coding assistants

A study from the MATS research program found that Claude Code and OpenAI Codex consistently misjudge how long coding tasks take, with errors of 3x to 10x, and routinely overrate the quality of their own work. Giving agents a tool to check elapsed time fixed the problem almost completely.

GitHub has published benchmark results for its Copilot agentic harness, evaluating performance across multiple tasks and over 20 different models. The company claims the framework achieves leading token efficiency while maintaining flexibility in model selection.