US EditionPopular AIs head-to-head: OpenAI beats DeepSeek on sentence-level reasoning
- Researchers compared OpenAI's o1 and DeepSeek's R1 using a benchmark on April 17, 2025.
- AI chatbots sometimes make up citations, so the benchmark, Reasons, tested citation accuracy and reasoning.
- The Reasons benchmark evaluated the models on F-1 score and hallucination rate for generated responses.
- OpenAI's o1 scored 0.65 on F-1 with 35% hallucination; DeepSeek's R1 scored 0.35 with 85% hallucination.
- OpenAI shows an advantage, possibly from its training data, though users should still verify AI-generated citations.
6 Articles
6 Articles
TechXplore
Popular AIs head-to-head: OpenAI beats DeepSeek on sentence-level reasoning
ChatGPT and other AI chatbots based on large language models are known to occasionally make things up, including scientific and legal citations. It turns out that measuring how accurate an AI model's citations are is a good way of assessing the model's reasoning abilities.
Here's Where OpenAI Beats DeepSeek
ChatGPT and other artificial intelligence chatbots based on large language models are known to occasionally make things up, including scientific and legal citations. It turns out that measuring how accurate an AI model’s citations are is a good way of assessing the model’s reasoning abilities. An AI model “reasons” by breaking down a query into steps and working through them in order. Think of how you learned to solve math word problems in schoo…
OpenAI beats DeepSeek on sentence-level reasoning - Tech and Science Post
ChatGPT and other AI chatbots based on large language models are known to occasionally make things up, including scientific and legal citations. It turns out that measuring how accurate an AI model’s citations are is a good way of assessing the model’s reasoning abilities. An AI model “reasons” by breaking down a query into steps and working through them in order. Think of how you learned to solve math word problems in school. Ideally, to genera…
Coverage Details
Bias Distribution
- 67% of the sources are Center
To view factuality data please Upgrade to Premium
Ownership
To view ownership data please Upgrade to Vantage
