To measure the success of their work, companies cite industry-standard benchmark tests whenever they release a new model. The ...

AI model makers love to flex their benchmarks scores ... scored 79.1 percent on MMLU-Pro - an enhanced version of the original MMLU test designed to test natural language understanding.

Google has launched Gemma 3, the third generation of its open-source AI models. The model is better than rivals like DeepSeek ...

Inception Labs released Mercury Coder, a new AI language model that uses diffusion techniques to generate text faster than ...