Degree of Change on PerturbQA HepG2
79.89AccuracyBoN w/ Full Set
Evaluation results
| Method | Links | |
|---|---|---|
| BoN w/ Full SetDecoding Strategy=Best-of-N, Reward Model=Full Set2026.03 | 79.89 | |
| Majority VotingDecoding Strategy=Majority Voting2026.03 | 74.51 | |
| BoN w/ Qwen-PRM800KDecoding Strategy=Best-of-N, Reward Model=Qwen-PRM800K2026.03 | 73.53 | |
| BoN w/ Llama-PRM800KDecoding Strategy=Best-of-N, Reward Model=Llama-PRM800K2026.03 | 71.27 | |
| Greedy DecodingDecoding Strategy=Greedy2026.03 | 71.15 | |
| BoN w/ VersaPRMDecoding Strategy=Best-of-N, Reward Model=VersaPRM2026.03 | 69.7 |