Released: 2026-05-17
Key:
Score Threshold:
google/gemini-2.0-flash-001
(10 * 7 * 7) + 100 - 7 - 1
= 582
deepseek/deepseek-chat-v3-0324
deepseek
(((100 + 10) * (7 - (7 / 7))) + 1)
= 661
z-ai/glm-5
z-ai
(100 - 10 - 7 - 7 - 1) * 7
= 525
moonshotai/kimi-k2.5
moonshot
7 * (100 - (7 + 7 + 10 + 1))
= 525
minimax/minimax-m2.5
minimax
7 * (100 - (7 + 7 + 10 + 1))
= 525
mistralai/mistral-medium-3
mistral
((100 + 7) * (7 - 1)) - (10 - 7)
= 639
openai/gpt-4o
openai
(100 * 7) + 10 + 7 + 1
= 718
google/gemini-3-flash-preview
7 * (100 - (10 + 7 + 7 + 1))
= 525
anthropic/claude-sonnet-4.6
anthropic
100 * 7 / (7 + 7) * (1 + 10)
= 550
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.