Tracing on Beavertails (test)
99.29Tracing Success Rate (TSR)Llama-3.2-1B
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama-3.2-1BBase Model=Qwen-3-8B2026.03 | 99.29 | |
| Llama-3.2-1BBase Model=Llama-3-8B2026.03 | 98.93 | |
| DEBUGLMBase Model=Llama-3-8B2026.03 | 98.57 | |
| DEBUGLMBase Model=Qwen-3-8B2026.03 | 98.48 | |
| SBERTBase Model=Qwen-3-8B2026.03 | 97.41 | |
| SBERTBase Model=Llama-3-8B2026.03 | 97.23 | |
| ROUGE-LBase Model=Qwen-3-8B2026.03 | 96.7 | |
| BM25Base Model=Llama-3-8B2026.03 | 96.34 | |
| BM25Base Model=Qwen-3-8B2026.03 | 96.16 | |
| ROUGE-LBase Model=Llama-3-8B2026.03 | 95.54 |