List your company

STEM Reasoning on TheoremQA (Avg@2)

55.4Avg@2RLPR
30.33636.84343.3549.857Jan 21, 2026

Evaluation results

MethodLinks
RLPRBase=Base, Verifier=None2026.0155.4
DARLBase=Base, Verifier=None2026.0155.2
Oat-ZeroBase=Math, Verifier=Rule2026.0153.3
RLVRBase=Base, Verifier=Rule2026.0152.2
General ReasonerBase=Base, Verifier=Model2026.0152.1
SimpleRL-ZooBase=Math, Verifier=Rule2026.0151.1
SimpleRL-ZooBase=Base, Verifier=Rule2026.0149.5
TTRLBase=Base, Verifier=Rule2026.0148.8
PRIMEBase=Math, Verifier=Rule2026.0147.7
VeriFreeBase=Base, Verifier=None2026.0147.6
Qwen2.5-7B-InstBase=-, Verifier=None2026.0147.3
Qwen2.5-7BBase=-, Verifier=None2026.0141.4
DARLBase=Inst, Verifier=None2026.0139.4
RLPRBase=Inst, Verifier=None2026.0136.5
RLVRBase=Inst, Verifier=Rule2026.0132
Llama3.1-8B-InstBase=-, Verifier=None2026.0131.3