Counseling Evaluation on PsychEval Resistant
0.45I(P; C)Simpsybot
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Simpsybot2026.06 | 0.45 | 0.7 | 0.27 | |
| CAMEL2026.06 | 0.37 | 0.69 | 0.43 | |
| MAGneT2026.06 | 0.36 | 0.67 | 0.54 | |
| Cpsycounx2026.06 | 0.35 | 0.63 | 0.55 | |
| MusPsy2026.06 | 0.29 | 0.42 | 0.6 | |
| Graph2Counsel2026.06 | 0.27 | 0.46 | 0.45 | |
| MeChat2026.06 | 0.27 | 0.42 | 0.67 | |
| STREAMS-RL2026.06 | 0.24 | 0.79 | 0.23 | |
| Psychat2026.06 | 0.21 | 0.67 | 0.25 | |
| STREAMS-SFT2026.06 | 0.2 | 0.56 | 0.28 | |
| Gemini-3.12026.06 | 0.18 | 0.37 | 0.08 | |
| Soulchat22026.06 | 0.17 | 0.3 | 0.23 | |
| MiniMax-M2.52026.06 | 0.17 | 0.57 | 0.52 | |
| DeepSeek-v3.22026.06 | 0.16 | 0.73 | 0.43 | |
| STREAMS-RG2026.06 | 0.15 | 0.64 | 0.19 | |
| STREAMS-SG2026.06 | 0.14 | 0.61 | 0.21 | |
| Psydial2026.06 | 0.13 | 0.78 | 0.58 | |
| PsyAdvisor2026.06 | 0.11 | 0.36 | 0.38 | |
| GPT-5.42026.06 | 0.11 | 1.15 | 0.26 |