AI Agent Skills

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities…

Build and govern a 50-200 example domain-specific held-out benchmark sampled from real traffic. Distinct from public benchmarks (MMLU/HumanEval/GSM8K via lm-evaluation-h…