List your company

Mathematical Reasoning on Minerva (Avg@2)

57.7Avg@2DARL
31.738.4545.251.95Jan 21, 2026

Evaluation results

MethodLinks
DARLBase=Base, Verifier=None2026.0157.7
RLPRBase=Base, Verifier=None2026.0156.5
RLVRBase=Base, Verifier=Rule2026.0154.9
TTRLBase=Base, Verifier=Rule2026.0152.8
Oat-ZeroBase=Math, Verifier=Rule2026.0152.1
General ReasonerBase=Base, Verifier=Model2026.0151.7
SimpleRL-ZooBase=Math, Verifier=Rule2026.0151
Qwen2.5-7B-InstBase=-, Verifier=None2026.0149.4
SimpleRL-ZooBase=Base, Verifier=Rule2026.0149.2
VeriFreeBase=Base, Verifier=None2026.0149
PRIMEBase=Math, Verifier=Rule2026.0145.5
RLPRBase=Inst, Verifier=None2026.0139
DARLBase=Inst, Verifier=None2026.0137.9
Qwen2.5-7BBase=-, Verifier=None2026.0137.6
RLVRBase=Inst, Verifier=Rule2026.0135.2
Llama3.1-8B-InstBase=-, Verifier=None2026.0132.7