The ± value shows how much the counted judges’ scores vary across both rounds of scoring.
Claude Opus 5.5 · medium · Pass 15.30
Claude Opus 5.5 · medium · Pass 25.30
GPT-6 Astra · medium · Pass 14.75Not counted
GPT-6 Astra · medium · Pass 25.05Not counted
Grok 4.7 · medium · Pass 16.60
Grok 4.7 · medium · Pass 26.70
Scoring criteria
Pelican likeness
4.50
Bicycle correctness
6.50
Riding pose
6.00
Composition
7.50
Obvious errors (higher is better)
6.00
Drawing checks passedNormal
Judges
Claude Opus 5.5 · medium · Pass 1
5.30
What the judge sees: Original (Chinese) 这是一幅扁平风格的插画，画面中央有一只米白色、身体呈椭圆形的卡通鸟，它头顶有棕色的冠羽，长着长长的橙色喙，翅膀是浅灰蓝色。鸟正骑在一辆红色自行车上，自行车有两个白色车轮，鸟的一只翅膀握着黄色的车把。背景是浅蓝色的天空，右上方有一个黄色的圆形太阳，鸟身两侧各有几条蓝色横线，下方是绿色的起伏草地，自行车下面有一片深绿色的阴影。
The crest looks like a chicken's, the beak has no pouch, and pelican features are weak; feet aren't on the pedals.
Machine translated
Original (Chinese) 头冠像鸡，喙没有喉囊，鹈鹕特征弱；脚没踩踏板。
Long beak and throat pouch: No
Two wheels: Yes
Frame connects the wheels: Yes
Bird sits on the seat: No
Feet on the pedals: No
Pelican likeness
4.00
Bicycle correctness
6.00
Riding pose
5.00
Composition
7.00
Obvious errors (higher is better)
5.00
Claude Opus 5.5 · medium · Pass 2
5.30
What the judge sees: Original (Chinese) 这是一幅扁平风格的插画，画面中央有一只米白色、身体呈椭圆形的卡通鸟，它头顶有棕色的冠羽，长着长长的橙色喙，翅膀是浅灰蓝色。鸟正骑在一辆红色自行车上，自行车有两个白色车轮，鸟的一只翅膀握着黄色的车把。背景是浅蓝色的天空，右上方有一个黄色的圆形太阳，鸟身两侧各有几条蓝色横线，下方是绿色的起伏草地，自行车下面有一片深绿色的阴影。
The picture is appealing, but the bird looks like a rooster and has no pouch; no saddle or handlebars, and both feet hang in the air.
Machine translated
Original (Chinese) 画面讨喜，但鸟像公鸡，没有喉囊；没有车座和车把，双脚悬空。
Long beak and throat pouch: No
Two wheels: Yes
Frame connects the wheels: Yes
Bird sits on the seat: No
Feet on the pedals: No
Pelican likeness
4.00
Bicycle correctness
6.00
Riding pose
5.00
Composition
7.00
Obvious errors (higher is better)
5.00
GPT-6 Astra · medium · Pass 1
4.75Not counted
What the judge sees: Original (Chinese) 画面中央是一只骑着红色自行车的卡通鸟，身体呈乳白色，翅膀为灰蓝色，头顶有棕色冠状形状，橙色长喙向右伸出。自行车有两个红色轮圈、浅白色内部的圆形车轮，位于绿色起伏地面上；背景为浅蓝色，右上方有一个黄色圆形，鸟的左右两侧有几条蓝色短横线。
The crest makes it less recognizable as a pelican, and both feet are disconnected from the crank and pedals.
Machine translated
Original (Chinese) 头冠削弱鹈鹕辨识度，双脚与曲柄踏板脱节。
Long beak and throat pouch: No
Two wheels: Yes
Frame connects the wheels: Yes
Bird sits on the seat: No
Feet on the pedals: No
Pelican likeness
4.00
Bicycle correctness
6.00
Riding pose
3.00
Composition
7.00
Obvious errors (higher is better)
4.00
GPT-6 Astra · medium · Pass 2
5.05Not counted
What the judge sees: Original (Chinese) 画面中央是一只骑着红色自行车的卡通鸟，身体呈乳白色，翅膀为灰蓝色，头顶有棕色冠状形状，橙色长喙向右伸出。自行车有两个红色轮圈、浅白色内部的圆形车轮，位于绿色起伏地面上；背景为浅蓝色，右上方有一个黄色圆形，鸟的左右两侧有几条蓝色短横线。
The long beak lacks a clear pouch, and both feet are off the pedals.
Machine translated
Original (Chinese) 长喙缺少明确喉囊，双脚与踏板脱离。
Long beak and throat pouch: No
Two wheels: Yes
Frame connects the wheels: Yes
Bird sits on the seat: No
Feet on the pedals: No
Pelican likeness
4.00
Bicycle correctness
6.00
Riding pose
3.00
Composition
8.00
Obvious errors (higher is better)
5.00
Grok 4.7 · medium · Pass 1
6.60
What the judge sees: Original (Chinese) 画面中央是一只白色卡通鸟骑在红色自行车上，面向右侧。鸟有棕色头顶、橙色长喙、黑色圆眼和灰色翅膀，双脚踩在踏板上。背景是浅蓝色天空，右上方有一个黄色圆，底部是起伏的绿色地面，左右两侧各有几条浅蓝色短横线。
Riding pose and bike are fairly complete, but there's no pouch, and the crest makes it look unlike a pelican.
Machine translated
Original (Chinese) 骑姿和车体较完整，但缺喉囊，冠羽使它不像鹈鹕。
Long beak and throat pouch: No
Two wheels: Yes
Frame connects the wheels: Yes
Bird sits on the seat: Yes
Feet on the pedals: Yes
Pelican likeness
4.00
Bicycle correctness
7.00
Riding pose
8.00
Composition
8.00
Obvious errors (higher is better)
7.00
Grok 4.7 · medium · Pass 2
6.70
What the judge sees: Original (Chinese) 画面中央是一只白色卡通鸟骑在红色自行车上，面向右侧。鸟有棕色头顶、橙色长喙、黑色圆眼和灰色翅膀，双脚踩在踏板上。背景是浅蓝色天空，右上方有一个黄色圆，底部是起伏的绿色地面，左右两侧各有几条浅蓝色短横线。
Riding pose mostly works, but the pouch is a bit faint and neither foot is firmly on a pedal.
