Released: 2026-06-08
Key:
Score Threshold:
anthropic/claude-sonnet-4.6
anthropic
75 * 2 - 10 + 25 + 3 + 3
= 171
mistralai/mistral-medium-3
mistral
(75 + 25) * (10 - (3 / 3))
= 900
deepseek/deepseek-chat-v3-0324
deepseek
(75 - 25) * 3 - (10 - 2)
= 142
openai/gpt-4o
openai
(75 + 25 + (3 * 10) + 3)
= 133
moonshotai/kimi-k2.5
moonshot
75 + 25 * 3 - (10 - 3 * 2)
= 146
z-ai/glm-5
z-ai
75 * 2 - 10 + 3 + 3
= 146
minimax/minimax-m2.5
minimax
75 + 25*3 - (10 - 3*2)
= 146
google/gemini-3-flash-preview
(25 * (3 + 3)) - (10 / 2)
= 145
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.