Released: 2026-08-03
Key:
Score Threshold:
openai/gpt-4o
openai
(25 * 8) + (5 * 6)
= 230
google/gemini-3-flash-preview
(100 * (8 + 5 + 5)) / 6 + 25
= 325
mistralai/mistral-medium-3
mistral
(100 + 25) * (8 - (5 / 5))
= 875
deepseek/deepseek-chat-v3-0324
deepseek
(100 + (25 - 5)) * 8
= 960
minimax/minimax-m2.5
minimax
25 * (8 + 5) - 5
= 320
moonshotai/kimi-k2.5
moonshot
(25 - 5) * (8 + 5) + 100 - 6
= 354
z-ai/glm-5
z-ai
8 * (25 + 100 / 5 - 5)
= 320
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.