Released: 2026-07-20
Key:
Score Threshold:
deepseek/deepseek-chat-v3-0324
deepseek
((75 + 50) + (8 * 8)) + 10
= 199
z-ai/glm-5
z-ai
75 + 50 + 10 + 8*8 - 6
= 193
moonshotai/kimi-k2.5
moonshot
50 * (8 - 6) + 75 + 8 + 10
= 193
mistralai/mistral-medium-3
mistral
(75 * (8 + 6)) - (50 + 10)
= 990
openai/gpt-4o
openai
(8 * (10 * 50) - (75 - 6))
= 3931
anthropic/claude-sonnet-4.6
anthropic
50 * (8 - 6) + 75 + 10 + 8
= 193
minimax/minimax-m2.5
minimax
(8+8)*6+50+75
= 221
google/gemini-3-flash-preview
((75 * 50) + 8) / (10 + 8) + 6
= 214
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.