Compute the RRF score for a candidate ranked 3 by dense and 5 by BM25 · Zenaique

Attempt it

A candidate document is ranked at position 3 by the dense retriever and position 5 by BM25. Using Reciprocal Rank Fusion with the standard k=60, compute the candidate's RRF score. Express as a decimal rounded to 5 decimal places.

Quick reference

TL;DR

Plug rank 3 and rank 5 with k=60 into 1/(k+rank); sum 1/63 + 1/65 ≈ 0.01587 + 0.01538 ≈ 0.03126.

Memory aid

Sign in for the mnemonic that makes this stick. See Pro pricing.

Easy to grasp

Imagine two judges each list contestants in order of preference. A contestant comes third on one list and fifth on the other. To combine the lists fairly, each judge gives that contestant a small bonus. The bonus is one divided by a smoothing number plus the position. The smoothing number is 60 by convention, so the bonuses are about one over sixty-three and one over sixty-five. Add the two bonuses. You get about three hundredths. Notice how close the two bonuses are even though the positions differ by two slots. That closeness is the whole point: the smoothing number 60 keeps the early ranks from dwarfing each other.

Key concepts

Detailed answer & concept explanation

~4 min read

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

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

Sign in for 5 free unlocks/day or go Pro for unlimited. See Pro pricing.

Quick scan · 2–4 min

Everything important, quickly.

60s: write the formula, plug in ranks 3 and 5 with k=60, compute 1/63 + 1/65 ≈ 0.03126, then explain why the two contributions are so close (k=60 smoothing) and what that buys you in hybrid retrieval.

Real-world examples

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

Elastic's RRF retriever in 2026 uses exactly this `1/(k+rank)` formula with `k=60` as the default, and exposes the per-candidate contributions for debugging in the `_explanation` API.
Vespa's hybrid retrieval tutorial walks through the same arithmetic on a worked example, showing how `k=60` flattens rank differences between BM25 and dense retrievers.
OpenSearch's neural search plugin documents the identical formula in its RRF processor, with `k=60` as the documented default value.
LangChain's EnsembleRetriever computes RRF scores under the hood when combining BM25 and dense retrievers, defaulting to `k=60` and exposing the fused score for inspection.

Interviewer follow-ups

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

QHow would the score change if `k` were set to 0 instead of 60?

Sign in or go Pro to see the approach for this follow-up.

QIf a third retriever ranks the same document at position 10, what is the new RRF score?

Sign in or go Pro to see the approach for this follow-up.

QHow would you handle a candidate that appears in only one retriever's top-K list?

Sign in or go Pro to see the approach for this follow-up.

Don't say this

Red flags and common mistakes that signal junior thinking. Click to expand.

Most common mistake

Forgetting the smoothing constant in the denominator and computing one over 3 plus one over 5 instead. That gives 0.533, an order of magnitude wrong, and ignores the smoothing role of the constant.

Sign in or go Pro to see all red flags and common mistakes. See Pro pricing.

60-second cheat sheet

The night-before-the-interview bullets. Scan these on the way to the call.

Sign in for 5 unlocks/day or go Pro for unlimited revision sheets. See Pro pricing.

References

Primary sources. Skim if you want the original framing.