Released: 2026-08-12
Key:
Score Threshold:
openai/gpt-4o
openai
(50 + (100 * (7 - 4))) + 6
= 356
mistralai/mistral-medium-3
mistral
(100 * (7 - 3)) * (6 + 4)
= 4000
deepseek/deepseek-chat-v3-0324
deepseek
((100 - 50) * (7 + 3)) - (6 * 4)
= 476
z-ai/glm-5
z-ai
6 * (100 - 7 * 4)
= 432
moonshotai/kimi-k2.5
moonshot
((100 + 50) - 6) * 3
= 432
minimax/minimax-m2.5
minimax
100 * 4 + (50 - 6 * 3)
= 432
google/gemini-3-flash-preview
(100 + 50 + 7 + 4 - 3) * 6
= 948
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.