Released: 2026-08-07
Key:
Score Threshold:
deepseek/deepseek-chat-v3-0324
deepseek
(100 * (7 + 2)) + (50 * 2) + 4
= 1004
minimax/minimax-m2.5
minimax
(100 + 7 + 2) * (50 + 4 + 2)
= 6104
openai/gpt-4o
openai
(100 * 7) + (50 * 4) + 2
= 902
mistralai/mistral-medium-3
mistral
((100 + 7) * (50 - (4 / 2))) - 2
= 5134
google/gemini-3-flash-preview
(100 + 50) * (4 + 2) - (7 / 2)
= 896
moonshotai/kimi-k2.5
moonshot
(100 * 7) + (50 * 4) - 2 - 2
= 896
z-ai/glm-5
z-ai
(100 * 4 + 50 + 2) * 2 - 7
= 897
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.