LLM-as-a-Judge on Peer-Support Evaluation Set
4.89EmpathyMindTailor
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| MindTailorBackbone Model=Gemma42026.06 | 4.89 | 4.5 | 4.92 | 4.74 | 4.76 | |
| MentalAgoraBackbone Model=Gemma42026.06 | 4.88 | 4.81 | 4.82 | 4.71 | 4.81 | |
| MindTailorBackbone Model=Gemma32026.06 | 4.74 | 4.14 | 4.91 | 4.66 | 4.61 | |
| VanillaBackbone Model=Gemma42026.06 | 4.65 | 4.41 | 4.87 | 4.68 | 4.65 | |
| ES-VRBackbone Model=Gemma32026.06 | 4.64 | 4.07 | 4.63 | 4.29 | 4.41 | |
| MindTailorBackbone Model=Gemini2026.06 | 4.61 | 4.15 | 4.86 | 4.64 | 4.56 | |
| MentalAgoraBackbone Model=Gemma32026.06 | 4.52 | 4.16 | 4.71 | 4.52 | 4.48 | |
| MentalAgoraBackbone Model=Gemini2026.06 | 4.5 | 4.26 | 4.72 | 4.53 | 4.5 | |
| VanillaBackbone Model=Gemma32026.06 | 4.47 | 4.06 | 4.84 | 4.52 | 4.47 | |
| ES-VRBackbone Model=Mistral2026.06 | 4.35 | 3.96 | 4.16 | 4.13 | 4.15 | |
| MindTailorBackbone Model=Qwen2.5 72B2026.06 | 4.19 | 4.17 | 4.63 | 4.39 | 4.35 | |
| ES-VRBackbone Model=Qwen2.5 14B2026.06 | 4.16 | 4.03 | 4.2 | 4.25 | 4.16 | |
| MindTailorBackbone Model=Qwen2.5 14B2026.06 | 4.13 | 4.05 | 4.41 | 4.26 | 4.21 | |
| MindTailorBackbone Model=Mistral2026.06 | 4.13 | 4.1 | 4.36 | 4.25 | 4.21 | |
| VanillaBackbone Model=Qwen2.5 72B2026.06 | 4.09 | 4.05 | 4.52 | 4.25 | 4.23 | |
| VanillaBackbone Model=Qwen2.5 14B2026.06 | 3.99 | 3.85 | 4.27 | 4.08 | 4.05 | |
| MentalAgoraBackbone Model=Qwen2.5 14B2026.06 | 3.97 | 4.14 | 4.19 | 4.13 | 4.11 | |
| ES-VRBackbone Model=Gemma42026.06 | 3.96 | 3.76 | 4.05 | 3.87 | 3.91 | |
| MentalAgoraBackbone Model=Qwen2.5 72B2026.06 | 3.92 | 4.16 | 4.24 | 4.13 | 4.11 | |
| ES-VRBackbone Model=Qwen2.5 72B2026.06 | 3.9 | 3.86 | 4.13 | 4.04 | 3.98 | |
| VanillaBackbone Model=Mistral2026.06 | 3.85 | 3.87 | 4.3 | 4.02 | 4.01 | |
| MentalAgoraBackbone Model=Mistral2026.06 | 3.7 | 4.03 | 4.12 | 3.95 | 3.95 | |
| VanillaBackbone Model=Gemini2026.06 | 3.57 | 2.94 | 3.32 | 3.11 | 3.24 |