Vision / Visual Counting

Fruit Counting From Image

In the image task, the model counts bananas, apples, and oranges, even when some fruit overlap. It has to identify each fruit type and count carefully instead of giving a rough description.

Prompt

How many fruits of each type are in the image?

Bananas, apples, and oranges arranged on a wooden table.
Max tokens
100K
temperature
0
top_p
1
seed
42
presence_penalty
0
frequency_penalty
0
Reasoning effort
High
Execution
Single-shot via API

Fortytwo Prime

Fortytwo

PASS4 / 4

Based on the image, here is the count of each fruit type:
• Apples: 8
• Bananas: 7 (3 in the bunch on the left, 4 in the bunch on the right)
• Oranges: 5
Total: 20 fruits

Fortytwo identifies apples, bananas, and oranges, including the two banana bunches, and returns the exact answer-key counts.

vs
Claude Fable 5Anthropic
MIXED3 / 4

Here's the fruit count from the image:

  • Apples: 8 — red apples arranged in the center of the image, several with stems and leaves still attached
  • Oranges: 5 — one in the top right, one near the top center, one in the middle, one in the bottom left (with green leaves), and one in the bottom right
  • Bananas: 5 — a bunch of 2 on the left side and a bunch of 3 on the right side

Total: 18 pieces of fruit

Claude Fable 5 identifies all three fruit types and counts 8 apples and 5 oranges, but reports only 5 bananas instead of the required 7.

Model verdicts

Have a complex task to evaluate?

Request a custom evaluation for your use case.

Request a demo →