List your company

Bertrand Competition

-0.1168NEUntrained
-0.1390960.0114020.16190.312398Jan 22, 2026

Evaluation results

MethodLinks
Untrainedframework=GameTalk2026.01-0.116815,158.42-0.7269-1.43440.828310,096.35
STaRframework=GameTalk2026.01-0.04739,977.39-0.6266-1.45390.827210,059.1
GRPOframework=GameTalk2026.010.224826,370.380.577-1.46350.873610,433.34
DPO (pairs)framework=GameTalk2026.010.440644,619.980.9952-1.64880.884413,735.55