List your company
ResearchFormerly WizWand

Scientific Reasoning on GPQA Diamond (Avg@64)

39.6Avg@64DARS-HW-Breadth
27.95230.9763437.024Aug 19, 2025
Updated 6mo ago

Evaluation results

MethodLinks
DARS-HW-BreadthBase Model=Qwen2.5-Math-7B2025.0839.6
DARS-HWBase Model=Qwen2.5-Math-7B2025.0838.6
RLVR BaselineBase Model=Qwen2.5-Math-7B2025.0838.5
DARS-HW-BreadthBase Model=Qwen2.5-Math-1.5B2025.0829.3
RLVR BaselineBase Model=Qwen2.5-Math-1.5B2025.0828.5
DARS-HWBase Model=Qwen2.5-Math-1.5B2025.0828.4