#10
Terminal-Bench-Science: Evaluating AI agents on scientific research workflows
Matt_d's Terminal-Bench-Science, a benchmark for evaluating AI agents on scientific research workflows, scraped into the top ten at 74 points and 23 comments, early traction for what could become a standard evaluation suite.
Comments on "Terminal-Bench-Science: Evaluating AI agents on scientific research workflows"
Have a take on this ranking?
Comments are how the argument actually happens here. Posting one needs a free account — it takes about a minute.
No comments yet.
The first comment sets the terms of the argument.