Released: 2026-08-15
Key:
Score Threshold:
openai/gpt-4o
openai
((75 + 25) * 3) - 50 + 4
= 254
google/gemini-3-flash-preview
(75 * 3) - 25 - (50 / 5)
= 190
deepseek/deepseek-chat-v3-0324
deepseek
((25 + 50) + (5 * 4)) * 3
= 285
minimax/minimax-m2.5
minimax
75 + 50 + 25 + 5 * 3 + 4
= 169
z-ai/glm-5
z-ai
50 * 4 - (75 / 25 + 3)
= 194
mistralai/mistral-medium-3
mistral
(75 * (5 - (3 / (4 + 50)))) + 25
= 395
moonshotai/kimi-k2.5
moonshot
50*4 - (5 + 3/(75/25))
= 194
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.