Skip to content
Hot eventLive

CLM-v0.1-8B 公开裁判基准接近随机

1 reports1 sources3 hr ago updated

Get the story

AI overview

2026-10-07，arXiv·Machine Learning Theory 发布一手评测《CLM-as-a-Judge：在公开 Judge 基准上评测开源对比决策模型》。报道指出，开源对比决策模型 Contrastive-LM/CLM-v0.1-8B 在公开评测基准上作为评判接近随机水平：best-of-four 得分 0.351，随机基线为 0.250。该报道为目前唯一来源，未见更早或相互矛盾的数据。

Generated from reports · updated 3 hr ago

LatestOct 7
arXiv 评测称 CLM-v0.1-8B best-of-four 得 0.351，随机基线 0.250。

Timeline

Follow the coverage from different angles.

Oct 7, 2026
  1. arXiv · Machine Learning Theory
    CLM-as-a-Judge：在公开 Judge 基准上评测开源对比决策模型

    开源对比决策模型 Contrastive-LM/CLM-v0.1-8B 在公开评测基准上作为评判接近随机：best-of-four 得分 0.351（随机 0.250）。

Heat trend

Current heat 9·Comparable peak 10（Oct 7）·Comparable change over 24 hours –

02.557.510Oct7Oct7Oct7Oct7

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.