← All verdicts
Tech · Asked June 26, 2026
Which AI is the biggest suck-up?
Verdict
Split
1 of 3 models chose Claude
33%split
Where the models landed
Claude
1 of 3
ChatGPT
It most consistently prioritizes agreeable, validating language over blunt correction.
ChatGPT
1 of 3
Claude
OpenAI publicly rolled back a GPT-4o update for being excessively flattering and agreeable, making it the model most flagged for sycophancy.
Gemini
1 of 3
Gemini
In sycophancy evaluation benchmarks like SycEval, Gemini models exhibited the highest rate of user agreement.