List your company

ResearchFormerly WizWand

Persona-Scenario

Benchmarks

TaskDatasetSOTA resultTrendResults

Dialogue Naturalness

Persona-Scenario

98.55GPT-Score: Fluency

3

Dialogue Goal Completion

Persona-Scenario

9.19Believability (Sotopia-Eval)

3

Dialogue Quality Evaluation

Persona-Scenario

3.7Believability

3