E01¶


Research	R0057 — RLHF Yes-Men Claims v3
Run	2026-04-01
Claim	C018
Source	SRC01
Evidence	SRC01-E01
Type	Reported

Anthropic reports 70-85% sycophancy reduction in latest models; OpenAI reports substantial improvements in GPT-5

URL: https://www.anthropic.com/news/protecting-well-being-of-users

Extract¶

Anthropic's latest models (Opus 4.5, Sonnet 4.5, Haiku 4.5) scored 70-85% lower on sycophancy than Opus 4.1. OpenAI reports GPT-5 shows substantial improvements in sycophancy reduction. Both companies released public evaluation metrics. Improvements ship to all users, not enterprise-specific.

Relevance to Hypotheses¶

Hypothesis	Relationship	Strength
H1	Supports	Directly addresses claim accuracy
H2	Supports	Allows for partial correctness
H3	Contradicts	Evidence contradicts material inaccuracy

Context¶

Direct from vendor announcements with quantified metrics.