List your company

General Reasoning on TheoremQA (Average@2)

36.3Average@2CoVRL
24.75627.75330.7533.747Dec 14, 2025

Evaluation results

MethodLinks
CoVRLBackbone=Qwen2.5-7B-Base2025.1236.3
RAVRBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.1234.8
RLPRBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.1233.5
VeriFreeBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.1233.4
LaTROBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.1232.8
JLBBackbone=Qwen2.5-7B-Base, Algorithm=GRPO2025.1231.9
Base ModelBackbone=Qwen2.5-7B-Base2025.1225.2