Released: 2026-05-08
Key:
Score Threshold:
google/gemini-2.0-flash-001
(75 * (10 - 1)) / (7 - 50/100)
= 103
google/gemini-3-flash-preview
(50 * 7) + (100 - 75)
= 375
deepseek/deepseek-chat-v3-0324
deepseek
(75 * (10 - (7 - 1)))
= 300
x-ai/grok-3-mini-beta
x-ai
(75 * (50 / 10))
= 375
minimax/minimax-m2.5
minimax
75 * (10 - 7) + 100 + 50
= 375
moonshotai/kimi-k2.5
moonshot
(100 - 75) * (10 + 7) - 50
= 375
openai/gpt-4o
openai
(50 * 7) + 75
= 425
anthropic/claude-3.7-sonnet
anthropic
(100 + 50) * (7 + 1) - 75
= 1125
z-ai/glm-5
z-ai
75 * (50 / 10)
= 375
anthropic/claude-sonnet-4.6
anthropic
75 * (7 - 1) - 50 + 100 - 10
= 490
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.