What is BM25? A Plain English Guide

Search looks simple from the outside. You type a few words into a documentation search box, a product search box, or a small site search, and the system returns a list of pages.

Behind that list is a ranking problem. The search engine may know about hundreds or thousands of pages, but it still has to decide which matches should come first.

For example, the user may search:

pricing page

Some pages are clearly about pricing, some mention pricing once in a footer or changelog entry, and many pages have nothing to do with pricing. BM25 is one way for the search engine to sort those matches.

What is BM25?

BM25 is a ranking function for keyword search.

It gives each document a score based on how well that document matches the search query. Higher score, higher chance of appearing near the top.

Keyword search is also called lexical search. It works with matching words . If the query contains pricing, the search engine first looks for documents that contain pricing.

BM stands for Best Matching, and the 25 is a version number from a family of ranking functions. The name sounds more mysterious than the idea behind it.

BM25 looks at four main things:

• Which query words appear in the document
• How many times those words appear
• How rare those words are across all documents
• How long or short the document is

BM25 is still counting words, but it is not blind word counting. It weighs repetition, rarity, and length before deciding what should rank.

BM25 is useful when exact words matter , which happens a lot in product docs, support articles, API docs, error messages, settings pages, and technical search.

A simple matching example

The user searches:

pricing page

We have two documents.

Document A:

Pricing page for teams

Document B:

Billing and pricing

Document A has both words, pricing and page. Document B only has pricing.

A very simple search system can say:

Document A = 2 matchesDocument B = 1 match

That is the first idea behind keyword search: if a document contains more words from the query, it is often a better match. But this simple method breaks quickly.

Repeating a word should not win forever

Search only for:

pricing

Document A:

Our pricing page explains all plans.

Document B:

Pricing pricing pricing pricing pricing pricing pricing.

If we only count word frequency, Document B looks much better because pricing appears many times.

The problem is easy to see. Seven mentions of pricing are not seven times more useful than one mention, because after a point repetition stops giving new information.

BM25 handles this using term frequency saturation The first few mentions matter most. After that, repetition starts to flatten out. :

0 mentions   = no evidence1 mention    = useful evidence2-3 mentions = stronger evidence20 mentions  = not 20x stronger

Repetition still helps, but it does not help forever. A page should not win only because it repeats the same word again and again.

Rare words should count more

Take another query:

configure sso

The word configure may appear on many documentation pages, while sso may appear only on a few. If a document contains sso, that is a stronger signal than if it only contains configure.

BM25 uses this idea with IDF, which means inverse document frequency.

In simple words:

• If a word appears in many documents, it is less special.
• If a word appears in fewer documents, it is more special.

A user searches:

stripe webhook retry

On the website:

stripe  appears on 40 pageswebhook appears on 15 pagesretry   appears on 120 pages

Here, webhook is the rarest word, so it gives a stronger clue. stripe is also useful. retry is still useful, but it appears in more places, so it is less specific.

This depends on the website. On a developer website, api may appear everywhere; on another website, api may be rare.

How does the search engine know these counts?

BM25 does not read every page from scratch when a user searches. The search engine prepares this information before the query comes in.

When pages are crawled or indexed, the search engine builds an inverted index. An inverted index is a map from words to documents.

It looks like this:

stripe  -> doc1, doc7, doc9, doc20, ...webhook -> doc3, doc7, doc12, ...retry   -> doc2, doc3, doc7, doc8, doc21, ...

With this index, the search engine can know:

stripe  appears in 40 documentswebhook appears in 15 documentsretry   appears in 120 documents

That count is called document frequency Document frequency means: how many documents contain this word at least once. .

The search engine also stores other information:

• How many times each word appears in each document
• How long each document is
• What the average document length is

At search time, the engine can use these stored numbers to calculate the BM25 score.

The search engine does the slow remembering before the query arrives. At search time, BM25 uses that stored index instead of rereading the whole site.

Long documents need adjustment

Search for:

billing

Document A is short:

BillingManage billing settings for your workspace.

Document B is very long:

... 8,000 words ...billing appears once somewhere inside it...

Both documents contain billing once, but they should not get the same score. In Document A, billing is probably the main topic; in Document B, it may only be a small mention.

BM25 handles this using document length normalization. A match in a short, focused document can be stronger than the same match inside a very long document.

This does not mean long documents are bad. A long guide can still be the best result. BM25 is only trying to avoid giving long documents an unfair advantage because they have more words and more chances to match something.

So far, BM25 has made four corrections to simple word counting.

• It gives more credit when more query words match.
• It lets repetition help, but only up to a point.
• It gives more weight to rare words.
• It adjusts the score when the same match appears inside a very long document.

BM25 is still counting words, but it is counting them with useful corrections.

BM25 in real search systems

In a real website, search usually does not treat the whole page as one big block of text. A page has many fields:

• Title
• URL
• Headings
• Meta description
• Body text
• Anchor text
• Content chunks

A match in the title is usually more important than a match deep inside the body. If the user searches:

api keys

A page titled API Keys should usually rank higher than a long guide that mentions API keys once in the middle.

Many systems solve this by scoring each field separately:

final keyword score =  title BM25 score x title weight+ heading BM25 score x heading weight+ body BM25 score x body weight+ URL BM25 score x URL weight

Clear titles, headings, and URLs help both the reader and the search engine.

