Tracing on TruthfulQA (test)
96.34Truthfulness Score Rate (TSR)Llama-3.2-1B
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama-3.2-1BBase Model=Qwen-3-8B2026.03 | 96.34 | |
| Llama-3.2-1BBase Model=Llama-3-8B2026.03 | 92.07 | |
| DEBUGLMBase Model=Qwen-3-8B2026.03 | 90.24 | |
| DEBUGLMBase Model=Llama-3-8B2026.03 | 84.76 | |
| ROUGE-LBase Model=Llama-3-8B2026.03 | 81.1 | |
| ROUGE-LBase Model=Qwen-3-8B2026.03 | 80.49 | |
| SBERTBase Model=Qwen-3-8B2026.03 | 64.02 | |
| SBERTBase Model=Llama-3-8B2026.03 | 60.98 | |
| BM25Base Model=Llama-3-8B2026.03 | 15.24 | |
| BM25Base Model=Qwen-3-8B2026.03 | 15.24 |