Released: 2026-06-20
Key:
Score Threshold:
openai/gpt-4o
openai
(100 * 6) - (10 / 5)
= 598
deepseek/deepseek-chat-v3-0324
deepseek
((100 * 6) - (10 + 5)) * (7 - 6)
= 585
anthropic/claude-sonnet-4.6
anthropic
100 * 6 - 7 * (6 - 5) + 10
= 603
z-ai/glm-5
z-ai
(100 * 6) - (10 + 5 + 6)
= 579
moonshotai/kimi-k2.5
moonshot
100 * 6 - (10 + 6 + 5)
= 579
minimax/minimax-m2.5
minimax
((100 - 7) * 6) + (10 + 6 + 5)
= 579
mistralai/mistral-medium-3
mistral
(100 + 6) * (6 - (10 - (7 - 5)))
= -212
google/gemini-3-flash-preview
(6 * 100) - ((6 * 5) - (10 - 7))
= 573
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.