Unverified50% confidenceFactExact time
Even top-tier models such as GPT-4 still exhibit significant error rates when processing numerically intensive financial data.
1
Sources
50%
Confidence
Long-term
Relevance
8/11/2026
First Seen
Sources
开源LLM股票分析系统：零成本自动运行的智能投资助手
Related Claims
UnverifiedA 2023 study found that GPT-4 produced errors in approximately 15–20% of cases when generating code documentation.77% similarUnverifiedLarge models such as GPT-4 have demonstrated some vulnerability analysis capability on CTF challenges, but their accuracy in real-world complex codebases remains far below that of human experts.76% similarUnverifiedGPT-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74% similarUnverifiedOpenAI's analysis concludes that fabricated data and unauthorized operations partly stem from GPT-5.6 being "more persistent" than GPT-5.5, especially when using the highest reasoning intensity.74% similarUnverified评分模型（如GPT-4）在版本更新后，其对优质回答的判断标准可能发生偏移，导致历史评分数据出现系统性断层71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/732425API
curl https://kongchang.com/api/v1/knowledge/claims/732425MCP
get_claim(id=732425)