Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Sycophancy Resistance research benchmarks · SOTA2 Research

Sycophancy Resistance

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Anthropic model-written-evals sycophancy suite

Instruction Tuned

94.6Overall Sycophancy Resistance Score

6

Jun 5, 2026

Held-out MCQ sycophancy benchmark (aggregate)

Instruction Tuned

74MCQ Aggregate Score

6

Jun 5, 2026

Popular datasets

MCQ sycophancy benchmark Anthropic model-written-evals

Follow for updates

Join SOTA2 Contact