Jesse Dodge

A comprehensive benchmarking tool to assess AI model efficiency in real-world scenarios.

2025-10-18T16:52:24+00:00 ― 7 min read

A new dataset aims to enhance language model research and promote transparency.

2025-09-12T19:06:54+00:00 ― 6 min read

A new open language model for research and innovation in natural language processing.

2025-09-12T09:14:24+00:00 ― 6 min read

Learn how task scaling laws and model ladders improve AI predictions.

2025-04-11T19:54:18+00:00 ― 6 min read