Unverified50% confidenceBenchmarkExact time
GPT-5.4 mini got 5 of the 15 EMI and tax questions wrong, while scoring perfectly on the other three groups.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/11/2026
First Seen
Valid until: 10/25/2026
Sources
Related Entities
Related Claims
UnverifiedGPT-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% similarUnverifiedGPT-5.4 was reversed by a "trusted source" on 44.7% of questions, Grok-4.20 had a reversal rate as high as 87.5%, while Gemini-3.1-Pro was nearly unaffected at just 0.6%.71% similarUnverifiedThe perplexity of the GPT series of models on Wikipedia text has decreased from approximately 29 for GPT-2 to an even lower level for GPT-4.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/996747API
curl https://kongchang.com/api/v1/knowledge/claims/996747MCP
get_claim(id=996747)