Search systems also prepare text before ranking it. They may lowercase words, remove punctuation, handle plurals, remove stop words, or tolerate small typos:

API keysapi-keyapi key

After tokenization and normalization, these become easier to compare.

Modern search systems may also split long pages into chunks, because one long page can talk about many topics. A chunk can tell the search engine, “this section is about API keys,” instead of only saying, “this whole page contains API keys somewhere.”

The BM25 formula

The formula is less scary if we connect it back to the ideas above.

For the query:

reset api key

BM25 scores each query word and adds the scores:

score("reset") + score("api") + score("key")

A common BM25 formula looks like this:

score(D, Q) = sum over query terms:IDF(q) * ((f(q, D) * (k1 + 1)) /(f(q, D) + k1 * (1 - b + b * |D| / avgdl)))

The symbols mean:

D      = the documentQ      = the queryq      = one query wordf(q,D) = how many times q appears in DIDF(q) = how rare q is across the collection|D|    = document lengthavgdl  = average document lengthk1     = how much repetition helpsb      = how much document length matters

The two knobs to remember are k1 and b.

k1 controls repetition. If k1 is low, extra mentions stop helping quickly; if it is high, repeated words keep adding score for longer.

b controls document length. If b is 0, document length does not matter; if it is 1, document length matters a lot. Many systems use a value somewhere in the middle.

BM25 vs TF-IDF

BM25 is related to TF-IDF. TF-IDF means:

term frequency x inverse document frequency

It uses two ideas:

• Words that appear more in a document can matter more.
• Words that appear in fewer documents can matter more.

BM25 keeps those ideas, but adds two controls that matter in real search:

• Repeated words do not keep increasing the score forever.
• Long documents are adjusted so they do not win only because they contain more words.

That is why BM25 is usually a better baseline than plain TF-IDF for website search, documentation search, and product search.

Where BM25 works well

BM25 works well when the user searches for words that actually appear in the content:

reset api keybilling invoice downloadapi_key_invalidSOC2

These are good BM25 queries because the exact words matter. That makes BM25 useful for:

• Product names
• Feature names
• API names
• Error codes
• SKUs
• Settings pages
• Technical terms
• Support articles

If someone searches for api_key_invalid, we want the result that contains api_key_invalid. Exact matching should have real weight here.

Where BM25 struggles

BM25 struggles when the user and the document use different words for the same idea. The user may search:

change password

while the page says:

Update your credentials

A human can understand that these are related, but BM25 may not, because change does not match update, and password does not match credentials.

Another query:

remove teammate

may need this page:

Delete a workspace member

The meaning is close, but the words are different. BM25 can still do well if the page includes alternate wording, synonyms, headings, or anchor text; the core ranking function itself is lexical, so it rewards word overlap.

This is the main limit of lexical ranking: if the useful page says the idea with different words, BM25 may need help from synonyms, rewritten headings, or another retrieval method.

Other ranking methods

BM25 is one ranking method in the larger family of lexical and statistical search methods.

TF-IDF is the closest comparison because it is simpler and helps explain why BM25 adds saturation and document length normalization.

Boolean retrieval is older and more strict. It uses logic like:

api AND keybilling OR invoiceerror NOT deprecated

With Boolean retrieval, a document either matches or it does not. That is useful for filters and exact control, but it is not always enough for ranking.

Language models for information retrieval ask a different question: how likely is this document to produce this query?

DFR, or Divergence From Randomness, asks whether a term appears more often than we would expect by chance.

BM25F is a field-aware version of BM25 for documents with fields like title, body, anchor text, and metadata. BM25+ is another variant that changes how long documents are treated in some cases.

Learning to Rank goes broader. Instead of using one fixed formula, it learns how to combine many signals: BM25 score, title match, freshness, click data, phrase match, document type, and more. Even there, BM25 is often still one of the useful signals.

FAQ

What does BM25 stand for?

BM stands for Best Matching. BM25 is one version from the Best Matching family of ranking functions.

What is 25 in BM25?

The 25 is a version number. It does not mean BM25 has 25 steps or 25 inputs.

Is BM25 just TF-IDF?

No. BM25 is related to TF-IDF, but it is not the same. Both use term frequency and inverse document frequency. BM25 also adds term frequency saturation and document length normalization.

What is BM25 used for?

BM25 is used to rank keyword search results in full-text search, documentation search, product search, support search, and technical search.

What is BM25 in RAG?

In RAG systems, BM25 can retrieve documents or chunks that contain exact query terms before the results are sent to a language model. This helps with names, IDs, error codes, and technical terms.

Does BM25 understand meaning?

Not really. BM25 mostly works with word overlap and term statistics, so it may miss two phrases that mean the same thing but use different words.

What are k1 and b?

k1 and b are tuning parameters. k1 controls how much repeated words help, and b controls how much document length matters.

Summary

BM25 is a practical way to rank keyword search results. It looks at:

• Which query words match
• How often they appear
• How rare they are
• How long the document is

BM25 is not trying to understand language like a person. It is trying to rank exact word matches in a smarter way than simple word counting.

BM25 is still useful because exact words still matter . Product names, API names, error codes, settings pages, and technical concepts often need exact matching.

Once you understand BM25, many search results start to look less mysterious: the engine is asking which words matched, how strong those matches are, and whether the document looks focused enough to deserve the top spot.