Released: 2026-08-05
Key:
Score Threshold:
google/gemini-3-flash-preview
50 * (9 + 2) - (75 / (2 + 100))
= 549
deepseek/deepseek-chat-v3-0324
deepseek
((100 + 2) * (9 - 2)) + 75
= 789
mistralai/mistral-medium-3
mistral
((100 + 75) * (9 - (50 / 2))) + 2
= -2798
openai/gpt-4o
openai
((100 + 9) * 2) + (75 + 50 + 2)
= 345
moonshotai/kimi-k2.5
moonshot
(75 - 2) * (9 - 2) + 100 / 50
= 513
minimax/minimax-m2.5
minimax
((75 - 2) * (9 - 2)) + (100 / 50)
= 513
z-ai/glm-5
z-ai
(75 - 2) * (9 - 100 / 50) + 2
= 513
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.