Released: 2026-05-29
Key:
Score Threshold:
google/gemini-2.0-flash-001
(75 * 2) + 8 + 7 - 3 - 100
= 62
mistralai/mistral-medium-3
mistral
(100 + 75) - (8 * (7 - (3 / 2)))
= 131
deepseek/deepseek-chat-v3-0324
deepseek
(75 * 2) + (100 + 8 + 7 - 3)
= 262
openai/gpt-4o
openai
((75 - 8) * 3) - 2
= 199
anthropic/claude-sonnet-4.6
anthropic
100 + 75 - 8 - 3 + 2 - 7
= 159
google/gemini-3-flash-preview
(100 + 75) - (8 + 2)
= 165
moonshotai/kimi-k2.5
moonshot
100 + 75 - 8 - 2
= 165
minimax/minimax-m2.5
minimax
100 + 75 - 7 - 3
= 165
z-ai/glm-5
z-ai
100 + 75 - 8 - 2
= 165
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.