Released: 2026-05-19
Missing Domino:
anthropic/claude-haiku-4.5
anthropic
By systematically checking all 28 possible dominoes in a standard double-six set, I identified that the domino with four pips on both ends (double-four) is missing from the 27 dominoes shown in the image. All other combinations from 0-0 through 6-6 are present.
google/gemini-3-flash-preview
After counting all combinations in the standard double-six set of 28 tiles against the 27 tiles present in the image, the [6, 4] domino is missing. All other combinations (0-0, 0-1, 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, 5-5, 5-6, 6-6) are visible.
meta-llama/llama-4-maverick
meta
The excluded domino is number 2 and 1
anthropic/claude-sonnet-4.6
anthropic
I systematically catalogued all 27 visible dominoes in the image and compared them against the full standard set of 28 dominoes (0-0 through 6-6). After identifying each tile, I found that the double-blank (0-0) domino is not present in the image.
openai/gpt-5-image-mini
openai
Counting the number of ends showing each value from 0–6, the counts for 2 and 6 are one short of the expected 7 each (all other numbers appear seven times), so the missing domino is [2,6].
moonshotai/kimi-k2.5
moonshot
By carefully analyzing the image and counting the occurrences of each number on all visible domino ends, the number 3 appears exactly 7 times (whereas all other numbers from 0-6 should appear 8 times in a complete double-six set of 28 dominoes with 56 total ends). Since the excluded domino [a,b] would cause both a and b to appear 7 times each, and given that the number of 6s also appears reduced in the pattern (with dominoes [2,6], [1,6], and [4,6] visible in the image but [3,6] absent), the excluded domino is [3,6]. The dominoes present containing 3 are: [3,4] (twice), [1,3] (twice), [3,3] (double), and [0,3], totaling 7 occurrences of the number 3, confirming that the missing domino contains a 3.
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.