Released: 2026-04-21
Missing Domino:
meta-llama/llama-4-maverick
meta
The excluded domino is number 0 and 1
anthropic/claude-haiku-4.5
anthropic
By systematically cataloging all 27 visible dominoes in the image and comparing against the complete standard double-six set of 28 tiles, the domino [2, 4] is missing. All other combinations of numbers from 0-6 are present in the image.
google/gemini-3-flash-preview
A full double-six set contains 28 tiles. By counting the tiles in the image, I found: blanks ([0,0], [0,1], [0,2], [0,3], [0,4], [0,5]), ones ([1,1], [1,2], [1,3], [1,4], [1,5], [1,6]), twos ([2,2], [2,3], [2,4], [2,5], [2,6]), threes ([3,3], [3,4], [3,5], [3,6]), fours ([4,4], [4,5], [4,6]), fives ([5,5], [5,6]), and sixes ([6,6]). The only tile from the standard set missing is the blank-six [0, 6].
anthropic/claude-sonnet-4.6
anthropic
After carefully cataloging all visible dominoes in the image and comparing against the full standard set of 28 dominoes (0-0 through 6-6), the domino [0,3] (blank-3) appears to be missing from the set.
openai/gpt-5-image-mini
openai
I scanned the 27 visible tiles and tallied occurrences of each face value (0–6). Every number except 4 and 5 appears seven times, while 4 and 5 each appear only six times, so the missing domino is [4,5].
x-ai/grok-4-fast
x-ai
By counting the occurrences of each number across all halves in the 27 dominoes shown, the numbers 3 and 5 each appear 7 times, while all other numbers (0, 1, 2, 4, 6) appear 8 times. This indicates that the missing domino is the one connecting 3 and 5.
moonshotai/kimi-k2.5
moonshot
By identifying all 27 present dominoes in the image and comparing against the standard 28-domino double-six set, every domino except [0,1] is accounted for. The present dominoes include: [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], [5,6], [6,6]. The only missing tile is [0,1].
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.