Domino
Released: 2026-06-27
Missing Domino:
meta-llama/llama-4-maverick
meta
The excluded domino is number 0 and 0
anthropic/claude-haiku-4.5
anthropic
By systematically cataloging all visible dominoes in the image and comparing against the complete standard double-six set (28 unique tiles with all combinations of 0-6), the domino [4, 4] is not present among the 27 shown dominoes. All other tiles including [0, 0], [1, 1], [2, 2], [3, 3], [5, 5], [6, 6] and all mixed combinations are accounted for.
google/gemini-3-flash-preview
By cataloging all 27 dominoes shown in the image, we find that the set contains all elements of a standard double-six set except for the double-six tile. The present tiles include: Blank-[0,1,2,3,4,5,6], 1-[1,2,3,4,5,6], 2-[2,3,4,5,6], 3-[3,4,5,6], 4-[4,5,6], and 5-[5,6]. The only missing combination is 6-6.
anthropic/claude-sonnet-4.6
anthropic
Let me systematically catalog all dominoes visible in the image. A standard set has 28 tiles. I need to find which one is missing. Going through the image carefully: Row 1: [0,1], [0,3], [1,2], [3,3], [1,3] Row 2: [2,2], [3,3]... let me recount more carefully. After cataloging all 27 visible dominoes and checking against the full set of 28, the missing domino is [0,6].
openai/gpt-5-image-mini
openai
I identified all 27 visible tiles and the only tile not present from the full double-six set is the double six (6,6).
moonshotai/kimi-k2.5
moonshot
In a standard double-six set, each number 0-6 should appear exactly 8 times across all dominoes. Counting the occurrences in the image: the number 4 appears 7 times (in dominoes [0,4], [1,4], [2,4], [3,4], [4,4] twice, and [4,6]), meaning one more 4 is needed. The number 5 appears 5 times in clearly identified dominoes ([1,5], [2,5], [3,5], [5,5] twice). With [0,5] and [5,6] also present in the set (accounting for 2 more 5s), the total would be 7 fives, still needing one more 5. The only domino that contains both the missing 4 and the missing 5 is [4,5].
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.