Released: 2026-07-12
Key:
Score Threshold:
openai/gpt-4o
openai
75 * 8 + 7
= 607
mistralai/mistral-medium-3
mistral
((75 * (8 + 7)) - (50 / (8 - 6)))
= 1100
deepseek/deepseek-chat-v3-0324
deepseek
(75 * (8 + (50 / (8 + 7)))) + 6
= 856
z-ai/glm-5
z-ai
75*(8+8-6)+7
= 757
moonshotai/kimi-k2.5
moonshot
75 * (8 + 8 - 6) + 7
= 757
minimax/minimax-m2.5
minimax
(75 + 50) * 6 + 7 + 8 - 8
= 757
google/gemini-3-flash-preview
(50 + 75) * 6 + 7
= 757
anthropic/claude-sonnet-4.6
anthropic
((75 + 8) * 8) + 50 + 7 - 6
= 715
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.