List your company
ResearchFormerly WizWand

Mental Health Assistant Evaluation on 10 situational well-being prompts

8.9ScoreGPT-4o
6.4047.0527.78.348Nov 18, 2025
Updated 4mo ago

Evaluation results

MethodLinks
GPT-4oJudge=GPT-4o, Rank=12025.118.9
Claude 3.7 SonnetJudge=GPT-4o, Rank=22025.118.7
Gemma-3Judge=GPT-4o, Rank=22025.118.7
LLaMA-3Judge=GPT-4o, Rank=42025.118.6
Al LunaJudge=GPT-4o, Rank=52025.118.5
LlamaSupportJudge=GPT-4o, Rank=62025.118.4
MistralJudge=GPT-4o, Rank=72025.118.3
Phi-4Judge=GPT-4o, Rank=82025.117.3
MentalLLaMA-2Judge=GPT-4o, Rank=92025.116.5