Released: 2026-08-18
Key:
Score Threshold:
openai/gpt-4o
openai
((100 + 9) * 9) + (50 * 4)
= 1181
deepseek/deepseek-chat-v3-0324
deepseek
(100 * 9) + (50 + 10) + (9 * 4)
= 996
google/gemini-3-flash-preview
(100 - 4) * 9 - (10 + 9)
= 845
mistralai/mistral-medium-3
mistral
((100 + 9) * (9 - 4)) - 50
= 495
minimax/minimax-m2.5
minimax
9 * (100 - (10 - 4))
= 846
moonshotai/kimi-k2.5
moonshot
100 * 9 - (50 + 4)
= 846
z-ai/glm-5
z-ai
(100 * 9) - 50 - 4
= 846
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.