LLM self-play on 20 Questions. gpt-3.5-turbo has a score of 68

DeepSeek LLM Scaling Open-Source Language Models with Longtermism

BDCC, Free Full-Text

LLM self-play on 20 Questions. gpt-3.5-turbo has a score of 68

AI #49: Bioweapon Testing Begins — LessWrong

LLM self-play on 20 Questions. gpt-3.5-turbo has a score of 68

Harness the Power of LLMs: Zero-shot and Few-shot Prompting

PDF) Evaluating the use of GPT-3.5-turbo to provide clinical

PDF) GPT-3.5/4 - Is the programming performance declining over time?

AgentTuning: Enabling Generalized Agent Abilities for LLMs

10 sec for a call of gpt-3.5-turbo - API - OpenAI Developer Forum

LLM self-play on 20 Questions. gpt-3.5-turbo has a score of 68

BDCC, Free Full-Text

LLM self-play on 20 Questions. gpt-3.5-turbo has a score of 68

I scored the top Open LLM Leaderboard models with my own benchmark

arxiv-sanity