Unverified50% confidenceBenchmarkExact time
gpt-oss-120b scored 0.625, lower than gpt-oss-20b's 0.720, indicating that a larger model does not necessarily mean a safer one.
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.70% similarUnverifiedEven in large models ranging from 70B to 72B, the penetration rate of safety instructions remains below 10%, and increased scale does not make safety prompts more effective.70% similarUnverifiedOn gpt-oss-120B, the conformity rate in the Asch conformity experiment under blind testing conditions was 0%, while the conformity rate rose to 83.3% when the paradigm was explicitly named.68% similarUnverifiedIn an editing benchmark, the same GPT model's score dropped from 99% to 70% depending on the framework used.68% similarUnverifiedGPT-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.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/999531API
curl https://kongchang.com/api/v1/knowledge/claims/999531MCP
get_claim(id=999531)