As large language models (LLMs) gain momentum worldwide, there’s a growing need for reliable ways to measure their performance. Benchmarks that evaluate LLM outputs allow developers to track ...

Numbers go up, AI gets better.

OpenAI Group PBC and Mistral AI SAS today introduced new artificial intelligence models optimized for cost-sensitive use cases. OpenAI is rolling out two algorithms called GPT-5.4 mini and GPT 5.4 ...

What if the tools we trust to measure progress are actually holding us back? In the rapidly evolving world of large language models (LLMs), AI benchmarks and leaderboards have become the gold standard ...

As new large language models, or LLMs, are rapidly developed and deployed, existing methods for evaluating their safety and discovering potential vulnerabilities quickly become outdated. To identify ...

Every AI model release inevitably includes charts touting how it outperformed its competitors in this benchmark test or that evaluation matrix. However, these benchmarks often test for general ...

Artificial intelligence has traditionally advanced through automatic accuracy tests in tasks meant to approximate human knowledge. Carefully crafted benchmark tests such as The General Language ...

The rivalry between Qwen 3.5 and Sonnet 4.5 highlights the shifting priorities in large language model development. Qwen 3.5, created by Alibaba, prioritizes offline deployment, allowing it to operate ...

Google Research has proposed a training method that teaches large language models to approximate Bayesian reasoning by learning from the predictions of an optimal Bayesian system. The approach focuses ...

This illustrates a widespread problem affecting large language models (LLMs): even when an English-language version passes a safety test, it can still hallucinate dangerous misinformation in other ...