Counseling Interaction Evaluation on PsychEval (Resistant)
8.6RRO (Client)GPT-5.4
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.4Client Resistance Setting=Resistant2026.06 | 8.6 | 2.79 | 1.22 | 9.34 | 3.4 | 6.49 | 9.11 | 6.91 | 8.33 | 9.33 | |
| DeepSeek-v3.2Client Resistance Setting=Resistant2026.06 | 7.1 | 3.16 | 0.98 | 7.85 | 2.6 | 6.07 | 7.97 | 5.12 | 7.23 | 8.33 | |
| STREAMS-RGClient Resistance Setting=Resistant2026.06 | 6.77 | 2.95 | 1.44 | 6.7 | 3.07 | 5.8 | 8.02 | 4.96 | 6.94 | 8.94 | |
| Gemini-3.1Client Resistance Setting=Resistant2026.06 | 6.73 | 3.02 | 1.3 | 7.22 | 3.32 | 6.28 | 7.84 | 5.12 | 7.69 | 8.6 | |
| MiniMax-M2.5Client Resistance Setting=Resistant2026.06 | 6.62 | 3.25 | 1.06 | 7.68 | 2.57 | 5.57 | 7.86 | 4.67 | 6.75 | 7.86 | |
| STREAMS-SGClient Resistance Setting=Resistant2026.06 | 6.57 | 2.8 | 1.51 | 6.41 | 3.09 | 5.51 | 7.77 | 4.62 | 6.61 | 8.69 | |
| Soulchat2Client Resistance Setting=Resistant2026.06 | 5.82 | 3.22 | 0.9 | 5.53 | 1.86 | 5.2 | 6.33 | 3.28 | 5.27 | 5.39 | |
| STREAMS-RLClient Resistance Setting=Resistant2026.06 | 5.8 | 3.25 | 1.08 | 6.18 | 2.48 | 5.74 | 6.91 | 5.19 | 5.72 | 7.87 | |
| Graph2CounselClient Resistance Setting=Resistant2026.06 | 5.61 | 3.39 | 1 | 5.41 | 1.91 | 4.99 | 6.17 | 2.89 | 5.46 | 5.83 | |
| STREAMS-SFTClient Resistance Setting=Resistant2026.06 | 5.56 | 3.29 | 0.97 | 5.85 | 2.39 | 5.01 | 6.6 | 4.82 | 5.46 | 7.37 | |
| MusPsyClient Resistance Setting=Resistant2026.06 | 5.35 | 3.04 | 0.95 | 4.66 | 1.49 | 4.86 | 5.93 | 2.61 | 4.48 | 4.73 | |
| PsydialClient Resistance Setting=Resistant2026.06 | 5.24 | 3.12 | 0.97 | 6.04 | 1.75 | 3.98 | 5.24 | 2.15 | 3.04 | 3.33 | |
| CpsycounxClient Resistance Setting=Resistant2026.06 | 5.23 | 3.24 | 0.81 | 4.02 | 1 | 2.8 | 4.75 | 2.53 | 2.32 | 3.23 | |
| SimpsybotClient Resistance Setting=Resistant2026.06 | 5.18 | 3.56 | 0.79 | 5.1 | 1.4 | 5.43 | 5.89 | 3.21 | 4.59 | 5.5 | |
| MAGneTClient Resistance Setting=Resistant2026.06 | 5.09 | 3.43 | 0.76 | 3.78 | 1.3 | 3.79 | 4.62 | 1.54 | 2.85 | 3.36 | |
| PsyAdvisorClient Resistance Setting=Resistant2026.06 | 5.07 | 3.21 | 0.83 | 5.2 | 1.69 | 4.13 | 5.49 | 1.92 | 3.82 | 4.22 | |
| CAMELClient Resistance Setting=Resistant2026.06 | 5.03 | 3.03 | 1.04 | 5.06 | 2.1 | 4.41 | 5.43 | 2.42 | 3.93 | 4.7 | |
| MeChatClient Resistance Setting=Resistant2026.06 | 4.99 | 2.93 | 0.7 | 3.16 | 1.32 | 3.17 | 3.82 | 1.42 | 2.17 | 1.94 | |
| PsychatClient Resistance Setting=Resistant2026.06 | 4.81 | 3.41 | 0.53 | 2.56 | 1.08 | 2.51 | 3.16 | 1.12 | 1.16 | 0.98 |