Released: 2026-06-03
Key:
Score Threshold:
openai/gpt-4o
openai
((7 * 9) + 25) * (4 + 1)
= 440
mistralai/mistral-medium-3
mistral
((25 * (9 + 7)) * (4 + 1)) + 3
= 2003
deepseek/deepseek-chat-v3-0324
deepseek
((25 * (9 + 7)) + (4 * 3)) + 1
= 413
minimax/minimax-m2.5
minimax
25 * (9 * 3 + 4 - 1) - 7
= 743
moonshotai/kimi-k2.5
moonshot
25 * 3 * (9 + 1) - 7
= 743
google/gemini-3-flash-preview
(25 * (4 + 7) * 3) - (9 - 1)
= 817
anthropic/claude-sonnet-4.6
anthropic
25 * (9 + 1) * 3 - 7
= 743
z-ai/glm-5
z-ai
25 * ((9 - 3) * (4 + 1)) - 7
= 743
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.