Orchestra-Research verified
Building open-source Claude skills. 1 skills with 4,668 total stars.
Contributed
1
Total Stars
4.7k
Total Forks
380
Avg Stars
4668
Showing 1 skills
evaluating-code-models
star 4.7k
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when ben...
tools debugging
3 months ago