General Alignment on General Alignment and Coherence
93.52Alignment ScoreUnsafeChain
Evaluation results
| Method | Links | ||
|---|---|---|---|
| UnsafeChainBase Model=R1-8B, Data Subset=selected2025.07 | 93.52 | 68.96 | |
| UnsafeChainBase Model=R1-8B, Data Subset=random2025.07 | 93.31 | 69.89 | |
| R1Model Size=8B2025.07 | 93.14 | 75.62 | |
| STAR-1Base Model=R1-8B2025.07 | 91.12 | 68.28 | |
| UnsafeChainBase Model=R1-8B, Data Subset=full2025.07 | 89.58 | 68.75 | |
| SafeChainBase Model=R1-8B2025.07 | 87.63 | 63.02 | |
| UnsafeChainBase Model=R1-7B, Data Subset=full2025.07 | 87.3 | 62.76 | |
| UnsafeChainBase Model=R1-7B, Data Subset=selected2025.07 | 87.1 | 67.66 | |
| STAR-1Base Model=R1-7B2025.07 | 86.53 | 70.78 | |
| R1Model Size=7B2025.07 | 86.37 | 68.95 | |
| UnsafeChainBase Model=R1-7B, Data Subset=random2025.07 | 86 | 67.97 | |
| SafeChainBase Model=R1-7B2025.07 | 85 | 67.7 | |
| UnsafeChainBase Model=R1-1.5B, Data Subset=selected2025.07 | 81.72 | 49.28 | |
| SafeChainBase Model=R1-1.5B2025.07 | 81.19 | 53.31 | |
| STAR-1Base Model=R1-1.5B2025.07 | 78.78 | 50.86 | |
| UnsafeChainBase Model=R1-1.5B, Data Subset=full2025.07 | 78.01 | 46.67 | |
| UnsafeChainBase Model=R1-1.5B, Data Subset=random2025.07 | 77.8 | 47.03 | |
| R1Model Size=1.5B2025.07 | 76.3 | 50.21 |