The ± value shows how much the counted judges’ scores vary across both rounds of scoring.
Claude Opus 5.5 · medium · Pass 14.80
Claude Opus 5.5 · medium · Pass 26.05
GPT-6 Astra · medium · Pass 15.00
GPT-6 Astra · medium · Pass 25.60
Grok 4.7 · medium · Pass 15.20
Grok 4.7 · medium · Pass 26.50
Scoring criteria
Pelican likeness
6.33
Bicycle correctness
5.33
Riding pose
4.17
Composition
6.50
Obvious errors (higher is better)
5.33
Drawing checks passedNormal
Judges
Claude Opus 5.5 · medium · Pass 1
4.80
What the judge sees: Original (Chinese) 画面是浅蓝色渐变的天空背景,左上角有一个黄色圆形太阳,底部有一条扁平的绿色椭圆形草地。画面中央是一辆红色车架的自行车,两个黑色车轮带有辐条,右上方有一个黑色车把。自行车上坐着一只白色的卡通鸟,长脖子向右上方伸出,头是圆形、眼睛是黑色的,右侧有一个橙色的大喙,喙下方有浅橙色的喉囊;鸟身左侧有一只灰色翅膀和几条灰色线条,两条橙色的腿向下踩在车中部的深灰色踏板上。
Original (Chinese) 车架结构怪异且没有车座,鸟身悬空,翅膀也没握车把。
Long beak and throat pouch: Yes
Two wheels: Yes
Frame connects the wheels: Yes
Bird sits on the seat: No
Feet on the pedals: Yes
Pelican likeness
6.00
Bicycle correctness
4.00
Riding pose
4.00
Composition
6.00
Obvious errors (higher is better)
4.00
Claude Opus 5.5 · medium · Pass 2
6.05
What the judge sees: Original (Chinese) 画面是浅蓝色渐变的天空背景,左上角有一个黄色圆形太阳,底部有一条扁平的绿色椭圆形草地。画面中央是一辆红色车架的自行车,两个黑色车轮带有辐条,右上方有一个黑色车把。自行车上坐着一只白色的卡通鸟,长脖子向右上方伸出,头是圆形、眼睛是黑色的,右侧有一个橙色的大喙,喙下方有浅橙色的喉囊;鸟身左侧有一只灰色翅膀和几条灰色线条,两条橙色的腿向下踩在车中部的深灰色踏板上。
Original (Chinese) 鹈鹕特征清楚,但没有车座,翅膀也没握车把,车架结构简陋。
Long beak and throat pouch: Yes
Two wheels: Yes
Frame connects the wheels: Yes
Bird sits on the seat: No
Feet on the pedals: Yes
Pelican likeness
7.00
Bicycle correctness
6.00
Riding pose
5.00
Composition
6.00
Obvious errors (higher is better)
6.00
GPT-6 Astra · medium · Pass 1
5.00
What the judge sees: Original (Chinese) 画面中央是一只骑着红色自行车的白色卡通鸟,鸟有灰色轮廓、黑色眼睛、橙黄色长嘴和橙色双腿,身体左侧有灰色尾羽。自行车的两个轮子为深灰色圆环,内部有放射状辐条,右上方是深灰色车把;背景为浅蓝色,左上角有一个黄色圆形,底部有一片绿色扁椭圆。
Original (Chinese) 鸟脚与踏板堆叠,车座和链条缺失,骑行结构较含混。
Long beak and throat pouch: Yes
Two wheels: Yes
Frame connects the wheels: Yes
Bird sits on the seat: No
Feet on the pedals: Yes
Pelican likeness
6.00
Bicycle correctness
5.00
Riding pose
3.00
Composition
6.00
Obvious errors (higher is better)
5.00
GPT-6 Astra · medium · Pass 2
5.60
What the judge sees: Original (Chinese) 画面中央是一只骑着红色自行车的白色卡通鸟,鸟有灰色轮廓、黑色眼睛、橙黄色长嘴和橙色双腿,身体左侧有灰色尾羽。自行车的两个轮子为深灰色圆环,内部有放射状辐条,右上方是深灰色车把;背景为浅蓝色,左上角有一个黄色圆形,底部有一片绿色扁椭圆。
Original (Chinese) 鹈鹕特征可辨,但车座缺失,翅膀未接触车把。
Long beak and throat pouch: Yes
Two wheels: Yes
Frame connects the wheels: Yes
Bird sits on the seat: No
Feet on the pedals: Yes
Pelican likeness
7.00
Bicycle correctness
5.00
Riding pose
4.00
Composition
7.00
Obvious errors (higher is better)
5.00
Grok 4.7 · medium · Pass 1
5.20
What the judge sees: Original (Chinese) 画面是一幅扁平卡通插画:一只白色圆身的鸟朝右骑在红色自行车上,鸟有橙色长喙、黑色圆眼、灰色翅膀和橙色细腿,车架为红色,黑色把手,两个黑色辐条轮。左上方是浅蓝色天空中的一颗黄色圆太阳,底部是一块绿色椭圆地面。
Original (Chinese) 双轮和车架都在,但鸟身悬空无座,不算真正骑上。
Long beak and throat pouch: Yes
Two wheels: Yes
Frame connects the wheels: Yes
Bird sits on the seat: No
Feet on the pedals: Yes
Pelican likeness
5.00
Bicycle correctness
6.00
Riding pose
4.00
Composition
6.00
Obvious errors (higher is better)
5.00
Grok 4.7 · medium · Pass 2
6.50
What the judge sees: Original (Chinese) 画面是一幅扁平卡通插画:一只白色圆身的鸟朝右骑在红色自行车上,鸟有橙色长喙、黑色圆眼、灰色翅膀和橙色细腿,车架为红色,黑色把手,两个黑色辐条轮。左上方是浅蓝色天空中的一颗黄色圆太阳,底部是一块绿色椭圆地面。