Released: 2026-07-07
Key:
Score Threshold:
openai/gpt-4o
openai
((100 * 8) + 50) - (3 + 75)
= 772
mistralai/mistral-medium-3
mistral
((100 - 3) * 8) + (75 + 50 + 25)
= 926
deepseek/deepseek-chat-v3-0324
deepseek
(100 * 8) + (75 - 25) * (50 - 3)
= 3150
z-ai/glm-5
z-ai
(8 * 100) - (50 / 25)
= 798
minimax/minimax-m2.5
minimax
100 * 8 - (3 - (75 - 50) / 25)
= 798
moonshotai/kimi-k2.5
moonshot
(8 * 100) - (50 / 25)
= 798
google/gemini-3-flash-preview
(100 * 8) - (50 / 25)
= 798
anthropic/claude-sonnet-4.6
anthropic
8 * 100 - 3 + 75/25 + 50
= 850
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.