Released: 2026-01-31
Missing Domino:
google/gemini-2.5-flash-preview-09-2025
Reasoning
A standard double-six domino set consists of 28 unique tiles. The image shows 27 tiles, meaning one is missing. By listing all present tiles and comparing them to the full set of 28, the missing tile is identified. The tiles present are: [0, 1], [0, 0], [0, 2], [0, 3], [0, 4], [0, 5], [0, 6], [1, 1], [1, 2], [1, 3], [1, 4], [1, 5], [1, 6], [2, 2], [2, 3], [2, 4], [2, 5], [2, 6], [3, 3], [3, 4], [3, 5], [3, 6], [4, 4], [4, 5], [4, 6], [5, 5], [6, 6]. The only possible unique tile from the full set that is not listed is [6, 4].
meta-llama/llama-4-maverick
meta
Reasoning
The image contains 27 dominoes. A standard double-six domino set has 28 tiles. By examining the image and comparing it to the possible combinations, the missing domino is [0, 0].
x-ai/grok-4-fast
x-ai
Reasoning
After visually inspecting the 27 dominoes in the image and comparing to the standard double-six set, the [3,5] domino is the only one absent.
openai/gpt-5-image-mini
openai
Reasoning
I counted the number of ends showing two pips and found only six occurrences (a full double-six set would show eight). That shortfall of two indicates the missing tile is the double 2 ([2,2]).
qwen/qwen3-vl-30b-a3b-thinking
qwen
Reasoning
The count for number 6 appears to be 6 times, indicating the missing double-six domino.
anthropic/claude-haiku-4.5
anthropic
Reasoning
A standard double-six domino set contains 28 unique tiles representing all possible combinations of numbers 0-6. By systematically checking all 27 visible dominoes in the image against the complete set of 28 possible combinations, the domino [4, 4] is the only one that is not present. All other combinations including [0,0], [0,1] through [0,6], [1,1] through [1,6], [2,2] through [2,6], [3,3] through [3,6], [5,5], [5,6], and [6,6] are accounted for in the image.
Each model receives the same domino puzzle grid. Models are tasked with identifying the missing domino using only visual clues from the grid. Their answers are evaluated without feedback or retries.