Unverified50% confidenceBenchmarkExact time
The author tested flagship models from OpenAI, xAI, and Anthropic using the same 20 scenarios, and the rate at which GPT, Grok, Gemini, and two Claude models held their position when faced with nurse's notes dropped from near-perfect scores to the 70%–85% range.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
UnverifiedIn a simulation experiment, the author generated weekly booking volume data for 40 regions spanning two years, with 5 regions receiving treatment and a true effect of a 10% increase in bookings.64% similarUnverifiedThe accuracy of the seven models tested on PhysMent ranges from 25% to 67%62% similarUnverifiedIn practical testing, a small OpenAI model lost 66% to 81% of scorer responses.62% similarUnverifiedRanked by question difficulty, persistence rate was 91.4% on the 60 questions that all models answered correctly, but only 73.5% on the 52 questions that at least one model got wrong, indicating that sycophancy tracks uncertainty.61% similarUnverifiedIn an editing benchmark, the same GPT model's score dropped from 99% to 70% depending on the framework used.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/999514API
curl https://kongchang.com/api/v1/knowledge/claims/999514MCP
get_claim(id=999514)