Released: 2026-07-27
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
((100 + 25) * (10 - (4 / (10 / 2))))
= 1150
deepseek/deepseek-chat-v3-0324
deepseek
(100 - 25) * (10 - 2) + 10 + 4
= 614
moonshotai/kimi-k2.5
moonshot
100*(10-4) - 25 + 2
= 577
openai/gpt-4o
openai
((100 * 4) + (25 * 10))-2
= 648
minimax/minimax-m2.5
minimax
(25 * 10 + 100) * 4 - 2
= 1398
z-ai/glm-5
z-ai
(10 - 4) * 100 + 2 - 25
= 577
google/gemini-3-flash-preview
(100 * (10 - 4)) - 25 + 2
= 577
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.