Unverified80% confidenceFactTime unknown
GPT-5.4及更早版本在提取文档中的数字时频繁出错，包括小数点位置偏移、千分位分隔符误读、负号遗漏等问题
1
Sources
80%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA 2023 study found that GPT-4 produced errors in approximately 15–20% of cases when generating code documentation.79% similarUnverifiedIn max mode, GPT-5.6's score is actually slightly lower than in ultra mode, confirming the overthinking phenomenon.73% similarUnverifiedGPT-4 in function calling mode can comply with schema constraints at nearly 100%, while less capable models may produce malformed output or missing fields.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/5892API
curl https://kongchang.com/api/v1/knowledge/claims/5892MCP
get_claim(id=5892)