Sycophancy (Lechmazur) — leaderboard

Tests whether models maintain consistent judgments when presented with opposite first-person perspectives of the same dispute. Measures sycophancy rate - how often a model agrees with both opposing narrators.

Metric: Sycophancy rate % (lower is better). Source: github.com. Status: saturated. 32 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)0.5
2Gemini 3.5 Flash0.5
3Grok 4.30.5
4Qwen 3.5 397B A17B2
5MiMo-V2.5-Pro2.5
6Claude Opus 4.6 (Non-reasoning)2.5
7Gemini 3.1 Flash Lite (Preview)3
8MiniMax-M33.5
9GPT-5.5 (High)3.5
10Qwen 3.6 Max Preview4
11GLM-5.14.5
12Kimi K2.64.5
13Gemma 4 31B (Reasoning)4.5
14Claude Opus 4.7 (High)4.5
15DeepSeek V4 Pro5

Interactive version: theaggregate.ai/benchmark?slug=sycophancy-lechmazur · How the rankings work · Data refreshed daily, snapshot 2026-07-22.