Researchers used questions from the NPR Sunday Puzzle challenge to build a benchmark to test AI 'reasoning' models.

The ASTRA Benchmark consists of multi-file, project-based problems designed to mimic real-world coding tasks. The intent of the HackerRank ASTRA Benchmark is to determine the correctness and ...

AMD claims its RX 7900 XTX runs DeepSeek R1 faster than Nvidia’s RTX 4090, 4080 Super, but Nvidia says the opposite is true.

According to a report by the International AI Benchmark Consortium, DeepSeek outperformed its American counterparts in language processing and data analysis by 15 percent. Its multilingual ...

and startup Cursor created an AI benchmark using riddles from Sunday Puzzle episodes. The team says their test uncovered surprising insights, like that reasoning models — OpenAI's o1 ...

It's not perfect quite yet, it's worth pointing out. Hugging Face's Open Deep Research scored a 55.15 percent accuracy on a benchmark called General AI Assistants, while OpenAI's version scored 67.36, ...

Hugging Face's Open Deep Research scored a 55.15 percent accuracy on a benchmark called General AI Assistants, while OpenAI's version scored 67.36, leaving some room for improvement. (OpenAI's ...