Hong Kong, China - February 26, 2026 - Etna Capital Management today released a new research framework, “Beyond ...

To fix the way we test and measure models, AI is learning tricks from social science. It’s not easy being one of Silicon Valley’s favorite benchmarks. SWE-Bench (pronounced “swee bench”) launched in ...

Backboard.io announced it has achieved state-of-the-art performance across both leading AI memory benchmarks, a first ...

Early benchmarks suggest Qualcomm’s chip in the Galaxy S26 Ultra may outpace the Exynos 2600 in the standard model.

3DMark and Superposition are considered two of the most reliable GPU benchmarking tools out there. Cinebench 2024 is also a ...

On Tuesday, startup Anthropic released a family of generative AI models that it claims achieve best-in-class performance. Just a few days later, rival Inflection AI unveiled a model that it asserts ...

The first smartphones powered by Qualcomm’s cutting edge Snapdragon 888 mobile application processor aren’t set to arrive until the new year, but we now have a better picture of how these phones might ...

XAI Grok 4 Benchmarks are showing it is the leading model. Humanity Last Exam at 35 and 45 for reasoning is a big improvement from about 21 for other top models. If these leaked Grok 4 benchmarks are ...

As large language models (LLMs) continue to improve at coding, the benchmarks used to evaluate their performance are steadily becoming less useful. That's because though many LLMs have similar high ...

How do you measure artificial intelligence? Since the idea first took hold in the 1950s, researchers have gauged the progress of AI by establishing benchmarks, such as the ability to recognize images, ...