Released: 2026-06-10
Key:
Score Threshold:
google/gemini-3-flash-preview
(25 * 10) - (75 + 50) + 100 + 1
= 226
openai/gpt-4o
openai
((25 * 10) - 75) + 1 + 50
= 226
deepseek/deepseek-chat-v3-0324
deepseek
((100 + 10) * (25 - 1)) - (75 + 50)
= 2515
moonshotai/kimi-k2.5
moonshot
(10 + 1) * (75 - 50 - 100 / 25)
= 231
z-ai/glm-5
z-ai
10 * (25 - 100 / 50) + 1
= 231
mistralai/mistral-medium-3
mistral
(100 + 75 + 50) * (25 / (10 - 1))
= 625
minimax/minimax-m2.5
minimax
(75 - (50 + 100/25)) * (10 + 1)
= 231
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.