Released: 2026-06-13
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
((25 * (9 + 1)) * 6) - 6
= 1494
google/gemini-3-flash-preview
(6+1)*((6*9)+6)+25
= 445
openai/gpt-4o
openai
(25 * 6 * 6) - 9 - 1
= 890
deepseek/deepseek-chat-v3-0324
deepseek
((25 * (6 + 9)) + (6 * 6)) + 1
= 412
minimax/minimax-m2.5
minimax
25 * (6 + 6 + 6 - 1) + 9
= 434
moonshotai/kimi-k2.5
moonshot
25 * (6 + 6 + 6 - 1) + 9
= 434
z-ai/glm-5
z-ai
25 * (6 + 6 + 6 - 1) + 9
= 434
Each model receives the same prompt with the numbers to use. Models are tasked with creating an expression using only arithmetic operations to reach the target number. Each number can only be used once and you do not have to use all the numbers. Their answers are evaluated without feedback or retries.