Released: 2026-05-21
Key:
Score Threshold:
moonshotai/kimi-k2.5
moonshot
(75 - 7) * (10 - 3) - 10 - 7
= 459
google/gemini-2.0-flash-001
(75 * 7) - (10 + 10)
= 505
mistralai/mistral-medium-3
mistral
((75 * (10 - 3)) + (7 * 10)) + 7
= 602
z-ai/glm-5
z-ai
(75 + 10 + 7) * (10 - 7) * 3
= 828
anthropic/claude-sonnet-4.6
anthropic
75 * (7 - 3) + 10 + 7 - 10
= 307
deepseek/deepseek-chat-v3-0324
deepseek
(75 - 10 - 7) * 7 + 10 + 3
= 419
openai/gpt-4o
openai
(75 * 7) - (7 + 10 + 3)
= 505
google/gemini-3-flash-preview
(75*10/3)+10+(7*7)
= 309
minimax/minimax-m2.5
minimax
75 * 3 + 10 * 7 + 10 * 7
= 365
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.