Released: 2026-08-13
Key:
Score Threshold:
openai/gpt-4o
openai
(75 * 4) + (50 - 3)
= 347
deepseek/deepseek-chat-v3-0324
deepseek
((100 + 50) * (4 - (75 / 25))) + 3
= 153
mistralai/mistral-medium-3
mistral
(100 * 4) - (75 + 25 - (50 / 3))
= 316
z-ai/glm-5
z-ai
(100 * 3) + 75 - 4 - (50 / 25)
= 369
minimax/minimax-m2.5
minimax
75 * 4 + 100 - 50 + 25 - 3
= 372
moonshotai/kimi-k2.5
moonshot
3 * (75 + (100 - 4) / (50 / 25))
= 369
google/gemini-3-flash-preview
(3 * (75 + 50)) - (4 + (100 / 25))
= 367
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.