Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
安装
npx skills add davila7/claude-code-templates --skill evaluating-llms-harnessnpx skills add davila7/claude-code-templates --skill evaluating-llms-harness -a claude-code -gnpx skills add davila7/claude-code-templates --skill evaluating-llms-harness -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/evaluation-lm-evaluation-harnessgh skill install davila7/claude-code-templates evaluating-llms-harnessgit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/evaluation-lm-evaluation-harness ~/.claude/skills/evaluating-llms-harness # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/evaluation-lm-evaluation-harness ~/.agents/skills/evaluating-llms-harness # Codex, Cursor, Gemini CLI, Copilot, OpenCode