Released: 2026-05-24
Key:
Score Threshold:
google/gemini-3-flash-preview
(25 * (6 - 1)) - (3 * 2)
= 119
openai/gpt-4o
openai
(25 * 3) + (6 * 2) - 1
= 86
mistralai/mistral-medium-3
mistral
(25 * 6) - (3 * (3 + 2)) + 1
= 136
deepseek/deepseek-chat-v3-0324
deepseek
((25 * 6) - (3 + 1)) * 3
= 438
google/gemini-2.0-flash-001
(25 * 6) - (3 + 3 + 1 + 2)
= 141
anthropic/claude-sonnet-4.6
anthropic
25 * (6 - 1) - 3 - 3
= 119
z-ai/glm-5
z-ai
25 * (3 + 2) - 6
= 119
moonshotai/kimi-k2.5
moonshot
25 * (3 + 2) - 6
= 119
minimax/minimax-m2.5
minimax
25 * (3 + 2) - 6
= 119
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.