Released: 2026-07-10
Key:
Score Threshold:
google/gemini-3-flash-preview
((75 + 50) / 25) + 10 * (100 - 10)
= 905
mistralai/mistral-medium-3
mistral
((100 - 10) * (75 + 10)) - (25 + 50)
= 7575
deepseek/deepseek-chat-v3-0324
deepseek
(75 * (10 + 10)) + (100 + 25 + 50)
= 1675
minimax/minimax-m2.5
minimax
75 * 10 + 50 + 100 / 10
= 810
anthropic/claude-sonnet-4.6
anthropic
(75 + 25) * (10 - 10)
= 0
openai/gpt-4o
openai
((75 + 50) * 10) + 100 - 25 - 10
= 1315
moonshotai/kimi-k2.5
moonshot
(100 - 10) * (10 - (75 - 50) / 25)
= 810
z-ai/glm-5
z-ai
75 * 10 + 100 - 50 + 25 - 10
= 815
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.