Released: 2026-06-19
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
((75 + 100) * (7 - (6 - (25 / 50))))
= 262
openai/gpt-4o
openai
(6 * 50) + 75 - (100 / 25)
= 371
z-ai/glm-5
z-ai
(75 * 50) / 25 + 100 + 7 + 6
= 263
deepseek/deepseek-chat-v3-0324
deepseek
(75 * (6 - (100 / (50 + 25)))) + 7
= 357
minimax/minimax-m2.5
minimax
(75-50)*(6+7)+(100/25)
= 329
moonshotai/kimi-k2.5
moonshot
7 * (100 - 50 - 6 + 75 / 25)
= 329
anthropic/claude-sonnet-4.6
anthropic
75 * 6 - 100 + 25 + 50 / 7
= 382
google/gemini-3-flash-preview
(75 * 7) - (100 + 50 + 25 + 6)
= 344
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.