MODEL RESULT / QWEN4-MAX

qwen4-max × Pelican Test

This page reads the same live leaderboard query as the public star leaderboard, isolates qwen4-max, and lists four reference models with identical fields. It computes no rank and does not treat visitor ratings as a capability score.

01 / LIVE DATA

Side by side, same criteria

Every model below comes from the same live leaderboard query: published runs, rating count and the average of signed-in visitor ratings. The order is this fixed comparison list, not a ranking.

ModelPublished runsRatingsAverage rating
qwen4-max10Unrated
claude-opus-5115.0 / 5
gpt-6-astra115.0 / 5
qwen3.8-max114.0 / 5
glm-5.3114.0 / 5

Live query: no ratings yet (averageStars: null), so this model is unrated — not zero stars.

A real zero-star average is shown as 0.0 / 5; unrated only means no one has rated the model yet.

02 / REAL PREVIEW

Real bitmap from the published run

Captured from the public isolated preview endpoint. The generated HTML is not injected into this page, and the preview CSP and sandbox are unchanged.

Screenshot of the qwen4-max Pelican Test run: a white pelican with an orange beak rides a red bicycle along a seaside path.
Specified historical run d50da632-a9cf-4097-91da-7ec283c0ee8a, revision 1, captured 2026-11-19T18:51:01Z (UTC) from the public preview.Open the isolated preview
03 / TASK & RATING RULES

One task, one subjective vote

The common task is to generate a single self-contained HTML file showing a pelican riding a bicycle. The star average comes only from signed-in visitor votes.

  • Every model receives the same prompt: generate one HTML file with the cycling pelican; all styles, SVG and images stay inline in that file.
  • Only signed-in visitors rate, subjectively, from 0 to 5 stars. Each account may rate each model once; 0 stars is a valid negative vote.
  • The average is not normalized for thinking strength or other provider effort settings, and it is not a model capability score.
  • An absent average is unrated, not zero stars. A 0.0 average exists only when visitors actually gave zero stars.
04 / FAQ

Frequently asked questions

What exactly does the Pelican Test ask a model to do?

Generate a single self-contained HTML file that shows a pelican riding a bicycle, with all styles, SVG and images inlined in that one file.

Who can rate a model, and what does a star mean?

Only signed-in visitors can rate, subjectively, from 0 to 5 stars. Each account can rate each model once, and 0 stars is a valid negative vote.

Does the average star rating measure model capability?

No. It is the average of subjective visitor votes. It is not normalized for thinking strength or other provider effort settings, and it is not a capability score.

Does this page rank qwen4-max against the other models?

No. The page lists qwen4-max and four reference models side by side with the same fields in a fixed comparison order. It does not calculate, display or imply a rank.

Does a missing average rating mean zero stars?

No. A null average means the model is unrated. A 0.0 / 5 average is shown only when real visitor votes gave zero stars.

Where does the page data come from?

The page and the public star leaderboard use the same server-side leaderboard query. This page selects five model keys; a missing entry or a failed query is shown as data unavailable, never backfilled.

PELICAN TEST

Run the same task, then check the live leaderboard.

Run the Pelican Test with your own API key. Your API provider may charge for usage. Ratings are signed-in visitor opinions, once per account per model.

Run the Pelican Test

Live figures come from the public leaderboard query. The screenshot is a historical snapshot of the named run, not a live iframe.