30,924 Steam games · rated by AI

Do great games get ignored on Steam?

I had an AI rate the store page of 30,924 Steam games: capsule art, screenshots and description. Then I compared that score with how many players each game got.

Short answer: almost never.The ignored games are overwhelmingly the ones with weak pages.

Better store pages get more reviews

Every dot is one game. Up means a better page score from Jev. Right means more Steam reviews, each step ten times more. Hover or tap a dot to see the game.

ignored (under 10 reviews)10 to 999 reviewshit (1,000+)typical page score at each levelpage score 75

The sample includes more successful games than Steam has, so that every level is covered. The charts below are weighted back to represent all 85,152 games.

Ignored games have the weakest store pages

How page scores are spread out within each group. The ignored games sit to the left, the hits to the right.

ignored10–999 reviewshits

A top-5% page is 14x more likely to be a hit

Games grouped by where their page score ranks on Steam. For each group, the red bar is the share that got ignored and the green bar the share that became a hit with 1,000+ reviews.

The great-page games that got ignored did almost no distribution: 1 in 34 had a video by another creator

A few games with a page score of 75 or more still got ignored. I took all 34 of them and 34 games with pages just as good that took off, and had a second AI (Claude Haiku) search the web for each one: official site, social accounts, press, videos by other creators, community threads. Store and database pages don't count. Hover a cover for what it found; click to open the game.

What the search found for the 34 ignored games

Ignored games link fewer social accounts: 46% link none, and only 16% link four or more (hits: 34%)

All 1,762 games with a page score of 75 or more, weighted to Steam, split by outcome. The count is what each store page itself lists.

Great pages that link 4+ social accounts become hits 66% of the time, vs 50% with none

One caveat: part of the presence of the games that took off came after their success — popular games get videos and articles written about them, so this cannot show that marketing causes success. The other side is clear, though: almost none of the ignored games got covered before, during or after launch.

Try it yourself: can you tell an ignored game from a hit by its page?

24 random games from each level, drawn in their real proportions. A red outline means the game got ignored. Click any game to open it on Steam.

Once you know the page score, what else matters?

A machine-learning model predicted every game's reviews from its page (Jev's ratings, in blue) and from facts about the game (in white). These are its Shapley values: each dot is a game, and the further right it sits, the more that feature pushed its reviews up. Red dots are games with a high value for that feature.

Shapley values of the reviews model

Who is behind the game matters most: how many reviews the developer's and publisher's other games have. Right after come the page signals: whether players would click it, capsule art quality, and whether it looks trustworthy. Together, the page ratings make up about a third of what the model uses.

The 46 questions Jev answered about every page

Every page got exactly these questions, word for word. header is the capsule image, screenshots the four screenshots, short_description and description the store texts. The page score is the average of the 29 ratings marked "counts toward the page score". Jev never saw any review count.

Show the 46 questions

Every request also started with this instruction:

This is the Steam store page of a video game. header is the capsule image shown in store lists, screenshots are its store screenshots, short_description and description are its store texts. Judge presentation craft only. Ignore awards, press quotes, review scores and sales claims; they must not raise any rating.

The capsule image 11

  1. Rate the overall quality of header as capsule art for a game store.

    rating · counts toward the page score: Amateur or placeholder → Weak, clearly low effort → Competent but generic → Good, professional → Top-tier key art
  2. Is header just an in-game screenshot with a title on top, rather than dedicated key art?

    yes / no
  3. Rate the color and contrast of header.

    rating · counts toward the page score: Dull, muddy or garish → Weak → Acceptable → Appealing → Striking
  4. Rate the typography / logo design of the title in header.

    rating · counts toward the page score: No title or default font → Basic → Decent → Designed logo → Iconic, professional logo
  5. Among dozens of capsules in a Steam list, how much would header stand out?

    rating · counts toward the page score: Invisible → Barely → Somewhat → Clearly → Immediately grabs attention
  6. What is the art style of header?

    pick one: Pixel art · 3D render · Hand-drawn or painted illustration · Anime / manga style · Photograph or live action · Mostly text or logo on a plain background · Other
  7. How readable would the title in header be when shown as a small thumbnail (about 230x90 px)?

    rating · counts toward the page score: Unreadable or no title → Hard to read → Readable with effort → Readable → Instantly readable
  8. How quickly can you tell the genre of the game from header alone?

    rating · counts toward the page score: Impossible to tell → Hard to tell → With some effort → Quickly → Instantly
  9. Does header prominently feature a character or creature?

    yes / no
  10. What is the dominant mood of header?

    pick one: Dark or horror · Epic or heroic · Cute or cozy · Bright and fun · Calm or melancholic · Neutral, no clear mood
  11. How well does header match the game actually shown in screenshots?

    rating · counts toward the page score: Misleading, a different game → Loosely → Somewhat → Well → Perfectly

The screenshots 11

  1. Rate the visual quality and polish of the game shown in screenshots.

    rating · counts toward the page score: Very crude → Rough → Average → Polished → Stunning
  2. Do screenshots mostly show actual gameplay (not menus, concept art, logos or text slides)?

    yes / no
  3. How varied are screenshots (different scenes, mechanics, situations)?

    rating · counts toward the page score: All nearly identical → Little variety → Some variety → Varied → Very varied, shows the whole game
  4. From screenshots alone, how well can you understand what the player actually does?

    rating · counts toward the page score: No idea → Vague → Roughly → Clearly → Instantly obvious
  5. How clean and readable is the in-game UI in screenshots?

