Skip to content
AX AI Daily
中EN
Trending storyDeveloping

Village benchmark: closed models now lead the price-performance frontier

1 report1 sourceupdated 3 hours ago

What happened

AI digest

Village's LLM Atlas benchmark shows open-weight models' share of the best price-performance frontier fell from 41% in June to 3%, per a Hacker News front-page report on November 6. Closed models now hold the price-performance frontier at nearly every budget level. GPT-6 Luna, GPT-6.1 Terra and Claude Haiku 5.5 cover the budget ranges where open models previously led; open models now hold an advantage mainly at the lowest price tier.

Written by AI from the coverage · updated 2 hours ago

LatestNov 6 10:49
Village's benchmark puts open-weight models' best-frontier share at 3%, with closed models leading nearly every budget tier.

Coverage

Follow the reports to see the story from different sides.

Nov 6
  1. Hacker News front page
    Closed AI models dominate the price-performance frontier

    Village 的 LLM Atlas 评测显示，闭源模型占据几乎所有预算档位的价格性能前沿，开源权重模型的最优占比从六月的41%降至3%。GPT-6 Luna、GPT-6.1 Terra 和 Claude Haiku 5.5 覆盖了开源模型此前领先的预算区间，开源模型目前主要在最低价区间占优。

Heat over time

Not enough continuous observations to draw a trend yet.