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. 24 models tracked.

Top models

#ModelScore
1Gemini 3.6 Flash0.5
2Gemini 3.5 Flash Lite1
3Qwen 3.7 Max (2026-06-08)1.5
4Ernie 5.12
5Qwen 3.7 Flash2.5
6MiMo-V2.5-Pro2.6
7MiniMax-M33.6
8Kimi K34.5
9Gemma 4 31B (Reasoning)4.6
10DeepSeek V4 Pro5.1
11Qwen 3.7 Plus5.1
12Arcee Trinity Large (Thinking)18.9
13Mistral Medium 3.5 (High)22.4

Interactive version: theaggregate.ai/benchmark?slug=sycophancy-lechmazur · How It Works · Data refreshed daily, snapshot 2026-09-05.