AI models are numerous and confusing to navigate, but the benchmarks used to measure their performance are also challenging.

OpenAI unveiled o3 and o4-mini, its latest AI models. Both of them have advanced image analyzation capabilities – and excel ...

Midjourney, one of the earliest AI image-generating services on the web, has released its first new AI image model in nearly ...

Meta Platforms plans to release the latest version of its large language model later this month, after delaying it at least ...

Meta Platforms on Saturday released the latest version of its large language model (LLM) Llama, called the Llama 4 Scout and ...

The Gemini 2.5 Pro "model card" lacks results for key safety evaluations. Google says a more detailed technical report will ...

OpenAI says it could adjust its AI safety policy if a rival ships a high-risk model without safeguards. Critics say it's ...

Following the recent launch of a new family of GPT-4.1 models, OpenAI released o3 and o4-mini on Wednesday, the latest ...

As for the older GPT-4 model, OpenAI plans to remove it from ChatGPT on April 30th and will replace it with GPT-4o. The Verge ...

DeepSeek-GRM models were able to outperform existing methods, achieving a competitive performance with strong public reward models.

The initial model lineup includes five base sizes: 3 billion, 8 billion, 14 billion, 32 billion, and 70 billion parameters.

is the best multimodal model in its class, beating GPT-4o and Gemini 2.0 Flash across a broad range of widely reported benchmarks, while achieving comparable results to the new DeepSeek v3 on ...