    rating · counts toward the page score: Unreadable or broken → Messy → Acceptable → Clean → Excellent
  6. How consistent is the art direction across screenshots?

    rating · counts toward the page score: Mismatched assets → Inconsistent → Mostly consistent → Consistent → Strong unified style
  7. What production scale do screenshots suggest?

    pick one: Hobbyist or student project · Low-budget indie · Polished indie · AA studio · AAA studio
  8. What kind of graphics does the game in screenshots have?

    pick one: Pixel art · 2D illustrated / hand-drawn · Low-poly 3D · Stylized 3D · Realistic 3D · Mostly text or UI · Visual novel
  9. How original are the art assets in screenshots?

    rating · counts toward the page score: Obvious generic store-bought assets → Mostly generic → Mixed → Mostly custom → Fully custom and distinctive
  10. How technically clean are the images in screenshots (resolution, no stretching, no compression artifacts)?

    rating · counts toward the page score: Very low resolution or broken → Poor → Acceptable → Clean → Crisp and high quality
  11. Do screenshots show placeholder, unfinished or debug graphics?

    yes / no

The description 13

  1. How well does the start of short_description and description hook the reader?

    rating · counts toward the page score: No hook, confusing → Weak → Okay → Strong → Irresistible
  2. After reading short_description and description, how clear is what you actually do in the game?

    rating · counts toward the page score: No idea → Vague → Roughly clear → Clear → Crystal clear
  3. How clear and distinctive is what makes this game different from others, per description?

    rating · counts toward the page score: Nothing distinctive → Generic → Somewhat distinctive → Clear unique angle → Very original and well sold
  4. Rate the writing quality of description (grammar, fluency, concision).

    rating · counts toward the page score: Broken, many errors → Poor → Acceptable → Good → Professional copywriting
  5. Rate the structure and formatting of description (headings, short paragraphs, lists).

    rating · counts toward the page score: Wall of text or almost empty → Poor → Acceptable → Well structured → Excellent
  6. Does description include a clear list of features?

    yes / no
  7. How generic or cliché is description?

    rating · counts toward the page score: Pure cliché → Mostly generic → Mixed → Mostly fresh → Fresh and specific
  8. Does description mention awards, press quotes, review scores or famous previous games?

    yes / no
  9. What is the tone of description?

    pick one: Hype marketing · Plain and informative · Personal / developer voice · Humorous · Story or lore heavy · Almost nothing written
  10. How concrete is description (named mechanics, numbers, specifics) versus vague adjectives?

    rating · counts toward the page score: Only vague adjectives → Mostly vague → Mixed → Mostly concrete → Very concrete
  11. How well does description evoke a feeling or a fantasy the player wants?

    rating · counts toward the page score: Not at all → Weakly → Somewhat → Well → Very strongly
  12. Does description clearly name the game's genre?

    yes / no
  13. Does the first sentence of short_description say what kind of game it is?

    yes / no

The whole page 11

  1. Rate the overall quality of this store page as a whole (images and text).

    rating · counts toward the page score: Amateur → Weak → Average → Professional → Outstanding
  2. How well do header, screenshots and description fit together as one consistent pitch?

    rating · counts toward the page score: Contradictory → Loose → Okay → Coherent → Perfectly aligned
  3. How likely would a typical Steam user be to click on and wishlist this game based on this page?

    rating · counts toward the page score: Very unlikely → Unlikely → Maybe → Likely → Very likely
  4. Who most likely made this game, judging by the page?

    pick one: A solo hobbyist · A dedicated solo developer · A small indie team · An established indie studio · A large AA/AAA studio
  5. How broad is this game's likely audience?

    rating: Tiny niche → Niche → Moderate → Broad → Mass market
  6. How legitimate and trustworthy does this game look (versus a cash grab or scam)?

    rating · counts toward the page score: Looks like a scam → Doubtful → Neutral → Trustworthy → Clearly a serious product
  7. How original is the game's concept?

    rating · counts toward the page score: Pure clone → Derivative → Some twist → Original → Highly original
  8. How memorable is this game after seeing the page once?

    rating · counts toward the page score: Forgettable → Barely → Somewhat → Memorable → Unforgettable
  9. Do you recognize this specific game as a well-known title?

    yes / no
  10. Within 3 seconds of seeing header and short_description, how well would a user grasp the game's concept?

    rating · counts toward the page score: Not at all → Barely → Partly → Well → Completely
  11. How crowded is this game's genre on Steam?

    rating: Almost no competition → Little → Moderate → Crowded → Extremely saturated

How it was done

I started from a list of 85,152 Steam games and their review counts, from SteamSpy. I picked 30,924 of them so that every level of success is covered, from zero reviews to millions, and weighted them back so the numbers represent all of Steam.

For each game I took what a player sees on its store page: the capsule image, four screenshots and the description, from Steam's store API. An AI model, Jev by TypeSafe, answered the 46 questions above about each page. Asked the same questions twice, it gave practically the same answers (r = 0.99). On 240 pages that I rated blind myself, it agreed with me on which page was better 7 to 8 times out of 10.

Steam keeps sales private, so success is measured in reviews. One review is roughly 30 to 60 copies sold. "Ignored" means fewer than 10 reviews.

For the web-presence section, Claude Haiku (a small model from Anthropic) web-searched 68 of these games: every ignored game with a page score of 75 or more released at least a year earlier (34), plus 34 equally good pages that ended up with 1,000 to 30,000 reviews, picked at random as a control. Each search looked for an official site, social accounts, press coverage, videos by other creators and community threads, with the same questions every time. Every claim on that section links to what the search actually found.