Released: 2026-08-11
Key:
Score Threshold:
deepseek/deepseek-chat-v3-0324
deepseek
((50 - 10) * 8) + (75 - 25)
= 370
z-ai/glm-5
z-ai
25 * 10 + 50 + 10 + 8
= 318
moonshotai/kimi-k2.5
moonshot
25 * 10 + 50 + 10 + 8
= 318
minimax/minimax-m2.5
minimax
75*(50-10)/10+25-8
= 317
openai/gpt-4o
openai
((75 + 8) * 10) - 50 - 10
= 770
google/gemini-3-flash-preview
(75 * (50 + 25)) / (10 + 8) + 10
= 322
mistralai/mistral-medium-3
mistral
((75 + 50) * (10 - 8)) + (25 + 10)
= 285
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.