv cs.LG

2026/10/26 17:35:58View 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