List your company

Science Reasoning on GPQA (Avg@4)

39.4Avg@4DARL
31.28833.39435.537.606Jan 21, 2026

Evaluation results

MethodLinks
DARLBase=Base, Verifier=None2026.0139.4
Oat-ZeroBase=Math, Verifier=Rule2026.0138.8
SimpleRL-ZooBase=Math, Verifier=Rule2026.0138.4
RLPRBase=Base, Verifier=None2026.0137.6
General ReasonerBase=Base, Verifier=Model2026.0137.4
DARLBase=Inst, Verifier=None2026.0136.9
VeriFreeBase=Base, Verifier=None2026.0136.7
RLPRBase=Inst, Verifier=None2026.0136.5
SimpleRL-ZooBase=Base, Verifier=Rule2026.0136.2
RLVRBase=Base, Verifier=Rule2026.0136.2
RLVRBase=Inst, Verifier=Rule2026.0136
Qwen2.5-7B-InstBase=-, Verifier=None2026.0134.2
TTRLBase=Base, Verifier=Rule2026.0134.1
Qwen2.5-7BBase=-, Verifier=None2026.0132.4
PRIMEBase=Math, Verifier=Rule2026.0132.1
Llama3.1-8B-InstBase=-, Verifier=None2026.0131.6