Popular AIs head-to-head: OpenAI beats DeepSeek on sentence-level reasoning

Thumbnail Image

Files

PopularAIsheadtohead.pdf (488.4 KB)

Links to Files

http://theconversation.com/popular-ais-head-to-head-openai-beats-deepseek-on-sentence-level-reasoning-249109

Permanent Link

http://hdl.handle.net/11603/39077

Collections

UMBC Faculty Collection
UMBC Computer Science and Electrical Engineering Department

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0002-5411-2230

Date

2025-04-17

Type of Work

articles
Text

Department

Program

Citation of Original Publication

Manas Gaur, “Popular AIs Head-to-Head: OpenAI Beats DeepSeek on Sentence-Level Reasoning,” The Conversation, April 17, 2025, http://theconversation.com/popular-ais-head-to-head-openai-beats-deepseek-on-sentence-level-reasoning-249109.

Rights

Attribution-NoDerivatives 4.0 International

Subjects

scientific and legal citations
AI chatbots
ChatGPT
UMBC Ebiquity Research Group
large language models

Abstract

Large language model AIs can ingest long documents and answer questions about them, but a key question is how well they ‘understand’ individual sentences in the documents.