Skip to content
Trending storyWatching

Two anonymous models outrank Fable 5.2 on a design leaderboard

1 report1 sourceupdated yesterday

What happened

AI digest

On November 19, the Hacker News front page reported that two anonymous models appeared on Contra Labs' Frontier Design Benchmark, both with Elo rankings above Claude Fable 5.2. The benchmark is built on 33 real client design briefs, with 68 professional designers casting 4,311 blind votes, and comes with a design review rubric covering 35 scoring dimensions. The report says rubric scores correlate with designer ratings at r = 0.94. The identities of the two models were not disclosed in the report.

Written by AI from the coverage · updated yesterday

Coverage

Follow the reports to see the story from different sides.

Nov 19
  1. Hacker News front page
    Two stealth models just appeared on the leaderboard, both ahead of Fable 5.2

    Contra Labs 的 Frontier Design Benchmark 榜单上出现两个匿名模型,Elo 排名均超过 Claude Fable 5.2。该基准基于 33 个真实客户设计需求、68 位专业设计师的 4,311 次盲评投票,并配有 35 个评分维度的设计评审量表,量表分数与设计师评分相关性达 r = 0.94。

Heat over time

Heat now 5·Comparable peak 9(Nov 19 22:00)·Comparable change over 24 hours -49%

02.557.510Nov 1922:00Nov 2006:00Nov 2015:00Nov 2023:00

The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.