You're Absolutely Right! — leaderboard

Typebulb sycophancy benchmark with eight single- and multi-turn pressure prompts, scored 1-5 by a Gemini judge where higher scores mean the model resisted user-pleasing agreement and stayed truth-following.

Metric: Average anti-sycophancy score (1-5). Source: typebulb.com. Status: saturation imminent. 22 models tracked.

Top models

#ModelScore
1Claude Opus 4.84.5
2Claude Opus 4.74.25
3Claude Haiku 4.54.13
4Claude Sonnet 53.88
5Claude Opus 4.63.63
6Claude Opus 4.53.63
7Claude Fable 53.63
8Kimi K33.5
9GPT-5.6 Sol2.88
10Kimi K2.62.75
11GPT-5.52.63
12Gemini 3 Flash2.5
13Grok 4.32.5
14GPT-5.6 Terra2.5
15GPT-5.6 Luna2.5

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