List your company

Planning on Trips (test)

15.6AccuracyReProbe
11.64812.67413.714.726Nov 9, 2025

Evaluation results

MethodLinks
ReProbe# Sample=32K, Input Features=Hidden States, Annotation Source=Self-anno, Decoding Method=Beam search2025.1115.6
ReProbe# Sample=32K, Input Features=Attn+Logit, Annotation Source=Self-anno, Decoding Method=Beam search2025.1115
ReProbe# Sample=32K, Input Features=Hidden States, Annotation Source=DeepSeek-anno, Decoding Method=Beam search2025.1113.4
Qwen2.5-Math-7B-PRM800k# Sample=263K, Decoding Method=Beam search2025.1113.1
Qwen2.5-Math-PRM-7B# Sample=860K, Decoding Method=Beam search2025.1113.1
ReProbe# Sample=32K, Input Features=Attn+Logit, Annotation Source=DeepSeek-anno, Decoding Method=Beam search2025.1111.8