Released: 2026-08-19
Key:
Score Threshold:
deepseek/deepseek-chat-v3-0324
deepseek
(75 + (50 + (25 - 10))) * 6
= 840
minimax/minimax-m2.5
minimax
75 * 6 - 50 / 10
= 445
z-ai/glm-5
z-ai
(75*6)-(50/10)
= 445
moonshotai/kimi-k2.5
moonshot
(75 * 6) - (50 / 10)
= 445
openai/gpt-4o
openai
(6 * 75) - (25 + 50 + 10)
= 365
mistralai/mistral-medium-3
mistral
((75 + 50) * 6) - (25 + (10 / 8))
= 723
google/gemini-3-flash-preview
(6 * 75) - (10 / (50 / 25))
= 445
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.