Domino
Released: 2026-03-02
Missing Domino:
meta-llama/llama-4-maverick
meta
The image shows 27 domino tiles, and upon closer inspection, it is evident that all combinations are present except for the double-zero tile (0,0).
google/gemini-3-flash-preview
After cataloging all 27 dominoes in the image and comparing them against the standard 28-tile double-six set, the double-blank (0-0) domino is missing. The existing tiles are: [2,3], [1,5], [1,2], [3,5], [4,5], [2,6], [2,5], [3,4], [1,3], [1,6], [6,6], [0,2], [0,4], [1,1], [4,6], [5,6], [0,5], [0,6], [0,1], [3,6], [0,3], [4,4], [2,2], [1,4], [4,4], [3,3], [1,4].
anthropic/claude-haiku-4.5
anthropic
By systematically examining all 27 dominoes visible in the image and cross-referencing against the complete set of 28 possible dominoes in a standard double-six set, the domino [4, 4] is not present. All other combinations from [0, 0] through [6, 6] appear to be represented in the displayed tiles.
anthropic/claude-sonnet-4.6
anthropic
I systematically catalogued all visible dominoes in the image and compared them against the full standard double-six set of 28 tiles. After checking each tile, the blank-blank (0|0) domino appears to be missing from the set.
openai/gpt-5-image-mini
openai
I checked each tile in the image against the full double-six set (00 through 66). All 27 shown tiles correspond to the set except the double-six tile, which does not appear in the arrangement, so the missing domino is [6,6].
x-ai/grok-4-fast
x-ai
After carefully analyzing the arrangement and counting the pips on each half of the 27 visible dominoes, all unique pairs from the standard double-six set are present except for the [5|3] domino.
moonshotai/kimi-k2.5
moonshot
The double-zero domino [0,0] is missing. All other doubles [1,1] through [6,6] are present, and all other dominoes containing 0 ([0,1] through [0,6]) are present. Counting all 27 dominoes confirms that [0,0] is the only one missing from the standard set of 28.
Methodology Note
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.