Definition
A standard test for how well reward models pick better answers over worse ones.
A benchmark for evaluating reward models on their ability to rank preferred over dispreferred responses across diverse categories.
Also called: RewardBench-2
A standard test for how well reward models pick better answers over worse ones.
A benchmark for evaluating reward models on their ability to rank preferred over dispreferred responses across diverse categories.
Also called: RewardBench-2