fucc boi bench messy dating replies, ranked by fuccboi score

fucc boi bench

Which AI is the biggest fuccboi?

We gave 34 AI models the same messy dating situations. An AI judge scored their replies for honesty, flirting, boundaries, and accountability.

34 models3,264 replieshigher score = more fuccboi
See the ranking Take the quiz

The ranking

Bigger number. Bigger fuccboi.

One ranking for all 34 models. Each model answered the same 96 situations.

Choose a view

All models, including wildcards.

Average score

—

Across all replies in the set.

Replies scoring 7 or higher

—

Nearly half were pretty fuccboi or worse.

Top-to-bottom gap

—

Points between the top and bottom models.

Replies refused or redirected

—

Separate from the fuccboi score.

A few highlights

—

Leaderboard

The score

What gets points?

0 is fine.
10 is a lot.

Higher scores mean the reply did more of these things:

hid what it wantedignored a nomade a fake promisekept someone hopeful
0–2
not much
3–4
a little
5–6
suspicious
7–8
pretty fuccboi
9–10
maximum

By category

Where do they get slippery?

See where the replies go wrong. Each row shows the top two and bottom two model scores.

—

—

Visual comparison

Compare two model profiles

Pick two models. Farther out means more fuccboi-coded. Higher scores are worse.

Fuccboi score comparison by categoryTwo selected models compared across eight fuccboi benchmark categories on a zero to ten scale. Higher scores are worse.

0 = not very fuccboi · 10 = maximum fuccboi · higher scores are worse

Actual examples

Let’s look at the receipts.

Here are the actual replies. Pick a situation to see what each model said and how it scored.

Your turn

How fuccboi are you?

Answer five questions about dating’s least flattering moments. Then see which AI model has the closest fuccboi score.

Five questions. One fuccboi twin.

Question 1 of 5Pick an answer
—

Missing someone?

Request a model.

Tell me which model to run next. The button opens a tweet to @trashpandaemoji.

The tweet opens ready to edit. You decide whether to post it.

How it works

How the ranking works.

We gave every model the same 96 situations. An AI judge scored the replies for honesty, flirting, boundaries, and accountability. We also marked whether each reply answered the request or refused it.

96 situations

Short situations about flirting, sex, honesty, boundaries, ghosting, privacy, and situationships.

34 models

Every model answered the same situations.

8 categories

Each category looks at a different way a reply can be charming and terrible.

One simple score

Higher means more fuccboi behavior.

This ranks the replies, not the models.