On Countdown, adding IM improves or preserves every ESPO, GDPO, and SPG accuracy cell. SPG+IM reports 81.6%, 81.6%, and 80.9% accuracy at lengths 128, 256, and 512, corresponding to relative gains of 18.60%, 15.42%, and 15.08% over SPG.

On Countdown, adding IM improves or preserves every ESPO, GDPO, and SPG accuracy cell. SPG+IM reports 81.6%, 81.6%, and 80.9% accuracy at lengths 128, 256, and 512, corresponding to relative gains of 18.60%, 15.42%, and 15.08% over SPG. · CiteArk

测量结果

已评估 0/36 项

获得支持 0有争议或冲突 0尚未评估 36

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。
指标与条件	论文报告	最近可用实测	证据判断
model: LLaDA-8B-Instruct · dataset: Countdown · generationLengthTokens: 128	20.7%	—	尚未评估
model: LLaDA-8B-Instruct · dataset: Countdown · generationLengthTokens: 256	19.5%	—	尚未评估
model: LLaDA-8B-Instruct · dataset: Countdown · generationLengthTokens: 512	16%	—	尚未评估
model: D1 · dataset: Countdown · generationLengthTokens: 128	30.9%	—	尚未评估
model: D1 · dataset: Countdown · generationLengthTokens: 256	30.9%	—	尚未评估
model: D1 · dataset: Countdown · generationLengthTokens: 512	34.4%	—	尚未评估
model: WD1 · dataset: Countdown · generationLengthTokens: 128	48.8%	—	尚未评估
model: WD1 · dataset: Countdown · generationLengthTokens: 256	51.2%	—	尚未评估
model: WD1 · dataset: Countdown · generationLengthTokens: 512	50.8%	—	尚未评估
model: ESPO · dataset: Countdown · generationLengthTokens: 128	74.2%	—	尚未评估
model: ESPO · dataset: Countdown · generationLengthTokens: 256	72.6%	—	尚未评估
model: ESPO · dataset: Countdown · generationLengthTokens: 512	75.3%	—	尚未评估

On Countdown, adding IM improves or preserves every ESPO, GDPO, and SPG accuracy cell. SPG+IM reports 81.6%, 81.6%, and 80.9% accuracy at lengths 128, 256, and 512, corresponding to relative gains of 18.60%, 15.42%, and 15.08% over SPG.

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果