Released: 2026-03-19
Missing Domino:
meta-llama/llama-4-maverick
meta
The excluded domino is number 0 and 0
google/gemini-3-flash-preview
A standard double-six domino set consists of 28 unique tiles ranging from [0,0] to [6,6]. After identifying all 27 dominoes present in the image, the missing tile is the [6,6] double-six.
anthropic/claude-haiku-4.5
anthropic
After systematically examining all 27 dominoes shown in the image and comparing them against the complete standard double-six set of 28 tiles, the domino [4, 4] is missing. This is a double domino (both sides showing 4 dots) which should be present in a complete set but is not visible anywhere in the image.
anthropic/claude-sonnet-4.6
anthropic
I systematically catalogued all visible dominoes in the image. A standard double-six set has 28 tiles. After identifying all 27 visible dominoes and checking which combination from 0-0 through 6-6 is missing, the tile [0,3] (blank-three) is not present in the image.
x-ai/grok-4-fast
x-ai
After carefully examining the image and identifying all 27 dominoes present, the double-four domino ([4-4]) is the only one missing from the standard double-six set.
openai/gpt-5-image-mini
openai
I identified all 27 tiles in the image and the only domino missing from the full double-six set is the double-six (6-6).
moonshotai/kimi-k2.5
moonshot
A standard double-six domino set contains 28 unique tiles with each number 0-6 appearing exactly 8 times across all tiles. The domino [6,6] is the only tile with 12 total pips (6 on each half). By examining all 27 dominoes in the image, the maximum pip count visible on any domino is 11 (from [5,6]). No domino shows the distinctive 6-6 pattern (12 dots total). Counting occurrences: [0,0], [0,1], [0,2], [0,3], [0,5], [0,6] account for the ’0’ series; [1,1], [2,2], [5,5] account for three doubles; high-count dominoes like [2,6], [3,6], [4,5], [5,6] are present but [6,6] with its unique 12-pip configuration is absent. Therefore, the missing domino is [6,6].
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.