IlyaGusev/ping_pong_bench

A benchmark for role-playing language models

40
/ 100
Emerging

This helps evaluate how well different large language models (LLMs) can role-play in conversations. It takes a description of a character and a conversational scenario, then uses another LLM to pretend to be a user interacting with the model being tested. The output is a detailed rating of the tested model's performance on criteria like staying in character, being entertaining, and fluency. It's for researchers and developers who need to assess the conversational abilities of LLMs without extensive human involvement.

116 stars. No commits in the last 6 months.

Use this if you need an automated way to test and compare how well large language models maintain a specific persona and engage in multi-turn role-playing conversations.

Not ideal if you want to evaluate general conversational abilities that don't involve specific character roles or complex scenarios.

LLM-evaluation conversational-AI persona-testing AI-benchmarking
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

116

Forks

11

Language

Python

License

Apache-2.0

Last pushed

May 25, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/IlyaGusev/ping_pong_bench"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.