List your company

Short-form Question Answering on Short-form QA Aggregate (Avg.) (test)

35.93EMVSPO + PRS_short
8.546815.655922.76529.8741Dec 8, 2025

Evaluation results

MethodLinks
VSPO + PRS_shortBackbone=Qwen2.5-3B-Instruct2025.1235.93
GRPO + PRS_shortBackbone=Qwen2.5-3B-Instruct2025.1234.83
PPO + PRS_shortBackbone=Qwen2.5-3B-Instruct2025.1233.33
SFTBackbone=Qwen2.5-3B-Instruct2025.1217.6
UntrainedBackbone=Qwen2.5-3B-Instruct2025.129.6