Released: 2026-06-02
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
(100 - (7 / 7)) * (9 - 1) + 75
= 867
openai/gpt-4o
openai
(75 + 7) * 9 + 1 + 100 * 7
= 1439
anthropic/claude-sonnet-4.6
anthropic
((100 + 75) * 7) - 9 - 7 + 1
= 1210
deepseek/deepseek-chat-v3-0324
deepseek
((100 + 7 + 1) * 7) + 75
= 831
minimax/minimax-m2.5
minimax
(100 * 7) + 75 - (9 + 7 - 1)
= 760
z-ai/glm-5
z-ai
100 * 7 + 75 - 9 - 7 + 1
= 760
moonshotai/kimi-k2.5
moonshot
100*7 + 75 - 9 - 7 + 1
= 760
google/gemini-3-flash-preview
(100 * 7) + 75 - (9 + 7 - 1)
= 760
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.