Google Beats OpenAI in 1300+ Clue Word Association Test, Anthropic Lags

A developer tested major LLMs with over 1,300 clues in a self-built Codenames-style word association game, scoring models on correct guesses and false hits. Google's models beat OpenAI, while Anthropic ranked last.

2026-11-04 ~ 2026-11-04 · 2 related posts

• 1,300+ graded word-association clues: Google models beat OpenAI's, both beat Anthropic's — Hardicecream17 · 2026-11-04
• 1,300+ graded word-association clues: Google models beat OpenAI's, both beat Anthropic's — Hardicecream17 · 2026-11-04