Full downstream results after standard 4-stage post-training pipeline (SFT, DPO, RLVR1, RLVR2) for 13B Switch Distillation post-training performance.

Full downstream results after standard 4-stage post-training pipeline (SFT, DPO, RLVR1, RLVR2) for 13B Switch Distillation post-training performance. · CiteArk

测量结果

已评估 0/16 项

获得支持 0有争议或冲突 0尚未评估 16

保留同一结论下的完整结果组。已有评估排在前面；单项判断不替代整组结论。展开行查看条件、来源与历次证据。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
论文报告	最近可用实测	证据判断
77.8 percentage_points	—	尚未评估
62.8 percentage_points	—	尚未评估
51.8 percentage_points	—	尚未评估
33.3 percentage_points	—	尚未评估
42.8 percentage_points	—	尚未评估
19.6 percentage_points	—	尚未评估
54.2 percentage_points	—	尚未评估
24.1 percentage_points	—	尚未评估
8.4 percentage_points	—	尚未评估
43.1 percentage_points	—	尚未评估
18.1 percentage_points	—	尚未评估
56.5 percentage_points	—	尚未评估

Full downstream results after standard 4-stage post-training pipeline (SFT, DPO, RLVR1, RLVR2) for 13B Switch Distillation post-training performance.

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果