Individual skill
llm-benchmarks
Use LLM benchmarks wisely — what major benchmarks measure, their limits, contamination risks, and how to interpret scores. Use when evaluating models or reading benchmark claims critically.
skills/llm-benchmarks/SKILL.md
Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Not checked yet
- Last checked
- Nov 8, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 54
- Repository last updated
- Oct 10, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai-agents Repository topic
- ai-agents-automation Repository topic
- ai-skills Repository topic
- awesome Repository topic
- awesome-list Repository topic
- chatgpt Repository topic
- claude-skills Repository topic
- meta-ai Repository topic
- muse-ai Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 3,962 bytes
Read excerpt
# LLM Benchmarks — A Critical Guide
Benchmarks are the industry's shared scoreboard — and widely misread. This skill covers what the
major benchmark families actually measure, why scores mislead, and how to use benchmarks without
fooling yourself.
## Overview
Benchmark families: knowledge (multi-choice QA across subjects), reasoning (math, logic, code —
often with verifiable answers), instruction-following (did it do what was asked, how asked),
long-context (retrieval and reasoning over long inputs), multilingual (quality beyond English), and
agentic (multi-step tool use). Each measures something real and something narrow. The critical
skills: knowing which family matches your use case, discounting for contamination (benchmark
questions in training data), and never mistaking a leaderboard for a buying decision.