Model Fingerprinting on RL Positive Samples
355.27Absolute Z-scoreAWM
Evaluation Results
| Method | Links | |
|---|---|---|
| AWMBase=Qwen2.5-7B, Offspring=Reason2025.10 | 355.27 | |
| AWMBase=Qwen2.5-1.5B, Offspring=Zero2025.10 | 355.27 | |
| AWMBase=Minicpm-2B, Offspring=DPO2025.10 | 355.27 | |
| AWMBase=Qwen3-4B, Offspring=GRPO2025.10 | 355.27 | |
| AWMBase=Chatglm-6B, Offspring=RLHF2025.10 | 355.27 | |
| AWMBase=Open llama3B, Offspring=RLHF2025.10 | 355.23 | |
| AWMBase=Mixtral, Offspring=DPO2025.10 | 355.23 | |
| AWMBase=Mistral-7B, Offspring=DPO2025.10 | 355.23 | |
| AWMBase=Mistral-7B, Offspring=Dolphin2025.10 | 355.23 | |
| AWMBase=Llama3-8B, Offspring=DPO2025.10 | 355.23 | |
| HuRefBase=Qwen2.5-7B, Offspring=Reason2025.10 | 44.58 | |
| HuRefBase=Qwen2.5-1.5B, Offspring=Zero2025.10 | 44.58 | |
| HuRefBase=Minicpm-2B, Offspring=DPO2025.10 | 44.58 | |
| HuRefBase=Qwen3-4B, Offspring=GRPO2025.10 | 44.58 | |
| HuRefBase=Chatglm-6B, Offspring=RLHF2025.10 | 44.58 | |
| HuRefBase=Mixtral, Offspring=DPO2025.10 | 44.57 | |
| HuRefBase=Mistral-7B, Offspring=Dolphin2025.10 | 44.54 | |
| HuRefBase=Mistral-7B, Offspring=DPO2025.10 | 44.53 | |
| HuRefBase=Open llama3B, Offspring=RLHF2025.10 | 44.52 | |
| HuRefBase=Llama3-8B, Offspring=DPO2025.10 | 44.52 | |
| REEFBase=Chatglm-6B, Offspring=RLHF2025.10 | 1.96 | |
| REEFBase=Llama3-8B, Offspring=DPO2025.10 | 1.96 | |
| REEFBase=Open llama3B, Offspring=RLHF2025.10 | 1.94 | |
| REEFBase=Qwen2.5-1.5B, Offspring=Zero2025.10 | 1.94 | |
| REEFBase=Qwen2.5-7B, Offspring=Reason2025.10 | 1.93 | |
| REEFBase=Minicpm-2B, Offspring=DPO2025.10 | 1.92 | |
| REEFBase=Qwen3-4B, Offspring=GRPO2025.10 | 1.78 | |
| REEFBase=Mixtral, Offspring=DPO2025.10 | 1.75 | |
| REEFBase=Mistral-7B, Offspring=DPO2025.10 | 1.48 | |
| REEFBase=Mistral-7B, Offspring=Dolphin2025.10 | 1.21 |