Large language models (LLMs), artificial intelligence (AI) systems that can process human language and generate texts in ...

Researchers debut "Humanity’s Last Exam," a benchmark of 2,500 expert-level questions that current AI models are failing.

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 ...

MLCommons today released AILuminate, a new benchmark test for evaluating the safety of large language models. Launched in 2020, MLCommons is an industry consortium backed by several dozen tech firms.

This study introduces MathEval, a comprehensive benchmarking framework designed to systematically evaluate the mathematical reasoning capabilities of large language models (LLMs). Addressing key ...

A comprehensive search was conducted in PubMed, Web of Science, and OpenAlex for literature published between December 1, 2022, and December 31, 2024. Studies were included if they explicitly ...

The company said the model is optimised for “efficient thinking”, delivering stronger responses while using fewer tokens — a key factor in reducing inference costs in production environments.

The new Mercury 2 AI model uses diffusion reasoning to generate 1,000 tokens per second; it runs about 5x faster than Haiku, speed limits are ...

A duplex speech-to-speech model changes the premise: The intelligence layer consumes audio and produces audio directly. The model can attend to what was said and how it was said—content and delivery ...

Explore how vision-language-action models like Helix, GR00T N1, and RT-1 are enabling robots to understand instructions and act autonomously.