← Back to events

ActiveAI

Terminal-Bench-Science: Evaluating AI agents on scientific research workflows

Photo: Hacker News

Terminal-Bench-Science Evaluating

What happened

A benchmark for evaluating AI agents on research workflows across scientific domains

Summary assembled by rule from the sources below

Why it's spreading

DiscussionCommunity discussion only (1 posts), not yet corroborated

Sources

Community

Terminal-Bench-Science: Evaluating AI agents on scientific research workflowsHacker News1 h ago