home/categories/machine-learning/orchestra-research-ai-research-skills-11-evaluation-nemo-evaluator-skill-md
machine-learningdata-ai
nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
maintainer
Orchestra-Research
更新于 1/15/2026
星标
6563
分支
515
quick start
Installation and usage
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
安装
$ install --globalskills.sh
使用
安装后，您可以通过在终端运行以下命令来使用此技能：
skills use nemo-evaluator-sdk