List your company

Summarization on TL;DR (Win Rate variants)

83.4Win Rate (0% Flip Rate)α-URM
76.53678.31880.181.882Jul 3, 2026

Evaluation results

MethodLinks
α-URMModels=Llama-3.2-3B2026.0783.481.976.179.9
α-URMModels=Qwen-3-1.7B2026.0782.979.268.969.6
URMModels=Llama-3.2-3B2026.0782.883.277.579.4
URMModels=Qwen-3-1.7B2026.0781.58071.670.1
RMModels=Qwen-3-1.7B2026.0781.376.263.363.9
cRMModels=Llama-3.2-3B2026.0780.876.569.975.7
cRMModels=Qwen-3-1.7B2026.0780.476.666.465
RMModels=Llama-3.2-3B2026.0779.476.469.175.5
rRMModels=Llama-3.2-3B2026.0777.377.768.675.7
rRMModels=Qwen-3-1.7B2026.0776.873.664.765.9