Released: 2026-07-31
Key:
Score Threshold:
openai/gpt-4o
openai
(100 + (10 * ((2 * 3) + 10))) + 6
= 266
mistralai/mistral-medium-3
mistral
(100 + 10) * (6 - (10 / (3 - 2)))
= -440
deepseek/deepseek-chat-v3-0324
deepseek
(100 * (6 - (10 / 10))) + (2 * 3)
= 506
moonshotai/kimi-k2.5
moonshot
(100 * 6) - ((10 - 2) * 3) - 10
= 566
google/gemini-3-flash-preview
(100 * 6) - (10 * 3) - (10 / 2)
= 565
z-ai/glm-5
z-ai
(100 - 10) * 6 + (10 + 3) * 2
= 566
minimax/minimax-m2.5
minimax
100*6 - 10*3 - 10 + 2
= 562
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.