Released: 2026-07-26
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
(100 + 75) - (10 * (9 - 2))
= 105
google/gemini-3-flash-preview
(100+75)-10
= 165
deepseek/deepseek-chat-v3-0324
deepseek
(100 + 75) - (10 * (9 + 2))
= 65
z-ai/glm-5
z-ai
100 + 75 - 10
= 165
minimax/minimax-m2.5
minimax
100 + 75 - 10
= 165
moonshotai/kimi-k2.5
moonshot
100 + 75 - 10
= 165
openai/gpt-4o
openai
(100 + 75 - 10) * 2 - 9
= 321
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.