List your company

Practice Pathway Evaluation on SocialCoach Practice Sessions (Simulated) (test)

4.38Average EngagementSocialCoachQwen3-8B
3.41283.66393.9154.1661Jun 2, 2026

Evaluation results

MethodLinks
SocialCoachQwen3-8BTuning Status=Finetuned, Backbone Model=Qwen3-8B2026.064.384.114.254.05
NonTuningGemini-3-ProTuning Status=NonTuning, Backbone Model=Gemini-3-Pro2026.063.953.884.083.78
NonTuningQwen3-235BTuning Status=NonTuning, Backbone Model=Qwen3-235B2026.063.923.683.963.67
NonTuningGPT-5Tuning Status=NonTuning, Backbone Model=GPT-52026.063.883.754.023.74
NonTuningDeepSeek-R1-0528Tuning Status=NonTuning, Backbone Model=DeepSeek-R1-05282026.063.763.723.923.68
NonTuningQwen3-8BTuning Status=NonTuning, Backbone Model=Qwen3-8B2026.063.613.443.783.42
ProfileQueryBackbone Model=ProfileQuery2026.063.453.523.613.4