Released: 2026-05-09
Key:
Score Threshold:
mistralai/mistral-medium-3
mistral
(100 + 8) + (7 * (7 + 50) / 25)
= 123
deepseek/deepseek-chat-v3-0324
deepseek
100 + (50 / (25 / (7 - (8 / 7))))
= 111
openai/gpt-4o
openai
(7 + (100 / (50 / 25))) * (8 - 7)
= 57
minimax/minimax-m2.5
minimax
8 * (7 + 7)
= 112
x-ai/grok-3-mini-beta
x-ai
(7 + 7) * 8
= 112
google/gemini-2.0-flash-001
50 + 100 - 8 * 7 + 25
= 119
anthropic/claude-3.7-sonnet
anthropic
(25 + 7) * 8 - 50 - 7
= 199
moonshotai/kimi-k2.5
moonshot
8 * (7 + 7)
= 112
google/gemini-3-flash-preview
100 + (50 / 25) + 8 + (7 - 7)
= 110
z-ai/glm-5
z-ai
8 * (7 + 7)
= 112
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.