Safety Evaluation on JBB
59.67Safe@1UnsafeChain
Evaluation Results
| Method | Links | |
|---|---|---|
| UnsafeChainBase Model=R1-8B, Data Subset=selected2025.07 | 59.67 | |
| UnsafeChainBase Model=R1-8B, Data Subset=full2025.07 | 59.67 | |
| SafeChainBase Model=R1-8B2025.07 | 59 | |
| STAR-1Base Model=R1-8B2025.07 | 57.67 | |
| UnsafeChainBase Model=R1-8B, Data Subset=random2025.07 | 56 | |
| STAR-1Base Model=R1-7B2025.07 | 54.67 | |
| SafeChainBase Model=R1-7B2025.07 | 54.33 | |
| R1Model Size=8B2025.07 | 53 | |
| UnsafeChainBase Model=R1-1.5B, Data Subset=full2025.07 | 53 | |
| UnsafeChainBase Model=R1-7B, Data Subset=random2025.07 | 52.67 | |
| UnsafeChainBase Model=R1-7B, Data Subset=full2025.07 | 52.33 | |
| R1Model Size=7B2025.07 | 52 | |
| UnsafeChainBase Model=R1-7B, Data Subset=selected2025.07 | 51.33 | |
| SafeChainBase Model=R1-1.5B2025.07 | 51 | |
| STAR-1Base Model=R1-1.5B2025.07 | 50 | |
| UnsafeChainBase Model=R1-1.5B, Data Subset=selected2025.07 | 47.67 | |
| UnsafeChainBase Model=R1-1.5B, Data Subset=random2025.07 | 44.33 | |
| R1Model Size=1.5B2025.07 | 1 |