Contamination Evaluation on ArxivRollBench
0.48Absolute RS_ILlama3.1-70B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Llama3.1-70B2025.07 | 0.48 | 0.02 | |
| Phi-22025.07 | 0.62 | 0.36 | |
| Llama3.1-8B2025.07 | 0.67 | 0.25 | |
| Qwen2-7B2025.07 | 0.69 | 0.42 | |
| Qwen2.5-7B2025.07 | 0.7 | 0.37 | |
| Llama3-8B2025.07 | 0.74 | 0.74 | |
| Llama-3.1-Nemotron-70B2025.07 | 0.77 | 0.14 | |
| Yi-1.5-34B2025.07 | 0.81 | 0.55 | |
| Phi-1.52025.07 | 0.82 | 0.57 | |
| Phi-3.5-mini2025.07 | 1.07 | 0.07 | |
| Llama2-7B2025.07 | 1.14 | 0.11 | |
| Phi-12025.07 | 1.21 | 1.31 | |
| Phi-3-mini2025.07 | 1.27 | 0.05 | |
| Qwen2.5-72B2025.07 | 1.41 | 0.32 |