Zenaique

Complete: Cohen's kappa >___ is 'substantial' agreement; >___ is 'almost perfect' agreement

Fill in blank·Medium·4.0 · 0·~1 min·Asked atStability AiVellum·Relevant atAnthropic
Attempt it
When calibrating an LLM judge against human raters, Cohen's kappa > is considered 'substantial' agreement, and kappa > is considered 'almost perfect' agreement. Below , the judge is likely too unreliable for production use.
TL;DR

Cohen's kappa above 0.6 signals substantial judge-human agreement; above 0.8 is almost perfect. Below 0.6 the judge is usually too unreliable to ship.

Memory aid
Sign in to see the mnemonic that makes this stick.
Easy to grasp

Imagine two teachers grading the same stack of essays pass or fail. If they agree on 90 percent of essays, that sounds great. But what if both just guess and most essays happen to pass? They would still agree most of the time by pure luck. Cohen's kappa is a fairness-adjusted agreement score. It asks how much two graders agree BEYOND what random guessing would give. A kappa of 0 means they agree no better than coin flips. A kappa of 1 means they agree perfectly. When you swap one teacher for an LLM judge, you want kappa above 0.6 before you trust it, and above 0.8 before you call it as good as a human.

Concept explanation~2 min read

Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.

Cohen's kappa is the workhorse metric for deciding whether an LLM judge can stand in for a human grader. The setup is simple: take a held-out set of outputs, have both a human and the judge label each one, and ask how much they agree. The trap is that the obvious metric, raw percent agreement, is badly inflated whenever one label dominates the set.

This question fixes two named thresholds from the 1977 Landis and Koch paper: kappa above 0.6 is substantial agreement, the usual minimum for trusting a judge in production, and kappa above 0.8 is almost perfect, the gold standard where the judge is effectively a second human. The deep dive derives the formula, explains observed and chance agreement, walks the interpretation bands, and covers the failure modes that bite at calibration time.

Why raw percent agreement fails

Suppose a judge and a human both label 200 model outputs as acceptable or not acceptable, and 190 of the outputs really are acceptable. If the judge just labels everything acceptable, it agrees with the human on 190 out of 200, a tidy-looking 95 percent. But the judge has learned nothing; it is exploiting the skew.

This is why raw percent agreement is the wrong metric. It rewards a constant guesser on any imbalanced set, and most real eval sets are imbalanced because good models are usually right. You need a metric that asks a sharper question: how much do the two raters agree beyond what they would hit by chance given how often each one uses each label?

That is exactly what Cohen's kappa was designed to answer. It strips out the chance-level agreement and reports only the surplus, which is why a 95 percent raw agreement can correspond to a kappa near zero.

The formula: observed minus chance, normalised
The interpretation bands
The kappa paradox and per-class reading
Variants and the calibration loop
Sign in to unlock the full deep dive.

Situations where this technique stops working.

Sign in to see when this approach fails.

2–4 min · Everything important, quickly.

Sign in to see the quick scan of the deep dive.
Kappa rangeLandis-Koch labelProduction read
< 0.0Poor (worse than chance)Broken judge or rubric
0.0 to 0.20SlightUnusable
0.21 to 0.40FairWeak, diagnose by class
0.41 to 0.60ModerateCoarse pre-filter only
0.61 to 0.80SubstantialMinimum production bar
0.81 to 1.00Almost perfectGold standard, human-equivalent

Real products, models, and research that use this idea.

  • RAGAS calibration guides recommend measuring judge-human kappa on a labelled holdout before trusting faithfulness scores in production.
  • Anthropic and OpenAI eval cookbooks report inter-rater agreement when validating LLM-judge prompts against human annotators.
Sign in to see more production examples.

What an interviewer would ask next. Try answering before peeking at the approach.

QWhy can a judge post 95 percent accuracy yet score a kappa near zero?
A

Walk through the kappa paradox: when one class dominates, the chance term p_e approaches the observed agreement, so the numerator p_o minus p_e collapses toward zero even though raw accuracy looks excellent.

2 more follow-ups an interviewer would ask next. Sign in to reveal them.

Red flags & common mistakes

The phrases that signal junior thinking. Click to expand.

Most common mistake

Reporting raw percent agreement instead of kappa. On a skewed label set two raters can agree 90 percent of the time while their chance-adjusted agreement is near zero.

Sign in to see all red flags and common mistakes.

60 second bullets to scan on the way to the call.

  • The kappa formula and what observed versus chance agreement mean

  • Why raw percent agreement misleads on skewed label sets

Sign in to unlock the revision sheet.

Primary sources. Browse if you want the original framing.

Similar questions

Same topic, related formats. Practice these next.

4 curated
Next question
Which metric best measures whether a RAG answer is grounded in the retrieved context?
MCQ·Medium