Released: 2026-05-20
Key:
Score Threshold:
google/gemini-2.0-flash-001
(75 * (8 + 3)) - (50 / 25)
= 823
google/gemini-3-flash-preview
(75 * (50 + 25 + 1)) / (8 - 3)
= 1140
mistralai/mistral-medium-3
mistral
((75 + 50 + 1) * 8) + (25 * 3)
= 1083
deepseek/deepseek-chat-v3-0324
deepseek
((75 + 50) * (8 - 1)) + 3
= 878
anthropic/claude-sonnet-4.6
anthropic
75 * 8 + 25 * 3 - 50 + 1
= 626
minimax/minimax-m2.5
minimax
75 * (8 + 50 / 25) + 3 + 1
= 754
z-ai/glm-5
z-ai
(75 + 25) * 8 - 50 + 3 + 1
= 754
openai/gpt-4o
openai
(75 * 8) + (3 * 25) + 1
= 676
moonshotai/kimi-k2.5
moonshot
(75 + 25) * 8 - 50 + 3 + 1
= 754
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.