← All topics
evaluation-frameworks
Latest stories covering evaluation-frameworks, with summaries and links to related coverage.
1 stories · 1 reports · page 1 of 1
Connected topics
Senior SWE-Bench: open-source benchmark that assesses agents as senior engineers
tool
3 min read
Senior SWE-Bench evaluates AI agents using realistic, natural language tasks similar to those given to senior engineers. A validation agent employs expert-designed recipes to create behavioral tests that adapt to the submitted solutions.