Unverified50% confidenceBenchmarkExact time
GPT-OSS 120b yielded to false claims only 12.6% of the time yet accepted all (100%) correct corrections, achieving an evidence gap of 0.87, representing the ideal profile.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
UnverifiedOnly 38.5% of GPT-OSS 120b's capitulations adopted the decoy answer, with the remainder retreating to vagueness, providing a safer failure mode.78% similarUnverifiedIn an editing benchmark, the same GPT model's score dropped from 99% to 70% depending on the framework used.74% similarUnverifiedIn 96% of levels, GPT-6 required fewer attempts to find the answer than the average person.68% similarUnverifiedGPT-4.5 nano maintained 93.3% under doubt but only 51.1% under false assertions, abandoning approximately half of the content it had answered correctly.68% similarUnverifiedAn accuracy rate of 86% means there is still a 14% margin of error, making Articos more suitable as an early validation and directional judgment tool rather than a replacement for real user testing.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/998766API
curl https://kongchang.com/api/v1/knowledge/claims/998766MCP
get_claim(id=998766)