Released: 2026-07-30
Key:
Score Threshold:
openai/gpt-4o
openai
(75 * 7) - 5 + (10 / 5)
= 522
google/gemini-3-flash-preview
(75 + 10) * 6 + 7 - 5
= 512
deepseek/deepseek-chat-v3-0324
deepseek
((75 - 5) * (7 + (10 - 6)))
= 770
mistralai/mistral-medium-3
mistral
((75 + (10 * 6)) * (7 + 5)) - 5
= 1615
minimax/minimax-m2.5
minimax
(75 + 7) * 6 + 10 + 5 + 5
= 512
moonshotai/kimi-k2.5
moonshot
7 * 75 - 6 - 5 - 10 / 5
= 512
z-ai/glm-5
z-ai
((75 - 5) - 6) * (10 - 7 + 5)
= 512
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.