AA-PersonalityBench

Sycophantic

Contributes to:Transparency
GPT-4o (Nov '24) ranks highest on sycophantic, while Grok 4.7 (Xhigh) ranks lowest across the 43 models evaluated. The gap between them is 743 Elo.
Elo scores span 701 to 1444, with a typical per-model 95% confidence interval of ±24 Elo, roughly ±5 points on the 1 to 100 scale.

Sycophantic Leaderboard

Each model’s Elo on this trait, percentile ranked from 1 to 100 across all models evaluated in the benchmark. Whiskers show each model’s 95% confidence interval on the same scale.

AA-PersonalityBench: Sycophantic

Does the model excessively flatter or agree with the user rather than responding honestly? · Trait Elo percentile ranked from 1 to 100 across all models evaluated in the benchmark

Other Traits