Our score, explained.

Every composite can be checked against its six published axes and our fixed weights. Three axes use formula data and three use an AI assessment with a recorded model and rubric. The ingredient evidence, score breakdown and written rationale make the result open to inspection; it is an assessment rather than clinical or wear testing.

The six axes

Segment width = each axis's share of the composite; the six weights sum to 100%.

• UV protection 25%

  A heuristic from stated SPF / PA and recorded filter properties; not a measured protection result.

  Deterministic
• Health safety 25%

  Evidence-limited ingredient screening; missing data or absorption alone does not establish harm.

  AI-judged
• Sensitivity safety 15%

  Formula-based irritation concerns from fragrance, ethanol and known sensitisers; tolerance varies.

  AI-judged
• Cosmetic elegance 15%

  Estimated wear from the formula and format; individual wear is not tested.

  AI-judged
• Filter modernity 10%

  Penalises legacy filters (octinoxate, oxybenzone); rewards photostable next-gen filters.

  Deterministic
• Environmental safety 10%

  A screening heuristic from recorded UV-filter concern flags; not a reef-safety certification.

  Deterministic

What "composite" actually means

The formula

Composite is a deterministic weighted sum:

composite = 0.25·uv + 0.10·modernity + 0.15·sensitivity + 0.10·environment + 0.15·elegance + 0.25·health

Weights are pinned in our scoring config. Changes queue a catalogue refresh; incomplete formulas wait for review. We never tweak a single product's score by hand.

Deterministic vs AI-judged

Deterministic axes are computed from structured fields in our product database and the joined UV-filter properties in our ingredient database — no model in the loop, fully reproducible. Judgement axes are scored by an AI judgement model with a structured-output rubric, and the reasoning summary sits right next to the scores so you can read exactly why a product got the number it got.

Scores come from the pipeline, not the sales team. No brand can pay to rank, and no product score is ever edited by hand. Real ones only.

What we don't do

• No paid placement. Brands and retailers cannot pay to be in or move up the rankings. Money buys nothing here.
• No editorial overrides. Scores come from the pipeline; we don't bump a favourite up or push a product we don't vibe with down.
• No invented data. If a field is unknown for a product, the page says unknown instead of making something up.
• No re-scoring on retailer change. Rankings are computed before commercial terms; new retailer listings don't shift scores.

Questions, answered

Can brands pay for placement in the rankings?

No. Brands and retailers cannot pay to be included, excluded, or moved. Scores are produced by a pipeline from formulation data; affiliate commercial terms are applied after scoring and have zero effect on rank.

How is the AI-judged part of the score kept honest?

The three judgement axes use a versioned rubric and recorded model. Each response must include valid scores and a written rationale. Tests check formula readiness, response validation, cache freshness and composite arithmetic. Model or rubric changes queue a refresh; incomplete ingredient evidence waits for review. No individual product score is edited by hand.

Why did a product’s score change?

Scores refresh when formula evidence, relevant ingredient properties, the rubric or the scoring model changes. The model and rubric are recorded with each score. Incomplete ingredient lists wait for review. New retailer listings, prices and affiliate terms do not change a formula score.

Do affiliate links affect the rankings?

No. Buy buttons route through retailer affiliate programs and we earn a commission on qualifying purchases — that revenue keeps the catalogue free. Rankings are computed before commercial terms, and a product with no affiliate relationship ranks exactly as its formula scores. Disclosure appears on every page with affiliate links, in EN / JP / KR.

How fresh is the data?

The catalogue is refreshed regularly: availability is re-checked (products no longer purchasable are removed, not just hidden), and regulatory watchers monitor the JP / KR / EU / US allowed-filter lists. Every refresh lands as a reviewed change before it ships.

Where does the ingredient data come from?

INCI lists are scraped from retailer listings and resolved against regulatory sources: the FDA OTC monograph (US), MHLW quasi-drug list (Japan), MFDS list (Korea), and Annex VI of EC Regulation 1223/2009 (EU). Unresolvable names are queued for human review instead of being guessed.

Sources & receipts

• FDA OTC sunscreen monograph (United States)
• MHLW quasi-drug ingredient list (Japan)
• MFDS approved-filter list (Korea)
• Annex VI, EC Regulation 1223/2009 (EU)

See the rankings →