Released: 2026-06-02
openai/gpt-4o
openai
3/6
mistralai/mistral-medium-3
mistral
Failed
meta-llama/llama-3.3-70b-instruct
meta
5/6
deepseek/deepseek-chat-v3-0324
deepseek
Failed
Each model receives the same prompt structure with Wordle rules and feedback format. Models are given a maximum of 6 attempts with standard positional feedback after each guess to help refine their next attempt.