Article
The Pelican Test: How Chinese Developers Benchmark AI Models With a 3D Pelican
Forget MMLU and HumanEval. In China's developer community, the hottest AI benchmark right now involves a pelican riding a bicycle — rendered in 3D, generated from a single prompt.
A few days ago, a thread on LINUX DO — one of China's largest developer forums — exploded. A member shared demos generated by a rumored new model, "Claude Opus 5.5": a QQ Speed-style 3D racing game and a cargo ship demo, each produced from a single sentence of prompting and hosted on Cloudflare Pages. The thread pulled 300 replies and over 13,000 views in days, with the original post collecting hundreds of likes.
But the detail that stuck wasn't the racing game. It was the community's homegrown evaluation ritual: the 3D pelican test. Ask a model to generate an interactive 3D pelican — preferably one riding a bicycle — and judge the model by what comes back. Different models get run through the same absurd prompt, and the results are compared side by side. "Pelican" (鹈鹕) has become the forum's unofficial unit of generative capability.
It sounds like a joke, but the pelican test is a surprisingly good evaluation. A single prompt exercises almost everything a code-generating model needs to be good at:
| What the test demands | What it reveals |
|---|---|
| 3D geometry (beak, wings, webbed feet) | Spatial reasoning and anatomical knowledge |
| A bicycle (frame, wheels, pedals) | Compositional complexity — two hard objects interacting |
| "Riding" (animation, balance) | Whether the model understands motion and physics |
| One-shot, no iteration | Raw capability, not the user's prompt-engineering skill |
| Visual output | Taste — proportions, colors, and polish you can see |
Standard benchmarks can be gamed or memorized. Nobody trains a model specifically to draw pelicans on bicycles, which makes it a delightfully honest test. A thread debating whether one viral demo was "real 3D rendering or just SVG" shows the community takes the methodology more seriously than the silliness suggests.
The pelican test belongs to a growing movement of vibes-based benchmarking — evaluating models the way users actually experience them, through open-ended creative tasks rather than multiple-choice exams. Western developers do the same thing when they ask a model to "build a landing page" or "clone Flappy Bird" and judge by feel.
What makes the Chinese version interesting is how it became shared infrastructure: a common prompt, a shared joke, and comparable results across models. When everyone runs the same pelican, you get something multiple-choice tests can't give you — a leaderboard with a sense of humor.
Want to try it? The recipe from the forums is simple:
If you're curious how Chinese developers think about AI more broadly, it's worth knowing this is the same community currently dissecting why a game studio wants to build a top-tier LLM — the pelican is just the friendliest entry point.