Novelty Evaluation on NoveltyBench
44Overall DominanceBACO-P-PUNC
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BACO-P-PUNCModels=Olmo2-7B and Olmo2-7B-Instruct2025.11 | 44 | 23.6 | |
| AlignedModels=Olmo2-7B and Olmo2-7B-Instruct2025.11 | 30.5 | 20.9 | |
| BaseModels=Olmo2-7B and Olmo2-7B-Instruct2025.11 | 11.7 | 9.8 | |
| OthersModels=Olmo2-7B and Olmo2-7B-Instruct2025.11 | 8.3 | — | |
| NudgingModels=Olmo2-7B and Olmo2-7B-Instruct2025.11 | 5.5 | 28.1 |