WildReward: Learning Reward Models from In-the-Wild Human Interactions
Open paper
Benchmark
Model
Rank
Results
arithmetic-reasoning-on-gsm8k
Llama3.1-8B-Instruct (online DPO with WildReward)
#93
Accuracy: 87.9
multi-task-language-understanding-on-mmlu-pro
Llama3.1-8B-Instruct (online DPO with WildReward)
#115
Accuracy: 48.9
Rank counts only results with a code link.