Released: 2026-07-09
Key:
Score Threshold:
google/gemini-3-flash-preview
((75 - 25 + 8) * 4) + 100 + 50
= 382
mistralai/mistral-medium-3
mistral
(100 * 50) - (75 + (25 * (8 + 4)))
= 4625
openai/gpt-4o
openai
(75 * 8) - (100 + 4)
= 496
anthropic/claude-sonnet-4.6
anthropic
((75 + 8) * 4) * (100 / 25) + 50
= 1378
deepseek/deepseek-chat-v3-0324
deepseek
(100 + 75) * (50 - 25) - (8 + 4)
= 4363
z-ai/glm-5
z-ai
(8*(50/25))*(100-75+4)
= 464
minimax/minimax-m2.5
minimax
8 * (100 / 50) * (25 + 4)
= 464
moonshotai/kimi-k2.5
moonshot
(100 + 8 * (50 / 25)) * 4
= 464
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.